{ "version": "1.0", "updated_at": "2026-10-13", "source_record_count": 550, "source": { "repo": "anomalyco/models.dev", "ref": "dev", "commit": "59aa52dbc09727fa6ead433b0285970ebc05ba82", "url": "https://github.com/anomalyco/models.dev", "immutable_url": "https://codeload.github.com/anomalyco/models.dev/tar.gz/59aa52dbc09727fa6ead433b0285970ebc05ba82", "path": "models/**/*.toml", "license": "MIT", "sha256": "31b92e3490e9970651be1e7d6efd7d012e9e5954694015e830f5dd0734598bae" }, "models": [ { "id": "model-ai21-jamba-large", "source_id": "ai21/jamba-large", "source_metadata": { "name": "Jamba Large", "description": "AI21's hybrid SSM-Transformer long-context model for enterprise agents and grounded generation", "family": "jamba", "release_date": "2025-07-01", "last_updated": "2025-07-01", "knowledge_cutoff": "2024-08-22", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/ai21labs/AI21-Jamba-Large-1.6" } ] } }, { "id": "model-ai21-jamba-mini", "source_id": "ai21/jamba-mini", "source_metadata": { "name": "Jamba Mini", "description": "AI21's efficient, lightweight hybrid SSM-Transformer model for a wide range of tasks", "family": "jamba", "release_date": "2026-01-01", "last_updated": "2026-01-01", "knowledge_cutoff": "2024-08-22", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/ai21labs/AI21-Jamba-Mini-1.6" } ] } }, { "id": "model-aion-labs-aion-2-0", "source_id": "aion-labs/aion-2.0", "source_metadata": { "name": "Aion-2.0", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "family": null, "release_date": "2026-02-23", "last_updated": "2026-02-23", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-aion-labs-aion-3-0", "source_id": "aion-labs/aion-3.0", "source_metadata": { "name": "Aion-3.0", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "family": null, "release_date": "2026-07-07", "last_updated": "2026-07-07", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-aion-labs-aion-3-0-mini", "source_id": "aion-labs/aion-3.0-mini", "source_metadata": { "name": "Aion-3.0-Mini", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "family": null, "release_date": "2026-07-07", "last_updated": "2026-07-07", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-aion-labs-aion-rp-llama-3-1-8b", "source_id": "aion-labs/aion-rp-llama-3.1-8b", "source_metadata": { "name": "Aion-RP 1.0 (8B)", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "family": "llama", "release_date": "2025-02-04", "last_updated": "2025-02-04", "knowledge_cutoff": "2023-12-31", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": false, "temperature": true }, "limits": { "context": 32768, "input": null, "output": 29491 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-aisingapore-gemma-sea-lion-v4-27b-it", "source_id": "aisingapore/gemma-sea-lion-v4-27b-it", "source_metadata": { "name": "Gemma-SEA-LION-v4-27B-IT", "description": "Gemma 3 27B tuned by AI Singapore for Southeast Asian languages and instruction following", "family": "gemma", "release_date": "2025-09-23", "last_updated": "2025-09-23", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 128000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/aisingapore/Gemma-SEA-LION-v4-27B-IT" } ] } }, { "id": "model-alibaba-qwen-flash", "source_id": "alibaba/qwen-flash", "source_metadata": { "name": "Qwen Flash", "description": "Efficient Qwen model for fast chat, extraction, and high-volume workloads", "family": "qwen", "release_date": "2025-07-28", "last_updated": "2025-07-28", "knowledge_cutoff": "2024-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen-image-2-1", "source_id": "alibaba/qwen-image-2.1", "source_metadata": { "name": "Qwen-Image-2.1", "description": "Unified text-to-image generation and image editing model with native RGBA transparency and reference-image editing", "family": "qwen", "release_date": "2026-09-14", "last_updated": "2026-09-21", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 8192, "input": null, "output": 0 }, "reported_open_weights": true, "reported_license": "qwen-research", "links": [ { "label": "Blog", "url": "https://qwen.ai/blog?id=qwen-image-2.1", "type": "announcement" }, { "label": "GitHub", "url": "https://github.com/QwenLM/Qwen-Image-2.1", "type": "docs" } ], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen-Image-2.1" } ] } }, { "id": "model-alibaba-qwen-max", "source_id": "alibaba/qwen-max", "source_metadata": { "name": "Qwen Max", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "family": "qwen", "release_date": "2024-04-03", "last_updated": "2025-01-25", "knowledge_cutoff": "2024-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 32768, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen-mt-plus", "source_id": "alibaba/qwen-mt-plus", "source_metadata": { "name": "Qwen MT Plus", "description": "Flagship Qwen translation model with terminology control and support for 92 languages", "family": "qwen", "release_date": "2025-07-24", "last_updated": "2025-07-24", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 16384, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen-omni-turbo", "source_id": "alibaba/qwen-omni-turbo", "source_metadata": { "name": "Qwen-Omni Turbo", "description": "Qwen omni model for text, vision, audio, and multimodal agent tasks", "family": "qwen", "release_date": "2025-01-19", "last_updated": "2025-03-26", "knowledge_cutoff": "2024-04", "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 32768, "input": null, "output": 2048 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen-plus", "source_id": "alibaba/qwen-plus", "source_metadata": { "name": "Qwen Plus", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "family": "qwen", "release_date": "2024-01-25", "last_updated": "2025-09-11", "knowledge_cutoff": "2024-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen-turbo", "source_id": "alibaba/qwen-turbo", "source_metadata": { "name": "Qwen Turbo", "description": "Efficient Qwen model for fast chat, extraction, and high-volume workloads", "family": "qwen", "release_date": "2024-11-01", "last_updated": "2025-04-28", "knowledge_cutoff": "2024-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 16384 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen-vl-max", "source_id": "alibaba/qwen-vl-max", "source_metadata": { "name": "Qwen-VL Max", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "family": "qwen", "release_date": "2024-04-08", "last_updated": "2025-08-13", "knowledge_cutoff": "2024-04", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen-vl-plus", "source_id": "alibaba/qwen-vl-plus", "source_metadata": { "name": "Qwen-VL Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "family": "qwen", "release_date": "2024-01-25", "last_updated": "2025-08-15", "knowledge_cutoff": "2024-04", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen2-5-vl-72b-instruct", "source_id": "alibaba/qwen2-5-vl-72b-instruct", "source_metadata": { "name": "Qwen2.5-VL 72B Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "family": "qwen", "release_date": "2024-09", "last_updated": "2024-09", "knowledge_cutoff": "2024-04", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct" } ] } }, { "id": "model-alibaba-qwen2-5-coder-0-5b", "source_id": "alibaba/qwen2.5-coder-0.5b", "source_metadata": { "name": "Qwen2.5-Coder-0.5B", "description": "Tiny open Qwen code model for lightweight completion and on-device coding", "family": "qwen", "release_date": "2024-11-12", "last_updated": "2024-11-12", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 32768, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": "Apache 2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B" } ] } }, { "id": "model-alibaba-qwen2-5-coder-32b-instruct", "source_id": "alibaba/qwen2.5-coder-32b-instruct", "source_metadata": { "name": "Qwen2.5-Coder-32B-Instruct", "description": "Open coding-focused Qwen model for code generation, repair, and repository reasoning", "family": "qwen", "release_date": "2024-11-12", "last_updated": "2024-11-12", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct" } ] } }, { "id": "model-alibaba-qwen3-235b-a22b", "source_id": "alibaba/qwen3-235b-a22b", "source_metadata": { "name": "Qwen3 235B-A22B", "description": "Large open Qwen MoE for multilingual reasoning, coding, and tool use", "family": "qwen", "release_date": "2025-04", "last_updated": "2025-04", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3-235B-A22B" } ] } }, { "id": "model-alibaba-qwen3-235b-a22b-instruct-2507", "source_id": "alibaba/qwen3-235b-a22b-instruct-2507", "source_metadata": { "name": "Qwen3 235B-A22B Instruct 2507", "description": "Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use", "family": "qwen", "release_date": "2025-07-21", "last_updated": "2025-07-21", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": "Apache 2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507" } ] } }, { "id": "model-alibaba-qwen3-30b-a3b", "source_id": "alibaba/qwen3-30b-a3b", "source_metadata": { "name": "Qwen3 30B A3B", "description": "Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning", "family": "qwen", "release_date": "2025-04-28", "last_updated": "2025-04-28", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3-30B-A3B" } ] } }, { "id": "model-alibaba-qwen3-32b", "source_id": "alibaba/qwen3-32b", "source_metadata": { "name": "Qwen3 32B", "description": "Dense open Qwen model for self-hosted chat, reasoning, and coding", "family": "qwen", "release_date": "2025-04", "last_updated": "2025-04", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3-32B" } ] } }, { "id": "model-alibaba-qwen3-coder-30b-a3b-instruct", "source_id": "alibaba/qwen3-coder-30b-a3b-instruct", "source_metadata": { "name": "Qwen3-Coder 30B-A3B Instruct", "description": "Smaller Qwen coder for efficient local agents and repo-level fixes", "family": "qwen", "release_date": "2025-04", "last_updated": "2025-04", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 65536 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct" } ] } }, { "id": "model-alibaba-qwen3-coder-480b-a35b-instruct", "source_id": "alibaba/qwen3-coder-480b-a35b-instruct", "source_metadata": { "name": "Qwen3-Coder 480B-A35B Instruct", "description": "Open Qwen coding heavyweight for repository reasoning and agentic engineering", "family": "qwen", "release_date": "2025-04", "last_updated": "2025-04", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 65536 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct" } ] } }, { "id": "model-alibaba-qwen3-coder-flash", "source_id": "alibaba/qwen3-coder-flash", "source_metadata": { "name": "Qwen3 Coder Flash", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "family": "qwen", "release_date": "2025-07-28", "last_updated": "2025-07-28", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-coder-next", "source_id": "alibaba/qwen3-coder-next", "source_metadata": { "name": "Qwen3 Coder Next", "description": "Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use", "family": "qwen", "release_date": "2026-02-03", "last_updated": "2026-02-03", "knowledge_cutoff": "2025-09", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 65536 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3-Coder-Next" } ] } }, { "id": "model-alibaba-qwen3-coder-plus", "source_id": "alibaba/qwen3-coder-plus", "source_metadata": { "name": "Qwen3 Coder Plus", "description": "Hosted Qwen coder for software agents, repo edits, and long-context code", "family": "qwen", "release_date": "2025-07-23", "last_updated": "2025-07-23", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-embedding-8b", "source_id": "alibaba/qwen3-embedding-8b", "source_metadata": { "name": "Qwen3 Embedding 8B", "description": "Multilingual text embedding model for retrieval, code search, classification, and clustering", "family": "qwen", "release_date": "2025-06-05", "last_updated": "2025-06-05", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text", "embedding" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 32768, "input": null, "output": 0 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3-Embedding-8B" } ] } }, { "id": "model-alibaba-qwen3-max", "source_id": "alibaba/qwen3-max", "source_metadata": { "name": "Qwen3 Max", "description": "Flagship Qwen3 model for coding agents, complex reasoning, and tool use", "family": "qwen", "release_date": "2025-09-23", "last_updated": "2025-09-23", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-max-preview", "source_id": "alibaba/qwen3-max-preview", "source_metadata": { "name": "Qwen3 Max Preview", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "family": "qwen", "release_date": "2025-09-05", "last_updated": "2025-09-23", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-next-80b-a3b-instruct", "source_id": "alibaba/qwen3-next-80b-a3b-instruct", "source_metadata": { "name": "Qwen3-Next 80B-A3B Instruct", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "family": "qwen", "release_date": "2025-09", "last_updated": "2025-09", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct" } ] } }, { "id": "model-alibaba-qwen3-next-80b-a3b-thinking", "source_id": "alibaba/qwen3-next-80b-a3b-thinking", "source_metadata": { "name": "Qwen3-Next 80B-A3B (Thinking)", "description": "Efficient Qwen thinking model for local reasoning, math, and coding agents", "family": "qwen", "release_date": "2025-09", "last_updated": "2025-09", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking" } ] } }, { "id": "model-alibaba-qwen3-omni-30b-a3b-thinking", "source_id": "alibaba/qwen3-omni-30b-a3b-thinking", "source_metadata": { "name": "Qwen3 Omni 30B A3B Thinking", "description": "Multimodal reasoning model accepting text, images, video, and audio with text output", "family": "qwen", "release_date": "2025-09-22", "last_updated": "2025-09-22", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 65536, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Thinking" } ] } }, { "id": "model-alibaba-qwen3-reranker-8b", "source_id": "alibaba/qwen3-reranker-8b", "source_metadata": { "name": "Qwen3 Reranker 8B", "description": "Multilingual query-document reranking model supporting more than 100 languages", "family": "qwen", "release_date": "2025-06-05", "last_updated": "2025-06-05", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 32768, "input": null, "output": 0 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3-Reranker-8B" } ] } }, { "id": "model-alibaba-qwen3-vl-235b-a22b-instruct", "source_id": "alibaba/qwen3-vl-235b-a22b-instruct", "source_metadata": { "name": "Qwen3 VL 235B A22B Instruct", "description": "Qwen vision-language instruct model for visual reasoning, documents, and agent tasks", "family": "qwen", "release_date": "2025-09-23", "last_updated": "2025-09-23", "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct" } ] } }, { "id": "model-alibaba-qwen3-vl-235b-a22b-thinking", "source_id": "alibaba/qwen3-vl-235b-a22b-thinking", "source_metadata": { "name": "Qwen3 VL 235B A22B Thinking", "description": "Qwen vision-language thinking model for visual reasoning, documents, and agent tasks", "family": "qwen", "release_date": "2025-09-23", "last_updated": "2025-09-23", "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Thinking" } ] } }, { "id": "model-alibaba-qwen3-vl-30b-a3b-instruct", "source_id": "alibaba/qwen3-vl-30b-a3b-instruct", "source_metadata": { "name": "Qwen3 VL 30B A3B Instruct", "description": "Open vision-language MoE model for image and video understanding, documents, and visual agents", "family": "qwen", "release_date": "2025-10-04", "last_updated": "2025-10-04", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct" } ] } }, { "id": "model-alibaba-qwen3-vl-flash", "source_id": "alibaba/qwen3-vl-flash", "source_metadata": { "name": "Qwen3 VL Flash (Alibaba Cloud)", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "family": null, "release_date": "2025-10-15", "last_updated": "2025-10-15", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-vl-plus", "source_id": "alibaba/qwen3-vl-plus", "source_metadata": { "name": "Qwen3-VL Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "family": "qwen", "release_date": "2025-09-23", "last_updated": "2025-09-23", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-5-122b-a10b", "source_id": "alibaba/qwen3.5-122b-a10b", "source_metadata": { "name": "Qwen3.5 122B-A10B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "family": "qwen", "release_date": "2026-02-23", "last_updated": "2026-02-23", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 65536 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B" } ] } }, { "id": "model-alibaba-qwen3-5-27b", "source_id": "alibaba/qwen3.5-27b", "source_metadata": { "name": "Qwen3.5 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "family": "qwen", "release_date": "2026-02-23", "last_updated": "2026-02-23", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 65536 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3.5-27B" } ] } }, { "id": "model-alibaba-qwen3-5-35b-a3b", "source_id": "alibaba/qwen3.5-35b-a3b", "source_metadata": { "name": "Qwen3.5 35B-A3B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "family": "qwen", "release_date": "2026-02-23", "last_updated": "2026-02-23", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 65536 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3.5-35B-A3B" } ] } }, { "id": "model-alibaba-qwen3-5-397b-a17b", "source_id": "alibaba/qwen3.5-397b-a17b", "source_metadata": { "name": "Qwen3.5 397B-A17B", "description": "Large open Qwen multimodal MoE for visual agents and long technical tasks", "family": "qwen", "release_date": "2026-02-15", "last_updated": "2026-02-15", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 65536 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3.5-397B-A17B" } ] } }, { "id": "model-alibaba-qwen3-5-9b", "source_id": "alibaba/qwen3.5-9b", "source_metadata": { "name": "Qwen3.5 9B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "family": "qwen", "release_date": "2026-02-23", "last_updated": "2026-02-23", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 65536 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3.5-9B" } ] } }, { "id": "model-alibaba-qwen3-5-flash", "source_id": "alibaba/qwen3.5-flash", "source_metadata": { "name": "Qwen3.5 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "family": "qwen", "release_date": "2026-02-23", "last_updated": "2026-02-23", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-5-plus", "source_id": "alibaba/qwen3.5-plus", "source_metadata": { "name": "Qwen3.5 Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "family": "qwen", "release_date": "2026-02-16", "last_updated": "2026-02-16", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-6-27b", "source_id": "alibaba/qwen3.6-27b", "source_metadata": { "name": "Qwen3.6 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "family": "qwen", "release_date": "2026-04-22", "last_updated": "2026-04-22", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 65536 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3.6-27B" } ] } }, { "id": "model-alibaba-qwen3-6-35b-a3b", "source_id": "alibaba/qwen3.6-35b-a3b", "source_metadata": { "name": "Qwen3.6 35B-A3B", "description": "Open multimodal Qwen MoE for local agents that need vision, audio, and code", "family": "qwen", "release_date": "2026-04-17", "last_updated": "2026-04-17", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 65536 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B" } ] } }, { "id": "model-alibaba-qwen3-6-flash", "source_id": "alibaba/qwen3.6-flash", "source_metadata": { "name": "Qwen3.6 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "family": "qwen3.6", "release_date": "2026-04-27", "last_updated": "2026-04-27", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-6-max-preview", "source_id": "alibaba/qwen3.6-max-preview", "source_metadata": { "name": "Qwen3.6 Max Preview", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "family": "qwen", "release_date": "2026-04-20", "last_updated": "2026-04-20", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-6-plus", "source_id": "alibaba/qwen3.6-plus", "source_metadata": { "name": "Qwen3.6 Plus", "description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks", "family": "qwen", "release_date": "2026-04-02", "last_updated": "2026-04-02", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-7-flash", "source_id": "alibaba/qwen3.7-flash", "source_metadata": { "name": "Qwen3.7 Flash", "description": "Lightweight multimodal Qwen model for high-throughput text, image, and video tasks", "family": "qwen", "release_date": "2026-07-15", "last_updated": "2026-07-15", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": 991808, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-7-max", "source_id": "alibaba/qwen3.7-max", "source_metadata": { "name": "Qwen3.7 Max", "description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks", "family": "qwen", "release_date": "2026-05-21", "last_updated": "2026-05-21", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-7-plus", "source_id": "alibaba/qwen3.7-plus", "source_metadata": { "name": "Qwen3.7 Plus", "description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding", "family": "qwen", "release_date": "2026-06-02", "last_updated": "2026-06-02", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 64000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-8-2-4t-a95b", "source_id": "alibaba/qwen3.8-2.4t-a95b", "source_metadata": { "name": "Qwen3.8 2.4T A95B", "description": "Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows", "family": "qwen", "release_date": "2026-08-12", "last_updated": "2026-08-12", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": "qwen3.8-max", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B" } ] } }, { "id": "model-alibaba-qwen3-8-27b", "source_id": "alibaba/qwen3.8-27b", "source_metadata": { "name": "Qwen3.8 27B", "description": "Dense 27B vision-language model for coding, agent tasks, and image and video understanding", "family": "qwen", "release_date": "2026-08-14", "last_updated": "2026-08-14", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3.8-27B" } ] } }, { "id": "model-alibaba-qwen3-8-flash", "source_id": "alibaba/qwen3.8-flash", "source_metadata": { "name": "Qwen3.8 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "family": "qwen", "release_date": "2026-08-26", "last_updated": "2026-08-26", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": null }, "limits": { "context": 1000000, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-8-flash-next", "source_id": "alibaba/qwen3.8-flash-next", "source_metadata": { "name": "Qwen3.8 Flash Next", "description": "Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding", "family": "qwen", "release_date": "2026-08-27", "last_updated": "2026-08-27", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": "qwen-community-1.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/Qwen3.8-Flash-Next" } ] } }, { "id": "model-alibaba-qwen3-8-max", "source_id": "alibaba/qwen3.8-max", "source_metadata": { "name": "Qwen3.8 Max", "description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows", "family": "qwen", "release_date": "2026-08-03", "last_updated": "2026-08-03", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-8-max-0902", "source_id": "alibaba/qwen3.8-max-0902", "source_metadata": { "name": "Qwen3.8 Max 0902", "description": "2026-09-02 upgraded snapshot of Qwen3.8 Max with stronger coding, collaborative agents, and multimodal document understanding", "family": "qwen", "release_date": "2026-09-02", "last_updated": "2026-09-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-8-max-preview", "source_id": "alibaba/qwen3.8-max-preview", "source_metadata": { "name": "Qwen3.8 Max Preview", "description": "Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows", "family": "qwen", "release_date": "2026-07-19", "last_updated": "2026-07-19", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-8-max-prime", "source_id": "alibaba/qwen3.8-max-prime", "source_metadata": { "name": "Qwen 3.8 Max Prime", "description": "High-throughput edition of Qwen3.8 Max for coding, professional work, multimodal understanding, and long-running agent workflows", "family": "qwen3.8-max", "release_date": "2026-09-23", "last_updated": "2026-09-23", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwen3-8-omni-flash", "source_id": "alibaba/qwen3.8-omni-flash", "source_metadata": { "name": "Qwen3.8 Omni Flash", "description": "Qwen omni model for text, vision, audio, and multimodal agent tasks", "family": "qwen", "release_date": "2026-09-17", "last_updated": "2026-09-17", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": null }, "limits": { "context": 1000000, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-alibaba-qwq-32b", "source_id": "alibaba/qwq-32b", "source_metadata": { "name": "QwQ 32B", "description": "Open reasoning model from the Qwen team for math, coding, and step-by-step problem solving", "family": "qwen", "release_date": "2025-03-05", "last_updated": "2025-03-05", "knowledge_cutoff": "2024-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Qwen/QwQ-32B" } ] } }, { "id": "model-alibaba-qwq-plus", "source_id": "alibaba/qwq-plus", "source_metadata": { "name": "QwQ Plus", "description": "Qwen reasoning model for deliberate problem solving, math, and coding", "family": "qwen", "release_date": "2025-03-05", "last_updated": "2025-03-05", "knowledge_cutoff": "2024-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-amazon-nova-2-lite", "source_id": "amazon/nova-2-lite", "source_metadata": { "name": "Nova 2 Lite", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "family": "nova", "release_date": "2025-12-02", "last_updated": "2025-12-01", "knowledge_cutoff": "2025-10", "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-amazon-nova-2-lite-v1", "source_id": "amazon/nova-2-lite-v1", "source_metadata": { "name": "Nova 2 Lite", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "family": "nova", "release_date": "2025-12-02", "last_updated": "2025-12-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 65535 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-amazon-nova-lite", "source_id": "amazon/nova-lite", "source_metadata": { "name": "Nova Lite", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "family": "nova-lite", "release_date": "2024-12-03", "last_updated": "2024-12-03", "knowledge_cutoff": "2024-10", "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 300000, "input": null, "output": 10000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-amazon-nova-lite-v1", "source_id": "amazon/nova-lite-v1", "source_metadata": { "name": "Nova Lite 1.0", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "family": "nova-lite", "release_date": "2024-12-05", "last_updated": "2024-12-05", "knowledge_cutoff": "2024-10-31", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 300000, "input": null, "output": 5120 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-amazon-nova-micro", "source_id": "amazon/nova-micro", "source_metadata": { "name": "Nova Micro", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "family": "nova-micro", "release_date": "2024-12-03", "last_updated": "2024-12-03", "knowledge_cutoff": "2024-10", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 10000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-amazon-nova-micro-v1", "source_id": "amazon/nova-micro-v1", "source_metadata": { "name": "Nova Micro 1.0", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "family": "nova-micro", "release_date": "2024-12-05", "last_updated": "2024-12-05", "knowledge_cutoff": "2024-10-31", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 5120 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-amazon-nova-premier", "source_id": "amazon/nova-premier", "source_metadata": { "name": "Nova Premier", "description": "Multimodal model for complex analysis, long-context understanding, tool use, and model distillation", "family": "nova", "release_date": "2025-04-30", "last_updated": "2025-04-30", "knowledge_cutoff": "2024-10", "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 10000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-amazon-nova-pro", "source_id": "amazon/nova-pro", "source_metadata": { "name": "Nova Pro", "description": "Flagship model for demanding analysis, coding, and production agent workflows", "family": "nova-pro", "release_date": "2024-12-03", "last_updated": "2024-12-03", "knowledge_cutoff": "2024-10", "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 300000, "input": null, "output": 10000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-amazon-nova-pro-v1", "source_id": "amazon/nova-pro-v1", "source_metadata": { "name": "Nova Pro 1.0", "description": "Flagship model for demanding analysis, coding, and production agent workflows", "family": "nova-pro", "release_date": "2024-12-05", "last_updated": "2024-12-05", "knowledge_cutoff": "2024-10-31", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 300000, "input": null, "output": 5120 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthracite-org-magnum-v4-72b", "source_id": "anthracite-org/magnum-v4-72b", "source_metadata": { "name": "Magnum v4 72B", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "family": null, "release_date": "2024-10-22", "last_updated": "2024-10-22", "knowledge_cutoff": "2024-06-30", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 32768, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-3-5-haiku-20241022", "source_id": "anthropic/claude-3-5-haiku-20241022", "source_metadata": { "name": "Claude Haiku 3.5", "description": "Fast Claude model for responsive assistance, classification, and lightweight agents", "family": "claude-haiku", "release_date": "2024-10-22", "last_updated": "2024-10-22", "knowledge_cutoff": "2024-07-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-3-5-sonnet-20241022", "source_id": "anthropic/claude-3-5-sonnet-20241022", "source_metadata": { "name": "Claude Sonnet 3.5 v2", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "family": "claude-sonnet", "release_date": "2024-10-22", "last_updated": "2024-10-22", "knowledge_cutoff": "2024-04-30", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-3-7-sonnet-20250219", "source_id": "anthropic/claude-3-7-sonnet-20250219", "source_metadata": { "name": "Claude Sonnet 3.7", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "family": "claude-sonnet", "release_date": "2025-02-19", "last_updated": "2025-02-19", "knowledge_cutoff": "2024-10-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 64000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-3-haiku-20240307", "source_id": "anthropic/claude-3-haiku-20240307", "source_metadata": { "name": "Claude Haiku 3", "description": "Legacy model retained for compatibility with older integrations", "family": "claude-haiku", "release_date": "2024-03-13", "last_updated": "2024-03-13", "knowledge_cutoff": "2023-08-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 4096 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-fable-5", "source_id": "anthropic/claude-fable-5", "source_metadata": { "name": "Claude Fable 5", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "family": "claude-fable", "release_date": "2026-06-09", "last_updated": "2026-06-09", "knowledge_cutoff": "2026-01-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": false }, "limits": { "context": 1000000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-fable-5-1", "source_id": "anthropic/claude-fable-5-1", "source_metadata": { "name": "Claude Fable 5.1", "description": "Claude model for demanding reasoning and long-horizon agentic work", "family": "claude-fable", "release_date": "2026-09-01", "last_updated": "2026-09-01", "knowledge_cutoff": "2026-06", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": false }, "limits": { "context": 1000000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-haiku-4-5", "source_id": "anthropic/claude-haiku-4-5", "source_metadata": { "name": "Claude Haiku 4.5 (latest)", "description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat", "family": "claude-haiku", "release_date": "2025-10-15", "last_updated": "2025-10-15", "knowledge_cutoff": "2025-02-28", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 64000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-haiku-4-5-20251001", "source_id": "anthropic/claude-haiku-4-5-20251001", "source_metadata": { "name": "Claude Haiku 4.5", "description": "Fast Claude model for responsive assistance, classification, and lightweight agents", "family": "claude-haiku", "release_date": "2025-10-15", "last_updated": "2025-10-15", "knowledge_cutoff": "2025-02-28", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 64000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-haiku-5-5", "source_id": "anthropic/claude-haiku-5-5", "source_metadata": { "name": "Claude Haiku 5.5", "description": "Fast Claude model for responsive assistance, classification, and lightweight agents", "family": "claude-haiku", "release_date": "2026-10-07", "last_updated": "2026-10-07", "knowledge_cutoff": "2026-06", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1000000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-mythos-5", "source_id": "anthropic/claude-mythos-5", "source_metadata": { "name": "Claude Mythos 5", "description": "Restricted Claude model for advanced cybersecurity and biology research workflows", "family": "claude-mythos", "release_date": "2026-06-09", "last_updated": "2026-06-09", "knowledge_cutoff": "2026-01-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1000000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-opus-4-0", "source_id": "anthropic/claude-opus-4-0", "source_metadata": { "name": "Claude Opus 4 (latest)", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "family": "claude-opus", "release_date": "2025-05-22", "last_updated": "2025-05-22", "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 32000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-opus-4-1", "source_id": "anthropic/claude-opus-4-1", "source_metadata": { "name": "Claude Opus 4.1 (latest)", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "family": "claude-opus", "release_date": "2025-08-05", "last_updated": "2025-08-05", "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 32000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-opus-4-1-20250805", "source_id": "anthropic/claude-opus-4-1-20250805", "source_metadata": { "name": "Claude Opus 4.1", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "family": "claude-opus", "release_date": "2025-08-05", "last_updated": "2025-08-05", "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 32000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-opus-4-20250514", "source_id": "anthropic/claude-opus-4-20250514", "source_metadata": { "name": "Claude Opus 4", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "family": "claude-opus", "release_date": "2025-05-22", "last_updated": "2025-05-22", "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 32000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-opus-4-5", "source_id": "anthropic/claude-opus-4-5", "source_metadata": { "name": "Claude Opus 4.5 (latest)", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "family": "claude-opus", "release_date": "2025-11-24", "last_updated": "2025-11-24", "knowledge_cutoff": "2025-05", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 64000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-opus-4-5-20251101", "source_id": "anthropic/claude-opus-4-5-20251101", "source_metadata": { "name": "Claude Opus 4.5", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "family": "claude-opus", "release_date": "2025-11-01", "last_updated": "2025-11-01", "knowledge_cutoff": "2025-05", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 64000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-opus-4-6", "source_id": "anthropic/claude-opus-4-6", "source_metadata": { "name": "Claude Opus 4.6", "description": "High-end Claude for difficult coding, planning, and slower expert reasoning", "family": "claude-opus", "release_date": "2026-02-05", "last_updated": "2026-03-13", "knowledge_cutoff": "2025-05-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-opus-4-7", "source_id": "anthropic/claude-opus-4-7", "source_metadata": { "name": "Claude Opus 4.7", "description": "Stronger Opus tier for advanced software work and high-stakes reasoning", "family": "claude-opus", "release_date": "2026-04-16", "last_updated": "2026-04-16", "knowledge_cutoff": "2026-01-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": false }, "limits": { "context": 1000000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-opus-4-8", "source_id": "anthropic/claude-opus-4-8", "source_metadata": { "name": "Claude Opus 4.8", "description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents", "family": "claude-opus", "release_date": "2026-05-28", "last_updated": "2026-05-28", "knowledge_cutoff": "2026-01", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": false }, "limits": { "context": 1000000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-opus-5", "source_id": "anthropic/claude-opus-5", "source_metadata": { "name": "Claude Opus 5", "description": "Strongest Claude Opus model for coding, agents, and professional work", "family": "claude-opus", "release_date": "2026-07-24", "last_updated": "2026-07-24", "knowledge_cutoff": "2026-05", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": false }, "limits": { "context": 1000000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-opus-5-5", "source_id": "anthropic/claude-opus-5-5", "source_metadata": { "name": "Claude Opus 5.5", "description": "Claude model for long-running agentic coding and knowledge work", "family": "claude-opus", "release_date": "2026-09-22", "last_updated": "2026-09-22", "knowledge_cutoff": "2026-06", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": false }, "limits": { "context": 1000000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-sonnet-4-0", "source_id": "anthropic/claude-sonnet-4-0", "source_metadata": { "name": "Claude Sonnet 4 (latest)", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "family": "claude-sonnet", "release_date": "2025-05-22", "last_updated": "2025-05-22", "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 64000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-sonnet-4-20250514", "source_id": "anthropic/claude-sonnet-4-20250514", "source_metadata": { "name": "Claude Sonnet 4", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "family": "claude-sonnet", "release_date": "2025-05-22", "last_updated": "2025-05-22", "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 64000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-sonnet-4-5", "source_id": "anthropic/claude-sonnet-4-5", "source_metadata": { "name": "Claude Sonnet 4.5 (latest)", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "family": "claude-sonnet", "release_date": "2025-09-29", "last_updated": "2025-09-29", "knowledge_cutoff": "2025-07-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 64000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-sonnet-4-5-20250929", "source_id": "anthropic/claude-sonnet-4-5-20250929", "source_metadata": { "name": "Claude Sonnet 4.5", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "family": "claude-sonnet", "release_date": "2025-09-29", "last_updated": "2025-09-29", "knowledge_cutoff": "2025-07-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 64000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-sonnet-4-6", "source_id": "anthropic/claude-sonnet-4-6", "source_metadata": { "name": "Claude Sonnet 4.6", "description": "Claude workhorse for coding agents, careful analysis, and production cost control", "family": "claude-sonnet", "release_date": "2026-02-17", "last_updated": "2026-03-13", "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 64000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-sonnet-5", "source_id": "anthropic/claude-sonnet-5", "source_metadata": { "name": "Claude Sonnet 5", "description": "Everyday Claude agent model for coding, planning, browsing, and general work", "family": "claude-sonnet", "release_date": "2026-06-30", "last_updated": "2026-06-30", "knowledge_cutoff": "2026-01-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": false }, "limits": { "context": 1000000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-anthropic-claude-sonnet-5-5", "source_id": "anthropic/claude-sonnet-5-5", "source_metadata": { "name": "Claude Sonnet 5.5", "description": "Fast Claude model for everyday coding, agents, and knowledge work", "family": "claude-sonnet", "release_date": "2026-09-28", "last_updated": "2026-09-28", "knowledge_cutoff": "2026-06", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": false }, "limits": { "context": 1000000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-apodex-apodex-1-1-mini", "source_id": "apodex/apodex-1.1-mini", "source_metadata": { "name": "Apodex 1.1 Mini", "description": "Open-weight 35B MoE model for long-horizon research, forecasting, and tool-assisted work", "family": null, "release_date": "2026-08-24", "last_updated": "2026-08-24", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/apodex/Apodex-1.1-mini" } ] } }, { "id": "model-arcee-ai-trinity-large-preview", "source_id": "arcee-ai/trinity-large-preview", "source_metadata": { "name": "Trinity Large Preview", "description": "Lightly post-trained 398B MoE chat model for creative work, long-context prompts, and tool-using agents", "family": "trinity", "release_date": "2026-01-27", "last_updated": "2026-05-28", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 524288, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": "OpenMDW-1.1", "links": [ { "label": "Model card", "url": "https://huggingface.co/arcee-ai/Trinity-Large-Preview", "type": "model_card" }, { "label": "Announcement", "url": "https://www.arcee.ai/blog/trinity-large", "type": "announcement" }, { "label": "License", "url": "https://huggingface.co/arcee-ai/Trinity-Large-Preview/blob/main/LICENSE", "type": "license" } ], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/arcee-ai/Trinity-Large-Preview", "format": "safetensors" } ] } }, { "id": "model-arcee-ai-trinity-large-thinking", "source_id": "arcee-ai/trinity-large-thinking", "source_metadata": { "name": "Trinity Large Thinking", "description": "Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use", "family": "trinity", "release_date": "2026-04-01", "last_updated": "2026-05-28", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 524288, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": "OpenMDW-1.1", "links": [ { "label": "Model card", "url": "https://huggingface.co/arcee-ai/Trinity-Large-Thinking", "type": "model_card" }, { "label": "Announcement", "url": "https://www.arcee.ai/blog/trinity-large-thinking", "type": "announcement" }, { "label": "License", "url": "https://huggingface.co/arcee-ai/Trinity-Large-Thinking/blob/main/LICENSE", "type": "license" } ], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/arcee-ai/Trinity-Large-Thinking", "format": "safetensors" } ] } }, { "id": "model-arcee-ai-trinity-mini", "source_id": "arcee-ai/trinity-mini", "source_metadata": { "name": "Trinity Mini", "description": "Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads", "family": "trinity", "release_date": "2025-12-01", "last_updated": "2026-05-28", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": "OpenMDW-1.1", "links": [ { "label": "Model card", "url": "https://huggingface.co/arcee-ai/Trinity-Mini", "type": "model_card" }, { "label": "Announcement", "url": "https://www.arcee.ai/blog/the-trinity-manifesto", "type": "announcement" }, { "label": "License", "url": "https://huggingface.co/arcee-ai/Trinity-Mini/blob/main/LICENSE", "type": "license" } ], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/arcee-ai/Trinity-Mini", "format": "safetensors" } ] } }, { "id": "model-arcee-ai-trinity-nano-preview", "source_id": "arcee-ai/trinity-nano-preview", "source_metadata": { "name": "Trinity Nano Preview", "description": "Experimental chat-tuned 6B MoE model with 1B active parameters for low-resource chat and instruction following", "family": "trinity", "release_date": "2025-12-01", "last_updated": "2026-05-28", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": "OpenMDW-1.1", "links": [ { "label": "Model card", "url": "https://huggingface.co/arcee-ai/Trinity-Nano-Preview", "type": "model_card" }, { "label": "Announcement", "url": "https://www.arcee.ai/blog/the-trinity-manifesto", "type": "announcement" }, { "label": "License", "url": "https://huggingface.co/arcee-ai/Trinity-Nano-Preview/blob/main/LICENSE", "type": "license" } ], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/arcee-ai/Trinity-Nano-Preview", "format": "safetensors" } ] } }, { "id": "model-baai-bge-m3", "source_id": "baai/bge-m3", "source_metadata": { "name": "BGE M3", "description": "Multilingual embedding model combining dense, sparse, and multi-vector retrieval", "family": "bge", "release_date": "2024-01-30", "last_updated": "2024-01-30", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text", "embedding" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 8192, "input": null, "output": 0 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/BAAI/bge-m3" } ] } }, { "id": "model-baai-bge-reranker-v2-m3", "source_id": "baai/bge-reranker-v2-m3", "source_metadata": { "name": "BGE Reranker V2 M3", "description": "Lightweight multilingual cross-encoder that scores query-document relevance", "family": "bge", "release_date": "2024-03-15", "last_updated": "2024-03-15", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 8192, "input": null, "output": 0 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/BAAI/bge-reranker-v2-m3" } ] } }, { "id": "model-baichuan-baichuan-m2-32b", "source_id": "baichuan/baichuan-m2-32b", "source_metadata": { "name": "Baichuan M2 32B", "description": "Open medical model trained for clinical reasoning and patient interaction with on, off, and auto thinking modes", "family": "baichuan", "release_date": "2025-08-13", "last_updated": "2025-08-13", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/baichuan-inc/Baichuan-M2-32B" } ] } }, { "id": "model-baidu-cobuddy", "source_id": "baidu/cobuddy", "source_metadata": { "name": "CoBuddy", "description": "Baidu Qianfan model optimized for code generation and tool-using coding agents", "family": null, "release_date": "2026-05-06", "last_updated": "2026-05-06", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-baidu-ernie-4-5-21b-a3b", "source_id": "baidu/ernie-4.5-21b-a3b", "source_metadata": { "name": "ERNIE 4.5 21B A3B", "description": "Open ERNIE text MoE with 21B total and 3B active parameters", "family": "ernie", "release_date": "2025-06-30", "last_updated": "2025-06-30", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8000 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-PT" } ] } }, { "id": "model-baidu-ernie-4-5-vl-424b-a47b", "source_id": "baidu/ernie-4.5-vl-424b-a47b", "source_metadata": { "name": "ERNIE 4.5 VL 424B A47B ", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "family": "ernie", "release_date": "2025-06-30", "last_updated": "2025-06-30", "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": false, "structured_output": false, "temperature": true }, "limits": { "context": 123000, "input": null, "output": 16000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-bytedance-seed-seed-1-6", "source_id": "bytedance-seed/seed-1-6", "source_metadata": { "name": "Seed 1.6", "description": "ByteDance Seed model for long-context reasoning, instruction following, and tool-assisted tasks", "family": "seed", "release_date": "2025-10-15", "last_updated": "2025-10-15", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 64000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-bytedance-seed-seed-1-6-flash", "source_id": "bytedance-seed/seed-1-6-flash", "source_metadata": { "name": "Seed 1.6 Flash", "description": "Low-latency ByteDance Seed model for high-throughput chat, extraction, and lightweight tool use", "family": "seed", "release_date": "2025-08-28", "last_updated": "2025-08-28", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 32000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-bytedance-seed-seed-1-6-vision", "source_id": "bytedance-seed/seed-1-6-vision", "source_metadata": { "name": "Seed 1.6 Vision", "description": "ByteDance Seed multimodal model for image understanding, visual reasoning, and tool-assisted tasks", "family": "seed", "release_date": "2025-08-15", "last_updated": "2025-08-15", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 32000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-bytedance-seed-seed-1-8", "source_id": "bytedance-seed/seed-1-8", "source_metadata": { "name": "Seed 1.8", "description": "ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows", "family": "seed", "release_date": "2025-12-28", "last_updated": "2025-12-28", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 64000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-bytedance-seed-seed-2-0-code", "source_id": "bytedance-seed/seed-2.0-code", "source_metadata": { "name": "Seed 2.0 Code", "description": "ByteDance Seed coding model for multimodal software engineering and long-running agents", "family": "seed", "release_date": "2026-02-14", "last_updated": "2026-02-14", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-bytedance-seed-seed-2-0-lite", "source_id": "bytedance-seed/seed-2.0-lite", "source_metadata": { "name": "Seed 2.0 Lite", "description": "Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation", "family": "seed", "release_date": "2026-02-14", "last_updated": "2026-02-14", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 32000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-bytedance-seed-seed-2-0-mini", "source_id": "bytedance-seed/seed-2.0-mini", "source_metadata": { "name": "Seed 2.0 Mini", "description": "Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks", "family": "seed", "release_date": "2026-02-14", "last_updated": "2026-02-14", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 32000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-bytedance-seed-seed-2-0-pro", "source_id": "bytedance-seed/seed-2.0-pro", "source_metadata": { "name": "Seed 2.0 Pro", "description": "Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows", "family": "seed", "release_date": "2026-02-14", "last_updated": "2026-02-14", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-bytedance-seed-seed-2-1-pro", "source_id": "bytedance-seed/seed-2.1-pro", "source_metadata": { "name": "Seed 2.1 Pro", "description": "Flagship ByteDance Seed 2.1 model for complex multimodal reasoning, coding, and agents", "family": "seed", "release_date": "2026-06-23", "last_updated": "2026-06-23", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 256000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-bytedance-seed-seed-2-1-turbo", "source_id": "bytedance-seed/seed-2.1-turbo", "source_metadata": { "name": "Seed 2.1 Turbo", "description": "Faster ByteDance Seed 2.1 model for multimodal reasoning and latency-sensitive agent workflows", "family": "seed", "release_date": "2026-06-23", "last_updated": "2026-06-23", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 256000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-bytedance-seed-seed-character", "source_id": "bytedance-seed/seed-character", "source_metadata": { "name": "Seed Character", "description": "ByteDance Seed model optimized for character-driven dialogue and consistent conversational behavior", "family": "seed", "release_date": "2026-06-23", "last_updated": "2026-06-23", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 256000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-bytedance-seed-seed-evolving", "source_id": "bytedance-seed/seed-evolving", "source_metadata": { "name": "Seed Evolving", "description": "Rolling ByteDance Seed model for rapidly updated reasoning, coding, and agent capabilities", "family": "seed", "release_date": "2026-06-23", "last_updated": "2026-06-23", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 256000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-bytedance-seed-seedance-2-0", "source_id": "bytedance-seed/seedance-2.0", "source_metadata": { "name": "Seedance 2.0", "description": "ByteDance unified multimodal audio-video model supporting text, image, video and audio references, editing, extension and synchronized stereo sound.", "family": "seed", "release_date": "2026-02-12", "last_updated": "2026-10-04", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "video", "audio" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": null }, "limits": { "context": 0, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [ { "url": "https://seed.bytedance.com/en/blog/seedance-2-0-official-launch", "type": "announcement" } ], "weights": [] } }, { "id": "model-bytedance-seed-seedance-2-5", "source_id": "bytedance-seed/seedance-2.5", "source_metadata": { "name": "Seedance 2.5", "description": "ByteDance multimodal audio-video model with up to 30-second single-pass generation, multi-round extension, reference inputs and timestamp-level editing.", "family": "seed", "release_date": "2026-07-31", "last_updated": "2026-10-04", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "video", "audio" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": null }, "limits": { "context": 0, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [ { "url": "https://seed.bytedance.com/en/blog/one-take-creation-flexible-referencing-introducing-seedance-2-5", "type": "announcement" } ], "weights": [] } }, { "id": "model-cognitivecomputations-dolphin-mistral-24b-venice-edition", "source_id": "cognitivecomputations/dolphin-mistral-24b-venice-edition", "source_metadata": { "name": "Uncensored", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "family": "mistral", "release_date": "2025-07-09", "last_updated": "2025-07-09", "knowledge_cutoff": "2024-04-30", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": false, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-cohere-c4ai-aya-expanse-32b", "source_id": "cohere/c4ai-aya-expanse-32b", "source_metadata": { "name": "Aya Expanse 32B", "description": "Open multilingual model optimized for generation across 23 languages", "family": null, "release_date": "2024-10-24", "last_updated": "2024-10-24", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4000 }, "reported_open_weights": true, "reported_license": "CC-BY-NC-4.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/aya-expanse-32b" } ] } }, { "id": "model-cohere-c4ai-aya-expanse-8b", "source_id": "cohere/c4ai-aya-expanse-8b", "source_metadata": { "name": "Aya Expanse 8B", "description": "Compact open multilingual model optimized for generation across 23 languages", "family": null, "release_date": "2024-10-24", "last_updated": "2024-10-24", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 8000, "input": null, "output": 4000 }, "reported_open_weights": true, "reported_license": "CC-BY-NC-4.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/aya-expanse-8b" } ] } }, { "id": "model-cohere-c4ai-aya-vision-32b", "source_id": "cohere/c4ai-aya-vision-32b", "source_metadata": { "name": "Aya Vision 32B", "description": "Open multilingual vision model for OCR, visual reasoning, and image question answering", "family": null, "release_date": "2025-03-04", "last_updated": "2025-05-14", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 16000, "input": null, "output": 4000 }, "reported_open_weights": true, "reported_license": "CC-BY-NC-4.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/aya-vision-32b" } ] } }, { "id": "model-cohere-c4ai-aya-vision-8b", "source_id": "cohere/c4ai-aya-vision-8b", "source_metadata": { "name": "Aya Vision 8B", "description": "Compact open multilingual vision model for OCR and visual question answering", "family": null, "release_date": "2025-03-04", "last_updated": "2025-05-14", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 16000, "input": null, "output": 4000 }, "reported_open_weights": true, "reported_license": "CC-BY-NC-4.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/aya-vision-8b" } ] } }, { "id": "model-cohere-command-a", "source_id": "cohere/command-a", "source_metadata": { "name": "Command A", "description": "Cohere command model for multilingual enterprise agents, tools, and chat", "family": "command-a", "release_date": "2025-03-13", "last_updated": "2025-03-13", "knowledge_cutoff": "2024-08-31", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-cohere-command-a-03-2025", "source_id": "cohere/command-a-03-2025", "source_metadata": { "name": "Command A", "description": "Cohere command model for multilingual enterprise agents, tools, and chat", "family": "command-a", "release_date": "2025-03-13", "last_updated": "2025-03-13", "knowledge_cutoff": "2024-06-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 8000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/c4ai-command-a-03-2025" } ] } }, { "id": "model-cohere-command-a-plus-05-2026", "source_id": "cohere/command-a-plus-05-2026", "source_metadata": { "name": "Command A Plus", "description": "Cohere's stronger command model for multilingual agents and enterprise workflows", "family": "command-a", "release_date": "2026-05-20", "last_updated": "2026-06-09", "knowledge_cutoff": "2025-04-01", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 64000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-cohere-command-a-reasoning-08-2025", "source_id": "cohere/command-a-reasoning-08-2025", "source_metadata": { "name": "Command A Reasoning", "description": "Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows", "family": "command-a", "release_date": "2025-08-21", "last_updated": "2025-08-21", "knowledge_cutoff": "2024-06-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 32000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/c4ai-command-a-reasoning-08-2025" } ] } }, { "id": "model-cohere-command-a-translate-08-2025", "source_id": "cohere/command-a-translate-08-2025", "source_metadata": { "name": "Command A Translate", "description": "Translation model for multilingual conversion, localization, and cross-language workflows", "family": "command-a", "release_date": "2025-08-28", "last_updated": "2025-08-28", "knowledge_cutoff": "2024-06-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 8000, "input": null, "output": 8000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/c4ai-command-a-translate-08-2025" } ] } }, { "id": "model-cohere-command-a-vision-07-2025", "source_id": "cohere/command-a-vision-07-2025", "source_metadata": { "name": "Command A Vision", "description": "Cohere vision model for multilingual document analysis, OCR, and image understanding", "family": "command-a", "release_date": "2025-07-31", "last_updated": "2025-07-31", "knowledge_cutoff": "2024-06-01", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 8000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/c4ai-command-a-vision-07-2025" } ] } }, { "id": "model-cohere-command-r-08-2024", "source_id": "cohere/command-r-08-2024", "source_metadata": { "name": "Command R", "description": "Cohere retrieval model for long-context chat and enterprise RAG workflows", "family": "command-r", "release_date": "2024-08-30", "last_updated": "2024-08-30", "knowledge_cutoff": "2024-06-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/c4ai-command-r-08-2024" } ] } }, { "id": "model-cohere-command-r-plus-08-2024", "source_id": "cohere/command-r-plus-08-2024", "source_metadata": { "name": "Command R+", "description": "Cohere's RAG workhorse for long-context enterprise search and tool use", "family": "command-r", "release_date": "2024-08-30", "last_updated": "2024-08-30", "knowledge_cutoff": "2024-06-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/c4ai-command-r-plus-08-2024" } ] } }, { "id": "model-cohere-command-r7b-12-2024", "source_id": "cohere/command-r7b-12-2024", "source_metadata": { "name": "Command R7B", "description": "Cohere retrieval model for long-context chat and enterprise RAG workflows", "family": "command-r", "release_date": "2024-12-02", "last_updated": "2024-12-02", "knowledge_cutoff": "2024-06-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/c4ai-command-r7b-12-2024" } ] } }, { "id": "model-cohere-command-r7b-arabic-02-2025", "source_id": "cohere/command-r7b-arabic-02-2025", "source_metadata": { "name": "Command R7B Arabic", "description": "Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge", "family": "command-r", "release_date": "2025-02-27", "last_updated": "2025-02-27", "knowledge_cutoff": "2024-06-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/c4ai-command-r7b-arabic-02-2025" } ] } }, { "id": "model-cohere-north-mini-code-1-0", "source_id": "cohere/north-mini-code-1-0", "source_metadata": { "name": "North Mini Code", "description": "Cohere coding model for practical software engineering and agentic edits", "family": "north", "release_date": "2026-06-09", "last_updated": "2026-06-09", "knowledge_cutoff": "2025-09-23", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 64000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-cohere-north-small-translate-1-0", "source_id": "cohere/north-small-translate-1-0", "source_metadata": { "name": "North Small Translate", "description": "Open-weight translation model for more than 50 languages and locale variants", "family": "north", "release_date": "2026-09-09", "last_updated": "2026-09-09", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 16000, "input": null, "output": 16000 }, "reported_open_weights": true, "reported_license": "CC-BY-NC-4.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/North-Small-Translate-1.0" } ] } }, { "id": "model-cohere-tiny-aya-earth", "source_id": "cohere/tiny-aya-earth", "source_metadata": { "name": "Tiny Aya Earth", "description": "Compact multilingual model specialized for West Asian and African languages", "family": null, "release_date": "2026-02-17", "last_updated": "2026-02-17", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 8000, "input": null, "output": 8000 }, "reported_open_weights": true, "reported_license": "CC-BY-NC-4.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/tiny-aya-earth" } ] } }, { "id": "model-cohere-tiny-aya-fire", "source_id": "cohere/tiny-aya-fire", "source_metadata": { "name": "Tiny Aya Fire", "description": "Compact multilingual model specialized for South Asian languages", "family": null, "release_date": "2026-02-17", "last_updated": "2026-02-17", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 8000, "input": null, "output": 8000 }, "reported_open_weights": true, "reported_license": "CC-BY-NC-4.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/tiny-aya-fire" } ] } }, { "id": "model-cohere-tiny-aya-global", "source_id": "cohere/tiny-aya-global", "source_metadata": { "name": "Tiny Aya Global", "description": "Compact multilingual model balanced across 70 languages and regions", "family": null, "release_date": "2026-02-17", "last_updated": "2026-02-17", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 8000, "input": null, "output": 8000 }, "reported_open_weights": true, "reported_license": "CC-BY-NC-4.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/tiny-aya-global" } ] } }, { "id": "model-cohere-tiny-aya-water", "source_id": "cohere/tiny-aya-water", "source_metadata": { "name": "Tiny Aya Water", "description": "Compact multilingual model specialized for European and Asia-Pacific languages", "family": null, "release_date": "2026-02-17", "last_updated": "2026-02-17", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 8000, "input": null, "output": 8000 }, "reported_open_weights": true, "reported_license": "CC-BY-NC-4.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/CohereLabs/tiny-aya-water" } ] } }, { "id": "model-deepreinforce-ornith-1-0-31b", "source_id": "deepreinforce/ornith-1.0-31b", "source_metadata": { "name": "Ornith 1.0 31B", "description": "Open coding-reasoning model for repository tasks and self-improving agents", "family": "ornith", "release_date": "2026-06-25", "last_updated": "2026-06-25", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": null }, "reported_open_weights": true, "reported_license": "MIT", "links": [ { "label": "Announcement", "url": "https://deep-reinforce.com/ornith_1_0.html", "type": "announcement" } ], "weights": [] } }, { "id": "model-deepreinforce-ornith-1-0-35b", "source_id": "deepreinforce/ornith-1.0-35b", "source_metadata": { "name": "Ornith 1.0 35B", "description": "Large coding-reasoning model for agentic software tasks and RL search", "family": "ornith", "release_date": "2026-06-25", "last_updated": "2026-06-25", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": null }, "reported_open_weights": true, "reported_license": "MIT", "links": [ { "label": "Model card", "url": "https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B", "type": "model_card" }, { "label": "Announcement", "url": "https://deep-reinforce.com/ornith_1_0.html", "type": "announcement" } ], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B" } ] } }, { "id": "model-deepreinforce-ornith-1-0-397b", "source_id": "deepreinforce/ornith-1.0-397b", "source_metadata": { "name": "Ornith 1.0 397B", "description": "Large coding-reasoning model for agentic software tasks and RL search", "family": "ornith", "release_date": "2026-06-25", "last_updated": "2026-06-25", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": null }, "reported_open_weights": true, "reported_license": "MIT", "links": [ { "label": "Model card", "url": "https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B", "type": "model_card" }, { "label": "Announcement", "url": "https://deep-reinforce.com/ornith_1_0.html", "type": "announcement" } ], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B" }, { "label": "Hugging Face (FP8)", "url": "https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B-FP8", "quantization": "fp8" } ] } }, { "id": "model-deepreinforce-ornith-1-0-9b", "source_id": "deepreinforce/ornith-1.0-9b", "source_metadata": { "name": "Ornith 1.0 9B", "description": "Open coding-reasoning model for repository tasks and self-improving agents", "family": "ornith", "release_date": "2026-06-25", "last_updated": "2026-06-25", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": null }, "reported_open_weights": true, "reported_license": "MIT", "links": [ { "label": "Model card", "url": "https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B", "type": "model_card" }, { "label": "Announcement", "url": "https://deep-reinforce.com/ornith_1_0.html", "type": "announcement" } ], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B" } ] } }, { "id": "model-deepreinforce-ornith-1-5-35b-a3b", "source_id": "deepreinforce/ornith-1.5-35b-a3b", "source_metadata": { "name": "Ornith 1.5 35B A3B", "description": "Mixture-of-experts coding-reasoning model for agentic software tasks, tool use, and image understanding", "family": "ornith", "release_date": "2026-08-18", "last_updated": "2026-08-23", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": null }, "reported_open_weights": true, "reported_license": "MIT", "links": [ { "label": "Model card", "url": "https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B", "type": "model_card" } ], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B" } ] } }, { "id": "model-deepseek-deepseek-chat", "source_id": "deepseek/deepseek-chat", "source_metadata": { "name": "DeepSeek Chat", "description": "DeepSeek chat model for instruction following, coding, and analysis", "family": "deepseek", "release_date": "2025-12-01", "last_updated": "2026-02-28", "knowledge_cutoff": "2025-09", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 384000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2" } ] } }, { "id": "model-deepseek-deepseek-chat-v3-0324", "source_id": "deepseek/deepseek-chat-v3-0324", "source_metadata": { "name": "DeepSeek V3 0324", "description": "DeepSeek chat model for instruction following, coding, and analysis", "family": "deepseek", "release_date": "2025-03-24", "last_updated": "2025-03-24", "knowledge_cutoff": "2024-07-31", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 163840, "input": null, "output": 147456 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-deepseek-deepseek-chat-v3-1", "source_id": "deepseek/deepseek-chat-v3.1", "source_metadata": { "name": "DeepSeek V3.1", "description": "DeepSeek chat model for instruction following, coding, and analysis", "family": "deepseek", "release_date": "2025-08-21", "last_updated": "2025-08-21", "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 163840, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-deepseek-deepseek-ocr-2", "source_id": "deepseek/deepseek-ocr-2", "source_metadata": { "name": "DeepSeek OCR 2", "description": "High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes", "family": null, "release_date": "2026-01-27", "last_updated": "2026-01-27", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": null }, "limits": { "context": 8192, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-deepseek-deepseek-r1", "source_id": "deepseek/deepseek-r1", "source_metadata": { "name": "DeepSeek-R1", "description": "Classic open reasoning model for transparent math, coding, and deliberate problem solving", "family": "deepseek-thinking", "release_date": "2025-01-20", "last_updated": "2025-05-29", "knowledge_cutoff": "2024-07", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-R1" } ] } }, { "id": "model-deepseek-deepseek-r1-0528", "source_id": "deepseek/deepseek-r1-0528", "source_metadata": { "name": "DeepSeek R1 0528", "description": "May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning", "family": "deepseek-thinking", "release_date": "2025-05-28", "last_updated": "2025-05-28", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 163840, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528" } ] } }, { "id": "model-deepseek-deepseek-r1-0528-qwen3-8b", "source_id": "deepseek/deepseek-r1-0528-qwen3-8b", "source_metadata": { "name": "DeepSeek R1 0528 Qwen3 8B", "description": "DeepSeek R1 0528 distilled into Qwen3 8B for mathematics, coding, and reasoning", "family": "deepseek-thinking", "release_date": "2025-05-29", "last_updated": "2025-05-29", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 32000 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B" } ] } }, { "id": "model-deepseek-deepseek-r1-distill-qwen-32b", "source_id": "deepseek/deepseek-r1-distill-qwen-32b", "source_metadata": { "name": "DeepSeek-R1-Distill-Qwen-32B", "description": "R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving", "family": "deepseek-thinking", "release_date": "2025-01-20", "last_updated": "2025-01-20", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B" } ] } }, { "id": "model-deepseek-deepseek-reasoner", "source_id": "deepseek/deepseek-reasoner", "source_metadata": { "name": "DeepSeek Reasoner", "description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools", "family": "deepseek-thinking", "release_date": "2025-12-01", "last_updated": "2026-02-28", "knowledge_cutoff": "2025-09", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 384000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2" } ] } }, { "id": "model-deepseek-deepseek-v3", "source_id": "deepseek/deepseek-v3", "source_metadata": { "name": "DeepSeek-V3", "description": "Open DeepSeek MoE chat model for coding, math, and general reasoning", "family": "deepseek", "release_date": "2024-12-26", "last_updated": "2024-12-26", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": "DeepSeek Model License", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3" } ] } }, { "id": "model-deepseek-deepseek-v3-0324", "source_id": "deepseek/deepseek-v3-0324", "source_metadata": { "name": "DeepSeek V3 0324", "description": "March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding", "family": "deepseek", "release_date": "2025-03-24", "last_updated": "2025-03-24", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 163840, "input": null, "output": 163840 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Model weights", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3-0324", "format": "safetensors" } ] } }, { "id": "model-deepseek-deepseek-v3-1", "source_id": "deepseek/deepseek-v3.1", "source_metadata": { "name": "DeepSeek-V3.1", "description": "Hybrid-reasoning DeepSeek model with thinking and non-thinking modes", "family": "deepseek", "release_date": "2025-08-21", "last_updated": "2025-08-21", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": "MIT License", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1" } ] } }, { "id": "model-deepseek-deepseek-v3-2", "source_id": "deepseek/deepseek-v3.2", "source_metadata": { "name": "DeepSeek V3.2", "description": "Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use", "family": "deepseek", "release_date": "2025-12-01", "last_updated": "2025-12-01", "knowledge_cutoff": "2024-07", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 64000 }, "reported_open_weights": true, "reported_license": "MIT License", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2" } ] } }, { "id": "model-deepseek-deepseek-v4-flash", "source_id": "deepseek/deepseek-v4-flash", "source_metadata": { "name": "DeepSeek V4 Flash", "description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work", "family": "deepseek-flash", "release_date": "2026-04-24", "last_updated": "2026-04-24", "knowledge_cutoff": "2025-05", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 384000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash" } ] } }, { "id": "model-deepseek-deepseek-v4-flash-0423", "source_id": "deepseek/deepseek-v4-flash-0423", "source_metadata": { "name": "DeepSeek V4 Flash 0423", "description": "Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads", "family": "deepseek-flash", "release_date": "2026-04-23", "last_updated": "2026-04-23", "knowledge_cutoff": "2025-05", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 384000 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash" } ] } }, { "id": "model-deepseek-deepseek-v4-flash-0731", "source_id": "deepseek/deepseek-v4-flash-0731", "source_metadata": { "name": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "family": "deepseek-flash", "release_date": "2026-07-31", "last_updated": "2026-07-31", "knowledge_cutoff": "2025-05", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 384000 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731" } ] } }, { "id": "model-deepseek-deepseek-v4-flash-vision-exp", "source_id": "deepseek/deepseek-v4-flash-vision-exp", "source_metadata": { "name": "DeepSeek V4 Flash Vision Exp", "description": "Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work", "family": "deepseek-flash", "release_date": "2026-08-21", "last_updated": "2026-09-01", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 384000 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp" } ] } }, { "id": "model-deepseek-deepseek-v4-pro", "source_id": "deepseek/deepseek-v4-pro", "source_metadata": { "name": "DeepSeek V4 Pro", "description": "Open MoE flagship with million-token context for coding and long agent runs", "family": "deepseek-thinking", "release_date": "2026-04-24", "last_updated": "2026-04-24", "knowledge_cutoff": "2025-05", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 384000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro" } ] } }, { "id": "model-deepseek-deepseek-v4-pro-0423", "source_id": "deepseek/deepseek-v4-pro-0423", "source_metadata": { "name": "DeepSeek V4 Pro 0423", "description": "DeepSeek V4 Pro initial snapshot with million-token context and support for thinking and non-thinking modes", "family": "deepseek-thinking", "release_date": "2026-04-23", "last_updated": "2026-04-23", "knowledge_cutoff": "2025-05", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 384000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-deepseek-deepseek-v4-pro-0813", "source_id": "deepseek/deepseek-v4-pro-0813", "source_metadata": { "name": "DeepSeek V4 Pro 0813", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "family": "deepseek-thinking", "release_date": "2026-08-12", "last_updated": "2026-08-22", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 384000 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813" } ] } }, { "id": "model-deepseek-deepseek-v4-1-flash", "source_id": "deepseek/deepseek-v4.1-flash", "source_metadata": { "name": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "family": "deepseek-flash", "release_date": "2026-09-10", "last_updated": "2026-09-10", "knowledge_cutoff": "2025-05", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 384000 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash" } ] } }, { "id": "model-google-deep-research-max-preview-04-2026", "source_id": "google/deep-research-max-preview-04-2026", "source_metadata": { "name": "Deep Research Max Preview", "description": "Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports", "family": "gemini-pro", "release_date": "2026-04-21", "last_updated": "2026-04-21", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text", "image" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": false }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-deep-research-preview-04-2026", "source_id": "google/deep-research-preview-04-2026", "source_metadata": { "name": "Gemini Deep Research Preview", "description": "Agentic model for autonomous multi-step research, synthesis, and cited reports", "family": "gemini-pro", "release_date": "2026-04-21", "last_updated": "2026-04-21", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text", "image" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": false }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-diffusiongemma-26b-a4b-it", "source_id": "google/diffusiongemma-26b-a4b-it", "source_metadata": { "name": "DiffusionGemma 26B A4B IT", "description": "Gemma 4 based discrete text diffusion model for fast chat, reasoning, and tool use", "family": "gemma", "release_date": "2026-06-09", "last_updated": "2026-07-15", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": "Apache 2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/google/diffusiongemma-26B-A4B-it" } ] } }, { "id": "model-google-gemini-2-0-flash", "source_id": "google/gemini-2.0-flash", "source_metadata": { "name": "Gemini 2.0 Flash", "description": "Earlier Gemini Flash workhorse for responsive multimodal apps and tool use", "family": "gemini-flash", "release_date": "2024-12-11", "last_updated": "2024-12-11", "knowledge_cutoff": "2024-06", "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-2-0-flash-lite", "source_id": "google/gemini-2.0-flash-lite", "source_metadata": { "name": "Gemini 2.0 Flash-Lite", "description": "Low-latency Gemini model for high-volume multimodal and agent workloads", "family": "gemini-flash-lite", "release_date": "2024-12-11", "last_updated": "2024-12-11", "knowledge_cutoff": "2024-06", "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-2-5-computer-use-preview-10-2025", "source_id": "google/gemini-2.5-computer-use-preview-10-2025", "source_metadata": { "name": "Gemini 2.5 Computer Use Preview", "description": "Specialized Gemini 2.5 model for browser-control agents that automate UI tasks", "family": "gemini-pro", "release_date": "2025-10-07", "last_updated": "2025-10-07", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 64000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-2-5-flash", "source_id": "google/gemini-2.5-flash", "source_metadata": { "name": "Gemini 2.5 Flash", "description": "Fast Gemini workhorse for multimodal apps where latency and price matter", "family": "gemini-flash", "release_date": "2025-06-17", "last_updated": "2025-06-17", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-2-5-flash-image", "source_id": "google/gemini-2.5-flash-image", "source_metadata": { "name": "Nano Banana", "description": "Nano Banana image model for fast generation, edits, and character-consistent assets", "family": "gemini-flash", "release_date": "2025-08-26", "last_updated": "2025-08-26", "knowledge_cutoff": "2024-06", "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 32768, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-2-5-flash-lite", "source_id": "google/gemini-2.5-flash-lite", "source_metadata": { "name": "Gemini 2.5 Flash-Lite", "description": "Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents", "family": "gemini-flash-lite", "release_date": "2025-06-17", "last_updated": "2025-06-17", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-2-5-flash-tts", "source_id": "google/gemini-2.5-flash-tts", "source_metadata": { "name": "Gemini 2.5 Flash TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "family": "gemini-flash", "release_date": "2025-09-30", "last_updated": "2025-12-10", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 32768, "input": null, "output": 16384 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-2-5-pro", "source_id": "google/gemini-2.5-pro", "source_metadata": { "name": "Gemini 2.5 Pro", "description": "Google's proven reasoning model for coding, math, and multimodal analysis", "family": "gemini-pro", "release_date": "2025-06-17", "last_updated": "2025-06-17", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-2-5-pro-preview", "source_id": "google/gemini-2.5-pro-preview", "source_metadata": { "name": "Gemini 2.5 Pro Preview 06-05", "description": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis", "family": "gemini", "release_date": "2025-06-05", "last_updated": "2025-06-05", "knowledge_cutoff": "2025-01-31", "modalities": { "input": [ "pdf", "image", "text", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-2-5-pro-tts", "source_id": "google/gemini-2.5-pro-tts", "source_metadata": { "name": "Gemini 2.5 Pro TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "family": "gemini-pro", "release_date": "2025-09-30", "last_updated": "2025-12-10", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 32768, "input": null, "output": 16384 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-flash-preview", "source_id": "google/gemini-3-flash-preview", "source_metadata": { "name": "Gemini 3 Flash Preview", "description": "New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs", "family": "gemini-flash", "release_date": "2025-12-17", "last_updated": "2025-12-17", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-pro-image", "source_id": "google/gemini-3-pro-image", "source_metadata": { "name": "Nano Banana Pro", "description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits", "family": "gemini-pro", "release_date": "2026-05-28", "last_updated": "2026-05-28", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 65536, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-pro-image-preview", "source_id": "google/gemini-3-pro-image-preview", "source_metadata": { "name": "Nano Banana Pro Preview", "description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits", "family": "gemini-pro", "release_date": "2025-11-20", "last_updated": "2025-11-20", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 65536, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-pro-preview", "source_id": "google/gemini-3-pro-preview", "source_metadata": { "name": "Gemini 3 Pro Preview", "description": "Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts", "family": "gemini-pro", "release_date": "2025-11-18", "last_updated": "2025-11-18", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-1-flash-image", "source_id": "google/gemini-3.1-flash-image", "source_metadata": { "name": "Nano Banana 2", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "family": "gemini-flash", "release_date": "2026-05-28", "last_updated": "2026-05-28", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text", "image" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-1-flash-image-preview", "source_id": "google/gemini-3.1-flash-image-preview", "source_metadata": { "name": "Nano Banana 2 Preview", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "family": "gemini-flash", "release_date": "2026-02-26", "last_updated": "2026-02-26", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text", "image" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 65536, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-1-flash-lite", "source_id": "google/gemini-3.1-flash-lite", "source_metadata": { "name": "Gemini 3.1 Flash Lite", "description": "Low-latency Gemini model for high-volume multimodal and agent workloads", "family": "gemini-flash-lite", "release_date": "2026-05-07", "last_updated": "2026-05-07", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-1-flash-lite-image", "source_id": "google/gemini-3.1-flash-lite-image", "source_metadata": { "name": "Nano Banana 2 Lite", "description": "Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing", "family": "gemini-flash-lite", "release_date": "2026-06-30", "last_updated": "2026-06-30", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 65536, "input": null, "output": 4096 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-1-flash-lite-preview", "source_id": "google/gemini-3.1-flash-lite-preview", "source_metadata": { "name": "Gemini 3.1 Flash Lite Preview", "description": "Low-latency Gemini model for high-volume multimodal and agent workloads", "family": "gemini-flash-lite", "release_date": "2026-03-03", "last_updated": "2026-03-03", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-1-flash-live-preview", "source_id": "google/gemini-3.1-flash-live-preview", "source_metadata": { "name": "Gemini 3.1 Flash Live Preview", "description": "High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications", "family": "gemini-flash", "release_date": "2026-03-26", "last_updated": "2026-03-26", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text", "audio" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-1-flash-tts-preview", "source_id": "google/gemini-3.1-flash-tts-preview", "source_metadata": { "name": "Gemini 3.1 Flash TTS Preview", "description": "Low-latency speech generation with steerable prompts and expressive audio tags", "family": "gemini-flash", "release_date": "2026-04-15", "last_updated": "2026-04-15", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 8192, "input": null, "output": 16384 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-1-pro-preview", "source_id": "google/gemini-3.1-pro-preview", "source_metadata": { "name": "Gemini 3.1 Pro Preview", "description": "Reasoning-first Gemini preview for agentic coding and complex problem solving", "family": "gemini-pro", "release_date": "2026-02-19", "last_updated": "2026-02-19", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-1-pro-preview-customtools", "source_id": "google/gemini-3.1-pro-preview-customtools", "source_metadata": { "name": "Gemini 3.1 Pro Preview Custom Tools", "description": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis", "family": "gemini-pro", "release_date": "2026-02-19", "last_updated": "2026-02-19", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-5-flash", "source_id": "google/gemini-3.5-flash", "source_metadata": { "name": "Gemini 3.5 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "family": "gemini-flash", "release_date": "2026-05-19", "last_updated": "2026-05-19", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-5-flash-lite", "source_id": "google/gemini-3.5-flash-lite", "source_metadata": { "name": "Gemini 3.5 Flash Lite", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "family": "gemini-flash-lite", "release_date": "2026-07-21", "last_updated": "2026-07-21", "knowledge_cutoff": "2026-03", "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-5-live-translate-preview", "source_id": "google/gemini-3.5-live-translate-preview", "source_metadata": { "name": "Gemini 3.5 Live Translate Preview", "description": "Low-latency audio-to-audio model for real-time speech translation across 70+ languages", "family": "gemini-pro", "release_date": "2026-06-09", "last_updated": "2026-06-09", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "audio" ], "output": [ "audio", "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 131072, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-5-transcribe-live", "source_id": "google/gemini-3.5-transcribe-live", "source_metadata": { "name": "Gemini 3.5 Transcribe Live", "description": "Speech transcription model for accurate audio-to-text and captioning workflows", "family": "gemini", "release_date": "2026-08-26", "last_updated": "2026-08-26", "knowledge_cutoff": null, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": null }, "limits": { "context": 0, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-6-flash", "source_id": "google/gemini-3.6-flash", "source_metadata": { "name": "Gemini 3.6 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "family": "gemini-flash", "release_date": "2026-07-21", "last_updated": "2026-07-21", "knowledge_cutoff": "2026-03", "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-7-flash", "source_id": "google/gemini-3.7-flash", "source_metadata": { "name": "Gemini 3.7 Flash", "description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning", "family": "gemini-flash", "release_date": "2026-08-13", "last_updated": "2026-08-13", "knowledge_cutoff": "2026-03", "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-3-8-flash", "source_id": "google/gemini-3.8-flash", "source_metadata": { "name": "Gemini 3.8 Flash", "description": "Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows", "family": "gemini-flash", "release_date": "2026-09-02", "last_updated": "2026-09-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-embedding-001", "source_id": "google/gemini-embedding-001", "source_metadata": { "name": "Gemini Embedding 001", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "family": "gemini", "release_date": "2025-05-20", "last_updated": "2025-05-20", "knowledge_cutoff": "2025-05", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 2048, "input": null, "output": 1 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-embedding-2", "source_id": "google/gemini-embedding-2", "source_metadata": { "name": "Gemini Embedding 2", "description": "Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space", "family": "gemini", "release_date": "2026-04-22", "last_updated": "2026-04-22", "knowledge_cutoff": "2025-11", "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 8192, "input": null, "output": 3072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-flash-latest", "source_id": "google/gemini-flash-latest", "source_metadata": { "name": "Gemini Flash Latest", "description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning", "family": "gemini-flash", "release_date": "2026-08-13", "last_updated": "2026-08-13", "knowledge_cutoff": "2026-03", "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-flash-lite-latest", "source_id": "google/gemini-flash-lite-latest", "source_metadata": { "name": "Gemini Flash-Lite Latest", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "family": "gemini-flash-lite", "release_date": "2026-07-21", "last_updated": "2026-07-21", "knowledge_cutoff": "2026-03", "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-nano-banana-2-1", "source_id": "google/gemini-nano-banana-2.1", "source_metadata": { "name": "Nano Banana 2.1", "description": "Image model for prompt-driven generation, multi-turn editing, and visual design workflows", "family": "gemini-flash", "release_date": "2026-10-06", "last_updated": "2026-10-06", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text", "image" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": false, "structured_output": false, "temperature": false }, "limits": { "context": 131072, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-omni-flash-preview", "source_id": "google/gemini-omni-flash-preview", "source_metadata": { "name": "Gemini Omni Flash Preview", "description": "Video generation and editing model for fast, conversational text- and image-to-video workflows", "family": "gemini", "release_date": "2026-06-30", "last_updated": "2026-06-30", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": false, "structured_output": null, "temperature": null }, "limits": { "context": 1048576, "input": null, "output": 57920 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemini-robotics-er-1-6-preview", "source_id": "google/gemini-robotics-er-1.6-preview", "source_metadata": { "name": "Gemini Robotics-ER 1.6 Preview", "description": "Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics", "family": "gemini", "release_date": "2026-04-14", "last_updated": "2026-04-14", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemma-2-27b-it", "source_id": "google/gemma-2-27b-it", "source_metadata": { "name": "Gemma 2 27B", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "family": "gemma", "release_date": "2024-07-13", "last_updated": "2024-07-13", "knowledge_cutoff": "2024-06-30", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 8192, "input": null, "output": 2048 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-gemma-3-12b-it", "source_id": "google/gemma-3-12b-it", "source_metadata": { "name": "Gemma 3 12B IT", "description": "Open multimodal Gemma instruction model for multilingual text generation and image understanding", "family": "gemma", "release_date": "2025-03-12", "last_updated": "2025-03-12", "knowledge_cutoff": "2024-08", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/google/gemma-3-12b-it" } ] } }, { "id": "model-google-gemma-3-27b-it", "source_id": "google/gemma-3-27b-it", "source_metadata": { "name": "Gemma 3 27B IT", "description": "Largest open Gemma 3 instruction model for multilingual text generation and visual understanding", "family": "gemma", "release_date": "2025-03-12", "last_updated": "2025-03-12", "knowledge_cutoff": "2024-08", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/google/gemma-3-27b-it" } ] } }, { "id": "model-google-gemma-3-4b-it", "source_id": "google/gemma-3-4b-it", "source_metadata": { "name": "Gemma 3 4B IT", "description": "Open multimodal Gemma instruction model for efficient text generation and image understanding", "family": "gemma", "release_date": "2025-03-12", "last_updated": "2025-03-12", "knowledge_cutoff": "2024-08", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/google/gemma-3-4b-it" } ] } }, { "id": "model-google-gemma-4-12b-it", "source_id": "google/gemma-4-12b-it", "source_metadata": { "name": "Gemma 4 12B IT", "description": "Compact Gemma 4 instruction model for open, self-hosted chat and reasoning", "family": "gemma", "release_date": "2026-06-09", "last_updated": "2026-06-09", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/google/gemma-4-12B-it" } ] } }, { "id": "model-google-gemma-4-26b-a4b-it", "source_id": "google/gemma-4-26b-a4b-it", "source_metadata": { "name": "Gemma 4 26B A4B IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "family": "gemma", "release_date": "2026-04-02", "last_updated": "2026-04-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/google/gemma-4-26B-A4B-it" } ] } }, { "id": "model-google-gemma-4-31b-it", "source_id": "google/gemma-4-31b-it", "source_metadata": { "name": "Gemma 4 31B IT", "description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning", "family": "gemma", "release_date": "2026-04-02", "last_updated": "2026-04-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/google/gemma-4-31B-it" } ] } }, { "id": "model-google-gemma-4-e2b-it", "source_id": "google/gemma-4-E2B-it", "source_metadata": { "name": "Gemma 4 E2B IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "family": "gemma", "release_date": "2026-04-02", "last_updated": "2026-04-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/google/gemma-4-E2B-it" } ] } }, { "id": "model-google-gemma-4-e4b-it", "source_id": "google/gemma-4-E4B-it", "source_metadata": { "name": "Gemma 4 E4B IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "family": "gemma", "release_date": "2026-04-02", "last_updated": "2026-04-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/google/gemma-4-E4B-it" } ] } }, { "id": "model-google-lyria-3-clip-preview", "source_id": "google/lyria-3-clip-preview", "source_metadata": { "name": "Lyria 3 Clip Preview", "description": "Music generation model for short 30-second clips, loops, and previews from text or image prompts", "family": "lyria", "release_date": "2026-03-25", "last_updated": "2026-03-25", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text", "audio" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": false, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-lyria-3-pro-preview", "source_id": "google/lyria-3-pro-preview", "source_metadata": { "name": "Lyria 3 Pro Preview", "description": "Music generation model for full-length songs from text or images with vocals and structure", "family": "lyria", "release_date": "2026-03-25", "last_updated": "2026-03-25", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text", "audio" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": false, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-veo-3-1-fast-generate-preview", "source_id": "google/veo-3.1-fast-generate-preview", "source_metadata": { "name": "Veo 3.1 Fast Preview", "description": "Video model for prompt-guided generation, editing, and motion workflows", "family": "veo", "release_date": "2025-10-15", "last_updated": "2026-01-01", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 1024, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-veo-3-1-generate-preview", "source_id": "google/veo-3.1-generate-preview", "source_metadata": { "name": "Veo 3.1 Preview", "description": "Video model for prompt-guided generation, editing, and motion workflows", "family": "veo", "release_date": "2025-10-15", "last_updated": "2026-01", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 1024, "input": null, "output": 1 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-google-veo-3-1-lite-generate-preview", "source_id": "google/veo-3.1-lite-generate-preview", "source_metadata": { "name": "Veo 3.1 Lite Preview", "description": "Video model for prompt-guided generation, editing, and motion workflows", "family": "veo", "release_date": "2026-03-31", "last_updated": "2026-03-31", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 1024, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-gryphe-mythomax-l2-13b", "source_id": "gryphe/mythomax-l2-13b", "source_metadata": { "name": "MythoMax L2 13B", "description": "Llama 2 merge combining MythoLogic and Huginn for creative writing and roleplay", "family": null, "release_date": "2023-08-10", "last_updated": "2023-08-10", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 4096, "input": null, "output": 3200 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Gryphe/MythoMax-L2-13b" } ] } }, { "id": "model-ibm-granite-4-h-micro", "source_id": "ibm/granite-4-h-micro", "source_metadata": { "name": "Granite-4.0-H-Micro", "description": "Compact open-weight hybrid Granite model for lightweight enterprise chat and tool calling", "family": "granite", "release_date": "2025-10-02", "last_updated": "2025-10-02", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/ibm-granite/granite-4.0-h-micro" } ] } }, { "id": "model-ibm-granite-4-h-small", "source_id": "ibm/granite-4-h-small", "source_metadata": { "name": "Granite-4.0-H-Small", "description": "Open-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloads", "family": "granite", "release_date": "2025-10-02", "last_updated": "2025-10-02", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/ibm-granite/granite-4.0-h-small" } ] } }, { "id": "model-ibm-granite-4-2-8b", "source_id": "ibm/granite-4.2-8b", "source_metadata": { "name": "Granite 4.2 8B", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "family": "granite", "release_date": "2026-08-31", "last_updated": "2026-08-31", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 117964 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-inception-mercury-2", "source_id": "inception/mercury-2", "source_metadata": { "name": "Mercury 2", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "family": "mercury", "release_date": "2026-03-04", "last_updated": "2026-03-04", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 50000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-inception-mercury-2-5", "source_id": "inception/mercury-2.5", "source_metadata": { "name": "Mercury 2.5", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "family": "mercury", "release_date": "2026-09-08", "last_updated": "2026-09-08", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 260000, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-inclusionai-ling-3-0-flash", "source_id": "inclusionai/ling-3.0-flash", "source_metadata": { "name": "Ling 3.0 Flash", "description": "Hybrid-linear MoE reasoning model with 124B total and 5.1B active parameters for efficient agents", "family": "ling", "release_date": "2026-07-23", "last_updated": "2026-07-23", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/inclusionAI/Ling-3.0-flash" } ] } }, { "id": "model-inclusionai-ling-3-0-flash-fin", "source_id": "inclusionai/ling-3.0-flash-fin", "source_metadata": { "name": "Ling 3.0 Flash Fin", "description": "Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution", "family": "ling", "release_date": "2026-08-27", "last_updated": "2026-09-03", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": null }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/inclusionAI/Ling-3.0-flash-Fin" } ] } }, { "id": "model-inclusionai-ling-3-0-flash-sante", "source_id": "inclusionai/ling-3.0-flash-sante", "source_metadata": { "name": "Ling 3.0 Flash Sante", "description": "Health and medicine specialization of Ling 3.0 Flash for medical reasoning and evidence-based retrieval", "family": "ling", "release_date": "2026-09-04", "last_updated": "2026-09-04", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-inclusionai-ling-3-0-flash-vl", "source_id": "inclusionai/ling-3.0-flash-vl", "source_metadata": { "name": "Ling 3.0 Flash VL", "description": "Native multimodal hybrid MoE model for image and video understanding, reasoning, and visual agents", "family": "ling", "release_date": "2026-09-10", "last_updated": "2026-09-10", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/inclusionAI/Ling-3.0-flash-VL" } ] } }, { "id": "model-inclusionai-ling-3-1-flash", "source_id": "inclusionai/ling-3.1-flash", "source_metadata": { "name": "Ling 3.1 Flash", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "family": "ling", "release_date": "2026-09-29", "last_updated": "2026-09-29", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": null }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-inference-net-schematron-v2-small", "source_id": "inference-net/schematron-v2-small", "source_metadata": { "name": "Schematron V2 Small", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "family": null, "release_date": "2026-09-12", "last_updated": "2026-09-12", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-inference-net-schematron-v2-turbo", "source_id": "inference-net/schematron-v2-turbo", "source_metadata": { "name": "Schematron V2 Turbo", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "family": null, "release_date": "2026-09-12", "last_updated": "2026-09-12", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-liquid-d1", "source_id": "liquid/d1", "source_metadata": { "name": "Liquid d1", "description": "System One decision model for typed classification, routing, and scoring over shared state", "family": "liquid", "release_date": "2026-09-29", "last_updated": "2026-09-29", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": null }, "limits": { "context": 65536, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mancer-weaver", "source_id": "mancer/weaver", "source_metadata": { "name": "Weaver (alpha)", "description": "General-purpose chat model for instruction following, writing, and analysis", "family": "alpha", "release_date": "2023-08-02", "last_updated": "2023-08-02", "knowledge_cutoff": "2023-06-30", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": false, "temperature": true }, "limits": { "context": 8000, "input": null, "output": 6000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-meituan-longcat-2-0", "source_id": "meituan/longcat-2.0", "source_metadata": { "name": "LongCat-2.0", "description": "Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window", "family": "longcat", "release_date": "2026-06-30", "last_updated": "2026-06-30", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-meituan-longcat-2-5-preview", "source_id": "meituan/longcat-2.5-preview", "source_metadata": { "name": "LongCat-2.5-Preview", "description": "Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window", "family": "longcat", "release_date": "2026-09-25", "last_updated": "2026-09-25", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-meta-llama-3-1-70b-instruct", "source_id": "meta/llama-3.1-70b-instruct", "source_metadata": { "name": "Llama-3.1-70B-Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "family": "llama", "release_date": "2024-07-23", "last_updated": "2024-07-23", "knowledge_cutoff": "2023-12", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct" } ] } }, { "id": "model-meta-llama-3-1-8b-instruct", "source_id": "meta/llama-3.1-8b-instruct", "source_metadata": { "name": "Llama-3.1-8B-Instruct", "description": "Compact open Llama model for lightweight chat, drafting, and self-hosting", "family": "llama", "release_date": "2024-07-23", "last_updated": "2024-07-23", "knowledge_cutoff": "2023-12", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct" } ] } }, { "id": "model-meta-llama-3-2-11b-vision-instruct", "source_id": "meta/llama-3.2-11b-vision-instruct", "source_metadata": { "name": "Llama-3.2-11B-Vision-Instruct", "description": "Open multimodal Llama model for image understanding, captioning, and visual QA", "family": "llama", "release_date": "2024-09-25", "last_updated": "2024-09-25", "knowledge_cutoff": "2023-12", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct" } ] } }, { "id": "model-meta-llama-3-2-1b", "source_id": "meta/llama-3.2-1b", "source_metadata": { "name": "Llama-3.2-1B", "description": "Compact open Llama base model for lightweight and on-device use", "family": "llama", "release_date": "2024-09-25", "last_updated": "2024-09-25", "knowledge_cutoff": "2023-12", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": "Llama 3.2 Community License", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/meta-llama/Llama-3.2-1B" } ] } }, { "id": "model-meta-llama-3-2-1b-instruct", "source_id": "meta/llama-3.2-1b-instruct", "source_metadata": { "name": "Llama 3.2 1B Instruct", "description": "Compact instruction-tuned Llama model for multilingual dialogue and on-device assistants", "family": "llama", "release_date": "2024-09-25", "last_updated": "2024-09-25", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 32000 }, "reported_open_weights": true, "reported_license": "Llama 3.2 Community License", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct" } ] } }, { "id": "model-meta-llama-3-2-3b", "source_id": "meta/llama-3.2-3b", "source_metadata": { "name": "Llama-3.2-3B", "description": "Small open Llama base model for lightweight text generation and self-hosting", "family": "llama", "release_date": "2024-09-25", "last_updated": "2024-09-25", "knowledge_cutoff": "2023-12", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": "Llama 3.2 Community License", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/meta-llama/Llama-3.2-3B" } ] } }, { "id": "model-meta-llama-3-3-70b-instruct", "source_id": "meta/llama-3.3-70b-instruct", "source_metadata": { "name": "Llama-3.3-70B-Instruct", "description": "Popular open Llama workhorse for multilingual chat, coding, and self-hosting", "family": "llama", "release_date": "2024-12-06", "last_updated": "2024-12-06", "knowledge_cutoff": "2023-12", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct" } ] } }, { "id": "model-meta-llama-4-maverick-17b-instruct", "source_id": "meta/llama-4-maverick-17b-instruct", "source_metadata": { "name": "Llama 4 Maverick 17B Instruct", "description": "Open multimodal Llama for strong reasoning with efficient everyday serving", "family": "llama", "release_date": "2025-04-05", "last_updated": "2025-04-05", "knowledge_cutoff": "2024-08", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct" } ] } }, { "id": "model-meta-llama-4-scout-17b-instruct", "source_id": "meta/llama-4-scout-17b-instruct", "source_metadata": { "name": "Llama 4 Scout 17B Instruct", "description": "Open Llama with long-context vision for efficient multimodal agents", "family": "llama", "release_date": "2025-04-05", "last_updated": "2025-04-05", "knowledge_cutoff": "2024-08", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 10000000, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct" } ] } }, { "id": "model-meta-llama-guard-3-8b", "source_id": "meta/llama-guard-3-8b", "source_metadata": { "name": "Llama-Guard-3-8B", "description": "Llama 3.1-based safety classifier for moderating prompts and model responses", "family": "llama", "release_date": "2024-07-23", "last_updated": "2024-07-23", "knowledge_cutoff": "2023-12", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/meta-llama/Llama-Guard-3-8B" } ] } }, { "id": "model-meta-muse-glimmer-30b", "source_id": "meta/muse-glimmer-30b", "source_metadata": { "name": "Muse Glimmer 30B", "description": "Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.", "family": "muse", "release_date": "2026-08-10", "last_updated": "2026-08-10", "knowledge_cutoff": "2026-01-04", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": "Apache 2.0", "links": [ { "label": "Announcement", "url": "https://research.meta.ai/blog/introducing-muse-glimmer-open-agentic-model", "type": "announcement" }, { "label": "Model card", "url": "https://huggingface.co/meta-models/Muse-Glimmer-30B", "type": "model_card" }, { "label": "Developer docs", "url": "https://developer.meta.com/ai/models/muse-glimmer/", "type": "docs" } ], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/meta-models/Muse-Glimmer-30B" } ] } }, { "id": "model-meta-muse-spark-1-1", "source_id": "meta/muse-spark-1.1", "source_metadata": { "name": "Muse Spark 1.1", "description": "Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.", "family": "muse", "release_date": "2026-04-08", "last_updated": "2026-07-09", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "pdf", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-meta-muse-spark-1-2", "source_id": "meta/muse-spark-1.2", "source_metadata": { "name": "Muse Spark 1.2", "description": "Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.", "family": "muse", "release_date": "2026-08-05", "last_updated": "2026-08-05", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "pdf", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-meta-muse-spark-1-3", "source_id": "meta/muse-spark-1.3", "source_metadata": { "name": "Muse Spark 1.3", "description": "Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.", "family": "muse", "release_date": "2026-09-02", "last_updated": "2026-09-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "pdf", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-meta-muse-wonder-1-0", "source_id": "meta/muse-wonder-1.0", "source_metadata": { "name": "Muse Wonder", "description": "Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.", "family": "muse", "release_date": "2026-10-12", "last_updated": "2026-10-12", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "pdf", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [ { "label": "Announcement", "url": "https://research.meta.ai/blog/muse-wonder", "type": "announcement" }, { "label": "Model card", "url": "https://research.meta.ai/static/muse-wonder-model-card", "type": "model_card" } ], "weights": [] } }, { "id": "model-meta-muse-wonder-full", "source_id": "meta/muse-wonder-full", "source_metadata": { "name": "Muse Wonder Full", "description": "Muse Wonder Full is the most capable model in Meta's Muse Wonder series, built for long-running professional agents and ultra-long-horizon software engineering. It shares Muse Wonder's Active Memory and Active Focus capabilities and generally scores higher on Meta's agentic and coding evaluations.", "family": "muse", "release_date": "2026-10-12", "last_updated": "2026-10-12", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": null }, "limits": { "context": 1048576, "input": null, "output": null }, "reported_open_weights": false, "reported_license": null, "links": [ { "label": "Announcement", "url": "https://research.meta.ai/blog/muse-wonder", "type": "announcement" }, { "label": "Model card", "url": "https://research.meta.ai/static/muse-wonder-model-card", "type": "model_card" } ], "weights": [] } }, { "id": "model-microsoft-mai-code-1-flash", "source_id": "microsoft/mai-code-1-flash", "source_metadata": { "name": "MAI-Code-1-Flash", "description": "Microsoft coding model built for fast, efficient assistance in everyday developer workflows", "family": "mai", "release_date": "2026-06-02", "last_updated": "2026-06-08", "knowledge_cutoff": "2025-12", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [ { "label": "Model card", "url": "https://microsoft.ai/pdf/MAI-Code-1-Flash-Model-Card.PDF", "type": "model_card" }, { "label": "Announcement", "url": "https://microsoft.ai/news/introducingmai-code-1-flash/", "type": "announcement" } ], "weights": [] } }, { "id": "model-microsoft-mai-code-1-1-flash", "source_id": "microsoft/mai-code-1.1-flash", "source_metadata": { "name": "MAI-Code-1.1-Flash", "description": "Microsoft coding model with native vision support, optimized for fast and efficient software development", "family": "mai", "release_date": "2026-08-11", "last_updated": "2026-08-11", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": null }, "limits": { "context": 256000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [ { "label": "Announcement", "url": "https://microsoft.ai/news/mai-code-1-1-flash-br-better-faster-at-a-quarter-of-the-cost/", "type": "announcement" } ], "weights": [] } }, { "id": "model-microsoft-phi-4-mini", "source_id": "microsoft/phi-4-mini", "source_metadata": { "name": "Phi-4-mini", "description": "Compact Microsoft instruction model tuned for efficient coding assistance, reasoning, and low-latency agent tasks", "family": "phi", "release_date": "2024-12-11", "last_updated": "2024-12-11", "knowledge_cutoff": "2023-10", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [ { "label": "Weights", "url": "https://huggingface.co/microsoft/Phi-4-mini-instruct", "type": "weights" } ], "weights": [] } }, { "id": "model-microsoft-wizardlm-2-8x22b", "source_id": "microsoft/wizardlm-2-8x22b", "source_metadata": { "name": "WizardLM 2 8x22B", "description": "Microsoft WizardLM instruction-tuned Mixtral MoE for multilingual dialogue and complex tasks", "family": null, "release_date": "2024-04-15", "last_updated": "2024-04-15", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 65536, "input": null, "output": 8000 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [], "weights": [ { "label": "Hugging Face archive", "url": "https://huggingface.co/alpindale/WizardLM-2-8x22B" } ] } }, { "id": "model-mindlab-macaron-v1-tall", "source_id": "mindlab/macaron-v1-tall", "source_metadata": { "name": "Macaron V1 Tall", "description": "Qwen3.6-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI", "family": null, "release_date": "2026-07-21", "last_updated": "2026-07-21", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mindlab-research/Macaron-V1-Tall" } ] } }, { "id": "model-mindlab-macaron-v1-venti", "source_id": "mindlab/macaron-v1-venti", "source_metadata": { "name": "Macaron V1 Venti", "description": "GLM-5.2-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI", "family": null, "release_date": "2026-07-21", "last_updated": "2026-07-21", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mindlab-research/Macaron-V1-Venti" } ] } }, { "id": "model-minimax-minimax-h3", "source_id": "minimax/MiniMax-H3", "source_metadata": { "name": "MiniMax H3", "description": "MiniMax general-purpose video model with multimodal references and synchronized stereo audio. Open H3-Base checkpoints; Context-IR and 2K regeneration are not included in the initial weights release.", "family": "minimax", "release_date": "2026-07-31", "last_updated": "2026-10-04", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "video", "audio" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": null }, "limits": { "context": 0, "input": null, "output": 0 }, "reported_open_weights": true, "reported_license": "MiniMax H3 Community License Agreement", "links": [ { "url": "https://www.minimax.io/blog/minimax-h3", "type": "announcement" }, { "url": "https://www.minimax.io/news/minimax-h3-open-source", "type": "announcement" }, { "url": "https://huggingface.co/MiniMaxAI/MiniMax-H3", "type": "model_card" }, { "url": "https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE", "type": "license" } ], "weights": [ { "label": "Hugging Face: H3-Base FL2VA / Ref2VA", "url": "https://huggingface.co/MiniMaxAI/MiniMax-H3", "format": "safetensors" } ] } }, { "id": "model-minimax-minimax-m2", "source_id": "minimax/MiniMax-M2", "source_metadata": { "name": "MiniMax-M2", "description": "Efficient open MiniMax model built for coding agents and tool-heavy workflows", "family": "minimax", "release_date": "2025-10-27", "last_updated": "2025-10-27", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 204800, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/MiniMaxAI/MiniMax-M2" } ] } }, { "id": "model-minimax-minimax-m2-her", "source_id": "minimax/MiniMax-M2-Her", "source_metadata": { "name": "MiniMax-M2 Her", "description": "MiniMax M2 variant tuned for conversational and character-driven agent interactions", "family": "minimax", "release_date": "2026-01-23", "last_updated": "2026-01-23", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 65536, "input": null, "output": 2048 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-minimax-minimax-m2-1", "source_id": "minimax/MiniMax-M2.1", "source_metadata": { "name": "MiniMax-M2.1", "description": "Earlier MiniMax agent model for practical coding and productivity tasks", "family": "minimax", "release_date": "2025-12-23", "last_updated": "2025-12-23", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 204800, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1" } ] } }, { "id": "model-minimax-minimax-m2-5", "source_id": "minimax/MiniMax-M2.5", "source_metadata": { "name": "MiniMax-M2.5", "description": "Prior MiniMax coding model for agent workflows, office edits, and automation", "family": "minimax", "release_date": "2026-02-12", "last_updated": "2026-02-12", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 204800, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.5" } ] } }, { "id": "model-minimax-minimax-m2-5-highspeed", "source_id": "minimax/MiniMax-M2.5-highspeed", "source_metadata": { "name": "MiniMax-M2.5-highspeed", "description": "High-speed MiniMax model for low-latency coding and agent workflows", "family": "minimax", "release_date": "2026-02-13", "last_updated": "2026-02-13", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 204800, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.5" } ] } }, { "id": "model-minimax-minimax-m2-7", "source_id": "minimax/MiniMax-M2.7", "source_metadata": { "name": "MiniMax-M2.7", "description": "Open MiniMax flagship for coding agents, office automation, and complex environments", "family": "minimax", "release_date": "2026-03-18", "last_updated": "2026-03-18", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 204800, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.7" } ] } }, { "id": "model-minimax-minimax-m2-7-highspeed", "source_id": "minimax/MiniMax-M2.7-highspeed", "source_metadata": { "name": "MiniMax-M2.7-highspeed", "description": "Low-latency M2.7 variant for interactive coding plans and agent loops", "family": "minimax", "release_date": "2026-03-18", "last_updated": "2026-03-18", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 204800, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.7" } ] } }, { "id": "model-minimax-minimax-m3", "source_id": "minimax/MiniMax-M3", "source_metadata": { "name": "MiniMax-M3", "description": "MiniMax multimodal model for long-context coding, perception, and agent planning", "family": "minimax", "release_date": "2026-06-01", "last_updated": "2026-06-01", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 512000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/MiniMaxAI/MiniMax-M3" } ] } }, { "id": "model-minimax-minimax-m3-1-flash-preview", "source_id": "minimax/MiniMax-M3.1-Flash-Preview", "source_metadata": { "name": "MiniMax-M3.1-Flash-Preview", "description": "Frontier multimodal coding model with 1M context window and tunable thinking depth", "family": "minimax", "release_date": "2026-09-27", "last_updated": "2026-09-27", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 512000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-minimax-minimax-text-01", "source_id": "minimax/MiniMax-Text-01", "source_metadata": { "name": "MiniMax Text 01 (MiniMax)", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "family": "minimax", "release_date": "2025-01-15", "last_updated": "2025-01-15", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-minimax-image-01", "source_id": "minimax/image-01", "source_metadata": { "name": "MiniMax image-01", "description": "MiniMax text-to-image generation model with reference-image support", "family": "minimax", "release_date": "2025-02-15", "last_updated": "2026-08-25", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 0, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-minimax-minimax-m1-80k", "source_id": "minimax/minimax-m1-80k", "source_metadata": { "name": "MiniMax M1 80K", "description": "Open hybrid-attention MoE reasoning model with a million-token context and an 80K thinking budget", "family": "minimax", "release_date": "2025-06-17", "last_updated": "2025-06-17", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 80000 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/MiniMaxAI/MiniMax-M1-80k" } ] } }, { "id": "model-mistral-codestral-22b-v0-1", "source_id": "mistral/codestral-22b-v0.1", "source_metadata": { "name": "Codestral-22B-v0.1", "description": "Open Mistral code model for fill-in-the-middle and 80+ programming languages", "family": "codestral", "release_date": "2024-05-29", "last_updated": "2024-05-29", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 32768, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": "Mistral AI Non-Production License", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Codestral-22B-v0.1" } ] } }, { "id": "model-mistral-codestral-2508", "source_id": "mistral/codestral-2508", "source_metadata": { "name": "Codestral 25.08", "description": "Mistral code model for low-latency completion, fill-in-the-middle, and code generation", "family": "codestral", "release_date": "2025-07-30", "last_updated": "2025-07-30", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-codestral-latest", "source_id": "mistral/codestral-latest", "source_metadata": { "name": "Codestral (latest)", "description": "Mistral code model for completions, refactors, and developer IDE workflows", "family": "codestral", "release_date": "2024-05-29", "last_updated": "2025-01-04", "knowledge_cutoff": "2024-10", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Codestral-22B-v0.1" } ] } }, { "id": "model-mistral-devstral-2512", "source_id": "mistral/devstral-2512", "source_metadata": { "name": "Devstral 2", "description": "Mistral's coding-agent model for repository work, terminal tasks, and software fixes", "family": "devstral", "release_date": "2025-12-09", "last_updated": "2025-12-09", "knowledge_cutoff": "2025-12", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512" } ] } }, { "id": "model-mistral-devstral-medium-2507", "source_id": "mistral/devstral-medium-2507", "source_metadata": { "name": "Devstral Medium", "description": "Mistral coding agent model for repository tasks and software engineering workflows", "family": "devstral", "release_date": "2025-07-10", "last_updated": "2025-07-10", "knowledge_cutoff": "2025-05", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-devstral-medium-latest", "source_id": "mistral/devstral-medium-latest", "source_metadata": { "name": "Devstral 2 (latest)", "description": "Mistral coding agent model for repository tasks and software engineering workflows", "family": "devstral", "release_date": "2025-12-02", "last_updated": "2025-12-02", "knowledge_cutoff": "2025-12", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512" } ] } }, { "id": "model-mistral-devstral-small-2", "source_id": "mistral/devstral-small-2", "source_metadata": { "name": "Devstral Small 2", "description": "Compact multimodal coding model for repository exploration, file editing, and software agents", "family": "devstral", "release_date": "2025-12-09", "last_updated": "2025-12-09", "knowledge_cutoff": "2025-12", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512" } ] } }, { "id": "model-mistral-devstral-small-2507", "source_id": "mistral/devstral-small-2507", "source_metadata": { "name": "Devstral Small", "description": "Mistral coding agent model for repository tasks and software engineering workflows", "family": "devstral", "release_date": "2025-07-10", "last_updated": "2025-07-10", "knowledge_cutoff": "2025-05", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 128000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Devstral-Small-2507" } ] } }, { "id": "model-mistral-magistral-medium-latest", "source_id": "mistral/magistral-medium-latest", "source_metadata": { "name": "Magistral Medium (latest)", "description": "Mistral reasoning model for transparent analysis, math, and complex decisions", "family": "magistral-medium", "release_date": "2025-03-17", "last_updated": "2025-03-20", "knowledge_cutoff": "2025-06", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 16384 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-magistral-small-2506", "source_id": "mistral/magistral-small-2506", "source_metadata": { "name": "Magistral Small", "description": "Open Mistral reasoning model for transparent step-by-step problem solving", "family": "magistral", "release_date": "2025-06-10", "last_updated": "2025-06-10", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": "Apache 2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Magistral-Small-2506" } ] } }, { "id": "model-mistral-magistral-small-2509", "source_id": "mistral/magistral-small-2509", "source_metadata": { "name": "Magistral Small 1.2", "description": "Open multimodal reasoning model for transparent analysis of text and images", "family": "magistral", "release_date": "2025-09-18", "last_updated": "2025-09-18", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": "Apache 2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Magistral-Small-2509" } ] } }, { "id": "model-mistral-ministral-14b", "source_id": "mistral/ministral-14b", "source_metadata": { "name": "Ministral 14B", "description": "Compact multimodal Mistral model for local assistants, edge agents, and efficient tool use", "family": "ministral", "release_date": "2025-12-02", "last_updated": "2025-12-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512" } ] } }, { "id": "model-mistral-ministral-14b-2512", "source_id": "mistral/ministral-14b-2512", "source_metadata": { "name": "Ministral 3 14B 2512", "description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads", "family": "ministral", "release_date": "2025-12-02", "last_updated": "2025-12-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 209715 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-ministral-3-14b-instruct-2512", "source_id": "mistral/ministral-3-14b-instruct-2512", "source_metadata": { "name": "Ministral 3 14B", "description": "Open vision-language model for efficient local deployment, instruction following, and tool use", "family": "ministral", "release_date": "2025-12-02", "last_updated": "2025-12-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": "Apache 2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512" } ] } }, { "id": "model-mistral-ministral-3-3b-instruct-2512", "source_id": "mistral/ministral-3-3b-instruct-2512", "source_metadata": { "name": "Ministral 3 3B", "description": "Compact open vision-language model for edge deployment, instruction following, and tool use", "family": "ministral", "release_date": "2025-12-02", "last_updated": "2025-12-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": "Apache 2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512" } ] } }, { "id": "model-mistral-ministral-3-8b-instruct-2512", "source_id": "mistral/ministral-3-8b-instruct-2512", "source_metadata": { "name": "Ministral 3 8B", "description": "Compact open vision-language model for edge deployment, instruction following, and tool use", "family": "ministral", "release_date": "2025-12-02", "last_updated": "2025-12-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": "Apache 2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512" } ] } }, { "id": "model-mistral-ministral-3b", "source_id": "mistral/ministral-3b", "source_metadata": { "name": "Ministral 3B", "description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads", "family": "ministral", "release_date": "2024-10-16", "last_updated": "2024-10-16", "knowledge_cutoff": "2024-03", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-ministral-3b-2512", "source_id": "mistral/ministral-3b-2512", "source_metadata": { "name": "Ministral 3 3B 2512", "description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads", "family": "ministral", "release_date": "2025-12-02", "last_updated": "2025-12-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 104857 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-ministral-8b-2512", "source_id": "mistral/ministral-8b-2512", "source_metadata": { "name": "Ministral 3 8B 2512", "description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads", "family": "ministral", "release_date": "2025-12-02", "last_updated": "2025-12-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 209715 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-ministral-8b-instruct-2410", "source_id": "mistral/ministral-8b-instruct-2410", "source_metadata": { "name": "Ministral 8B Instruct", "description": "Efficient open Mistral edge model for on-device chat and function calling", "family": "ministral", "release_date": "2024-10-16", "last_updated": "2024-10-16", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": "Mistral Research License", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Ministral-8B-Instruct-2410" } ] } }, { "id": "model-mistral-mistral-embed", "source_id": "mistral/mistral-embed", "source_metadata": { "name": "Mistral Embed", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "family": "mistral-embed", "release_date": "2023-12-11", "last_updated": "2023-12-11", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 8000, "input": null, "output": 3072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-mistral-large", "source_id": "mistral/mistral-large", "source_metadata": { "name": "Mistral Large", "description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work", "family": "mistral-large", "release_date": "2024-02-26", "last_updated": "2024-02-26", "knowledge_cutoff": "2024-11-30", "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 102400 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-mistral-large-2407", "source_id": "mistral/mistral-large-2407", "source_metadata": { "name": "Mistral Large 2407", "description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work", "family": "mistral-large", "release_date": "2024-11-19", "last_updated": "2024-11-19", "knowledge_cutoff": "2024-03-31", "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 104857 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-mistral-large-2411", "source_id": "mistral/mistral-large-2411", "source_metadata": { "name": "Mistral Large 2.1", "description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work", "family": "mistral-large", "release_date": "2024-11-18", "last_updated": "2024-11-18", "knowledge_cutoff": "2024-11", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Mistral-Large-Instruct-2411" } ] } }, { "id": "model-mistral-mistral-large-2512", "source_id": "mistral/mistral-large-2512", "source_metadata": { "name": "Mistral Large 3", "description": "Mistral's largest general model for enterprise agents, coding, and multilingual reasoning", "family": "mistral-large", "release_date": "2025-12-02", "last_updated": "2025-12-02", "knowledge_cutoff": "2024-11", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Mistral-Large-3-675B-Instruct-2512" } ] } }, { "id": "model-mistral-mistral-large-4", "source_id": "mistral/mistral-large-4", "source_metadata": { "name": "Mistral Large 4", "description": "Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work", "family": "mistral-large", "release_date": "2026-10-06", "last_updated": "2026-10-06", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 262144 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-mistral-large-latest", "source_id": "mistral/mistral-large-latest", "source_metadata": { "name": "Mistral Large (latest)", "description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work", "family": "mistral-large", "release_date": "2024-11-01", "last_updated": "2025-12-02", "knowledge_cutoff": "2024-11", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Mistral-Large-3-675B-Instruct-2512" } ] } }, { "id": "model-mistral-mistral-medium-2505", "source_id": "mistral/mistral-medium-2505", "source_metadata": { "name": "Mistral Medium 3", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "family": "mistral-medium", "release_date": "2025-05-07", "last_updated": "2025-05-07", "knowledge_cutoff": "2025-05", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-mistral-medium-2604", "source_id": "mistral/mistral-medium-2604", "source_metadata": { "name": "Mistral Medium 3.5", "description": "Balanced Mistral model for enterprise assistants, multilingual work, and tools", "family": "mistral-medium", "release_date": "2026-04-29", "last_updated": "2026-04-29", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Mistral-Medium-3.5-128B" } ] } }, { "id": "model-mistral-mistral-medium-3", "source_id": "mistral/mistral-medium-3", "source_metadata": { "name": "Mistral Medium 3", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "family": "mistral-medium", "release_date": "2025-05-07", "last_updated": "2025-05-07", "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 104857 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-mistral-medium-3-5", "source_id": "mistral/mistral-medium-3-5", "source_metadata": { "name": "Mistral Medium 3.5", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "family": "mistral-medium", "release_date": "2026-04-30", "last_updated": "2026-04-30", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 209715 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-mistral-medium-3-1", "source_id": "mistral/mistral-medium-3.1", "source_metadata": { "name": "Mistral Medium 3.1", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "family": "mistral-medium", "release_date": "2025-08-13", "last_updated": "2025-08-13", "knowledge_cutoff": "2025-06-30", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 104857 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-mistral-medium-latest", "source_id": "mistral/mistral-medium-latest", "source_metadata": { "name": "Mistral Medium (latest)", "description": "Balanced Mistral model for enterprise assistants, multilingual work, and tools", "family": "mistral-medium", "release_date": "2026-04-29", "last_updated": "2026-04-29", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Mistral-Medium-3.5-128B" } ] } }, { "id": "model-mistral-mistral-nemo", "source_id": "mistral/mistral-nemo", "source_metadata": { "name": "Mistral Nemo", "description": "Efficient Mistral-NVIDIA open model for multilingual chat and local deployment", "family": "mistral-nemo", "release_date": "2024-07-01", "last_updated": "2024-07-01", "knowledge_cutoff": "2024-07", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 128000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407" } ] } }, { "id": "model-mistral-mistral-saba", "source_id": "mistral/mistral-saba", "source_metadata": { "name": "Saba", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "family": "mistral", "release_date": "2025-02-17", "last_updated": "2025-02-17", "knowledge_cutoff": "2024-09-30", "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 32768, "input": null, "output": 26214 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-mistral-small-24b-instruct-2501", "source_id": "mistral/mistral-small-24b-instruct-2501", "source_metadata": { "name": "Mistral Small 3", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "family": "mistral-small", "release_date": "2025-01-30", "last_updated": "2025-01-30", "knowledge_cutoff": "2023-10-31", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 32768, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-mistral-small-2506", "source_id": "mistral/mistral-small-2506", "source_metadata": { "name": "Mistral Small 3.2", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "family": "mistral-small", "release_date": "2025-06-20", "last_updated": "2025-06-20", "knowledge_cutoff": "2025-03", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506" } ] } }, { "id": "model-mistral-mistral-small-2603", "source_id": "mistral/mistral-small-2603", "source_metadata": { "name": "Mistral Small 4", "description": "Fast Mistral production model for chat, extraction, and cost-sensitive agents", "family": "mistral-small", "release_date": "2026-03-16", "last_updated": "2026-03-16", "knowledge_cutoff": "2025-06", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 256000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Mistral-Small-4-119B-2603" } ] } }, { "id": "model-mistral-mistral-small-3-1-24b-instruct-2503", "source_id": "mistral/mistral-small-3-1-24b-instruct-2503", "source_metadata": { "name": "Mistral Small 3.1 24B", "description": "Efficient multimodal model for instruction following, coding, reasoning, and function calling", "family": "mistral-small", "release_date": "2025-03-17", "last_updated": "2025-03-17", "knowledge_cutoff": "2024-06", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503" } ] } }, { "id": "model-mistral-mistral-small-3-1-24b-instruct", "source_id": "mistral/mistral-small-3.1-24b-instruct", "source_metadata": { "name": "Mistral Small 3.1 24B", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "family": "mistral-small", "release_date": "2025-03-17", "last_updated": "2025-03-17", "knowledge_cutoff": "2023-10-31", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": false, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 102400 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-mistral-small-3-2-24b-instruct", "source_id": "mistral/mistral-small-3.2-24b-instruct", "source_metadata": { "name": "Mistral Small 3.2 24B", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "family": "mistral-small", "release_date": "2025-06-20", "last_updated": "2025-06-20", "knowledge_cutoff": "2023-10-31", "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-mistral-small-latest", "source_id": "mistral/mistral-small-latest", "source_metadata": { "name": "Mistral Small (latest)", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "family": "mistral-small", "release_date": "2026-03-16", "last_updated": "2026-03-16", "knowledge_cutoff": "2025-06", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 256000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Mistral-Small-4-119B-2603" } ] } }, { "id": "model-mistral-mixtral-8x22b-instruct", "source_id": "mistral/mixtral-8x22b-instruct", "source_metadata": { "name": "Mixtral 8x22B Instruct", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "family": "mistral", "release_date": "2024-04-17", "last_updated": "2024-04-17", "knowledge_cutoff": "2024-01-31", "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 65536, "input": null, "output": 52428 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-pixtral-12b", "source_id": "mistral/pixtral-12b", "source_metadata": { "name": "Pixtral 12B", "description": "Mistral vision-language model for image understanding and multimodal chat", "family": "pixtral", "release_date": "2024-09-01", "last_updated": "2024-09-01", "knowledge_cutoff": "2024-09", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 128000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Pixtral-12B-2409" } ] } }, { "id": "model-mistral-pixtral-large-2502", "source_id": "mistral/pixtral-large-2502", "source_metadata": { "name": "Pixtral Large (25.02)", "description": "Mistral vision-language model for image understanding and multimodal chat", "family": "pixtral", "release_date": "2025-04-08", "last_updated": "2025-04-08", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mistral-pixtral-large-latest", "source_id": "mistral/pixtral-large-latest", "source_metadata": { "name": "Pixtral Large (latest)", "description": "Mistral's larger vision model for document-heavy image understanding and chat", "family": "pixtral", "release_date": "2024-11-01", "last_updated": "2024-11-04", "knowledge_cutoff": "2024-11", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 128000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Pixtral-Large-Instruct-2411" } ] } }, { "id": "model-mistral-voxtral-mini-3b-2507", "source_id": "mistral/voxtral-mini-3b-2507", "source_metadata": { "name": "Voxtral Mini 3B 2507", "description": "Open audio-language model for speech transcription, audio understanding, and voice-driven tool use", "family": "voxtral", "release_date": "2025-07-15", "last_updated": "2025-07-15", "knowledge_cutoff": null, "modalities": { "input": [ "text", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 32768, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": "Apache 2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Voxtral-Mini-3B-2507" } ] } }, { "id": "model-mistral-voxtral-small-24b-2507", "source_id": "mistral/voxtral-small-24b-2507", "source_metadata": { "name": "Voxtral Small 24B 2507", "description": "Open audio-language model for speech transcription, audio understanding, and voice-driven tool use", "family": "voxtral", "release_date": "2025-07-15", "last_updated": "2025-07-15", "knowledge_cutoff": null, "modalities": { "input": [ "text", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 32768, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": "Apache 2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/mistralai/Voxtral-Small-24B-2507" } ] } }, { "id": "model-mistral-voxtral-small-latest", "source_id": "mistral/voxtral-small-latest", "source_metadata": { "name": "Voxtral Small (latest)", "description": "Instruct model with native audio input for speech understanding and tool use", "family": "voxtral", "release_date": "2025-07-15", "last_updated": "2025-07-15", "knowledge_cutoff": null, "modalities": { "input": [ "text", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 32000, "input": null, "output": 32000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-mixedbread-toast-1", "source_id": "mixedbread/toast-1", "source_metadata": { "name": "Toast 1", "description": "Specialized search model for knowledge-intensive questions, multi-step retrieval, and evidence synthesis", "family": null, "release_date": "2026-08-13", "last_updated": "2026-08-13", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": null }, "limits": { "context": 131000, "input": null, "output": 4000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-moonshotai-kimi-k2", "source_id": "moonshotai/kimi-k2", "source_metadata": { "name": "Kimi K2 0711", "description": "Kimi model for long-context chat, coding, and agentic reasoning", "family": "kimi-k2", "release_date": "2025-07-11", "last_updated": "2025-07-11", "knowledge_cutoff": "2024-12-31", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 98304 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-moonshotai-kimi-k2-0905", "source_id": "moonshotai/kimi-k2-0905", "source_metadata": { "name": "Kimi K2 Instruct 0905", "description": "September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding", "family": "kimi-k2", "release_date": "2025-09-05", "last_updated": "2025-09-05", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 98304 }, "reported_open_weights": true, "reported_license": "Modified MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905" } ] } }, { "id": "model-moonshotai-kimi-k2-instruct", "source_id": "moonshotai/kimi-k2-instruct", "source_metadata": { "name": "Kimi K2 Instruct", "description": "Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents", "family": "kimi-k2", "release_date": "2025-07-11", "last_updated": "2025-07-11", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": "Modified MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/moonshotai/Kimi-K2-Instruct" } ] } }, { "id": "model-moonshotai-kimi-k2-thinking", "source_id": "moonshotai/kimi-k2-thinking", "source_metadata": { "name": "Kimi K2 Thinking", "description": "Thinking Kimi model for slower research passes, planning, and hard technical questions", "family": "kimi-thinking", "release_date": "2025-11-06", "last_updated": "2025-11-06", "knowledge_cutoff": "2024-08", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/moonshotai/Kimi-K2-Thinking" } ] } }, { "id": "model-moonshotai-kimi-k2-thinking-turbo", "source_id": "moonshotai/kimi-k2-thinking-turbo", "source_metadata": { "name": "Kimi K2 Thinking Turbo", "description": "Kimi reasoning model for long-horizon research, planning, and tool use", "family": "kimi-thinking", "release_date": "2025-11-06", "last_updated": "2025-11-06", "knowledge_cutoff": "2024-08", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/moonshotai/Kimi-K2-Thinking" } ] } }, { "id": "model-moonshotai-kimi-k2-5", "source_id": "moonshotai/kimi-k2.5", "source_metadata": { "name": "Kimi K2.5", "description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work", "family": "kimi-k2", "release_date": "2026-01", "last_updated": "2026-01", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/moonshotai/Kimi-K2.5" } ] } }, { "id": "model-moonshotai-kimi-k2-6", "source_id": "moonshotai/kimi-k2.6", "source_metadata": { "name": "Kimi K2.6", "description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context", "family": "kimi-k2", "release_date": "2026-04-21", "last_updated": "2026-04-21", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/moonshotai/Kimi-K2.6" } ] } }, { "id": "model-moonshotai-kimi-k2-7-code", "source_id": "moonshotai/kimi-k2.7-code", "source_metadata": { "name": "Kimi K2.7 Code", "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking", "family": "kimi-k2", "release_date": "2026-06-12", "last_updated": "2026-06-12", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/moonshotai/Kimi-K2.7-Code" } ] } }, { "id": "model-moonshotai-kimi-k2-7-code-highspeed", "source_id": "moonshotai/kimi-k2.7-code-highspeed", "source_metadata": { "name": "Kimi K2.7 Code Highspeed", "description": "Lower-latency Kimi Code variant for interactive edits and coding-agent loops", "family": "kimi-k2", "release_date": "2026-06-12", "last_updated": "2026-06-12", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/moonshotai/Kimi-K2.7-Code" } ] } }, { "id": "model-moonshotai-kimi-k2-8-preview", "source_id": "moonshotai/kimi-k2.8-preview", "source_metadata": { "name": "Kimi K2.8 Preview", "description": "Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code", "family": "kimi-k2", "release_date": "2026-09-11", "last_updated": "2026-09-11", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": null }, "limits": { "context": 1048576, "input": null, "output": null }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-moonshotai-kimi-k3", "source_id": "moonshotai/kimi-k3", "source_metadata": { "name": "Kimi K3", "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work", "family": "kimi-k3", "release_date": "2026-07-16", "last_updated": "2026-07-16", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1048576, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-morph-morph-v3-fast", "source_id": "morph/morph-v3-fast", "source_metadata": { "name": "Morph V3 Fast", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "family": "morph", "release_date": "2025-07-07", "last_updated": "2025-07-07", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": false, "temperature": true }, "limits": { "context": 81920, "input": null, "output": 38000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-morph-morph-v3-large", "source_id": "morph/morph-v3-large", "source_metadata": { "name": "Morph V3 Large", "description": "Flagship model for demanding analysis, coding, and production agent workflows", "family": "morph", "release_date": "2025-07-07", "last_updated": "2025-07-07", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-motif-technologies-motif-3", "source_id": "motif-technologies/motif-3", "source_metadata": { "name": "Motif 3", "description": "Motif 3 is a large-scale, decoder-only Mixture-of-Experts (MoE) language model with 314 billion total parameters and 13.2 billion parameters activated per token.", "family": "motif", "release_date": "2026-08-07", "last_updated": "2026-08-07", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Model weights", "url": "https://huggingface.co/Motif-Technologies/Motif-3", "format": "safetensors" } ] } }, { "id": "model-nace-ai-drex-v1-5", "source_id": "nace-ai/drex-v1.5", "source_metadata": { "name": "Drex 1.5", "description": "System One decision model for typed, calibrated probabilistic answers over text or structured state", "family": null, "release_date": "2026-09-28", "last_updated": "2026-09-28", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": false }, "limits": { "context": 139264, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [ { "label": "Documentation", "url": "https://drex.nace.ai/docs", "type": "docs" } ], "weights": [] } }, { "id": "model-nex-agi-nex-n2-pro", "source_id": "nex-agi/nex-n2-pro", "source_metadata": { "name": "Nex-N2-Pro", "description": "Open agentic MoE model (397B total, 17B active) for coding, tool use, and research workflows", "family": null, "release_date": "2026-06-02", "last_updated": "2026-06-02", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/nex-agi/Nex-N2-Pro" } ] } }, { "id": "model-nousresearch-hermes-2-pro-llama-3-8b", "source_id": "nousresearch/hermes-2-pro-llama-3-8b", "source_metadata": { "name": "Hermes 2 Pro Llama 3 8B", "description": "Llama 3 fine-tune optimized for function calling, structured JSON responses, and dialogue", "family": null, "release_date": "2024-04-30", "last_updated": "2024-04-30", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 8192, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": "Llama 3 Community License", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B" } ] } }, { "id": "model-nousresearch-hermes-3-llama-3-1-405b", "source_id": "nousresearch/hermes-3-llama-3.1-405b", "source_metadata": { "name": "Hermes 3 405B Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "family": "nousresearch", "release_date": "2024-08-16", "last_updated": "2024-08-16", "knowledge_cutoff": "2023-12-31", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nousresearch-hermes-3-llama-3-1-70b", "source_id": "nousresearch/hermes-3-llama-3.1-70b", "source_metadata": { "name": "Hermes 3 70B Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "family": "nousresearch", "release_date": "2024-08-18", "last_updated": "2024-08-18", "knowledge_cutoff": "2023-12-31", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nousresearch-hermes-4-405b", "source_id": "nousresearch/hermes-4-405b", "source_metadata": { "name": "Hermes 4 405B", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "family": "hermes", "release_date": "2025-08-26", "last_updated": "2025-08-26", "knowledge_cutoff": "2024-08-31", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": false, "structured_output": false, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 117964 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-llama-3-1-nemotron-70b-instruct", "source_id": "nvidia/llama-3.1-nemotron-70b-instruct", "source_metadata": { "name": "Llama 3.1 Nemotron 70B Instruct", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "family": "nemotron", "release_date": "2025-04-15", "last_updated": "2025-04-15", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-llama-3-1-nemotron-safety-guard-8b-v3", "source_id": "nvidia/llama-3.1-nemotron-safety-guard-8b-v3", "source_metadata": { "name": "Llama 3.1 Nemotron Safety Guard 8B v3", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "family": "nemotron", "release_date": "2025-10-28", "last_updated": "2025-10-28", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-llama-3-1-nemotron-ultra-253b", "source_id": "nvidia/llama-3.1-nemotron-ultra-253b", "source_metadata": { "name": "Llama 3.1 Nemotron Ultra 253B", "description": "Flagship Nemotron model for high-throughput reasoning and complex agents", "family": "nemotron", "release_date": "2025-04-07", "last_updated": "2025-04-07", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-llama-3-3-nemotron-super-49b-v1", "source_id": "nvidia/llama-3.3-nemotron-super-49b-v1", "source_metadata": { "name": "Llama 3.3 Nemotron Super 49B v1", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "family": "nemotron", "release_date": "2025-04-07", "last_updated": "2025-04-07", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-llama-3-3-nemotron-super-49b-v1-5", "source_id": "nvidia/llama-3.3-nemotron-super-49b-v1.5", "source_metadata": { "name": "Llama 3.3 Nemotron Super 49B v1.5", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "family": "nemotron", "release_date": "2025-07-25", "last_updated": "2025-07-25", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-llama-nemotron-embed-1b-v2", "source_id": "nvidia/llama-nemotron-embed-1b-v2", "source_metadata": { "name": "Llama Nemotron Embed 1B v2", "description": "Multilingual text embedding model for retrieval and question answering pipelines", "family": "nemotron", "release_date": "2025-10-16", "last_updated": "2025-10-16", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text", "embedding" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 8192, "input": null, "output": 2048 }, "reported_open_weights": true, "reported_license": "nvidia-open-model-license", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/nvidia/llama-nemotron-embed-1b-v2" } ] } }, { "id": "model-nvidia-llama-nemotron-embed-vl-1b-v2", "source_id": "nvidia/llama-nemotron-embed-vl-1b-v2", "source_metadata": { "name": "Llama Nemotron Embed VL 1B v2", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "family": "nemotron", "release_date": "2026-02-10", "last_updated": "2026-02-10", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 32768, "input": null, "output": 2048 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-llama-nemotron-rerank-vl-1b-v2", "source_id": "nvidia/llama-nemotron-rerank-vl-1b-v2", "source_metadata": { "name": "Llama Nemotron Rerank VL 1B v2", "description": "Reranking model for improving retrieval quality in search and recommendation systems", "family": "nemotron", "release_date": "2026-03-31", "last_updated": "2026-03-31", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-mistral-nemotron", "source_id": "nvidia/mistral-nemotron", "source_metadata": { "name": "Mistral Nemotron", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "family": "nemotron", "release_date": "2025-06-11", "last_updated": "2025-06-12", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-nemotron-3-content-safety", "source_id": "nvidia/nemotron-3-content-safety", "source_metadata": { "name": "Nemotron 3 Content Safety", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "family": "nemotron", "release_date": "2026-04-16", "last_updated": "2026-04-16", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-nemotron-3-nano-30b-a3b", "source_id": "nvidia/nemotron-3-nano-30b-a3b", "source_metadata": { "name": "Nemotron 3 Nano 30B A3B", "description": "Small Nemotron 3 MoE for efficient coding, math, and long-context agents", "family": "nemotron", "release_date": "2025-12-15", "last_updated": "2025-12-15", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-nemotron-3-nano-omni-30b-a3b-reasoning", "source_id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning", "source_metadata": { "name": "Nemotron 3 Nano Omni 30B A3B Reasoning", "description": "Open Nemotron omni model combining reasoning with text, vision, and audio", "family": "nemotron", "release_date": "2026-04-28", "last_updated": "2026-04-28", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 65536 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-nemotron-3-super-120b-a12b", "source_id": "nvidia/nemotron-3-super-120b-a12b", "source_metadata": { "name": "Nemotron 3 Super 120B A12B", "description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads", "family": "nemotron", "release_date": "2026-03-11", "last_updated": "2026-03-11", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-nemotron-3-ultra-550b-a55b", "source_id": "nvidia/nemotron-3-ultra-550b-a55b", "source_metadata": { "name": "Nemotron 3 Ultra 550B A55B", "description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy", "family": "nemotron", "release_date": "2026-06-04", "last_updated": "2026-06-04", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 128000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-nemotron-3-5-content-safety", "source_id": "nvidia/nemotron-3.5-content-safety", "source_metadata": { "name": "Nemotron 3.5 Content Safety", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "family": "nemotron", "release_date": "2026-06-04", "last_updated": "2026-06-04", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-nemotron-3-5-lightning", "source_id": "nvidia/nemotron-3.5-lightning", "source_metadata": { "name": "Nemotron 3.5 Lightning 30B A3B", "description": "Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads", "family": "nemotron", "release_date": "2026-08-11", "last_updated": "2026-08-11", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 262144 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-nemotron-cascade-2-30b-a3b", "source_id": "nvidia/nemotron-cascade-2-30b-a3b", "source_metadata": { "name": "Nemotron Cascade 2 30B A3B", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "family": "nemotron", "release_date": "2026-03-24", "last_updated": "2026-04-09", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-nemotron-content-safety-reasoning-4b", "source_id": "nvidia/nemotron-content-safety-reasoning-4b", "source_metadata": { "name": "Nemotron Content Safety Reasoning 4B", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "family": "nemotron", "release_date": "2026-01-22", "last_updated": "2026-01-22", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-nemotron-mini-4b-instruct", "source_id": "nvidia/nemotron-mini-4b-instruct", "source_metadata": { "name": "Nemotron Mini 4B Instruct", "description": "Compact Nemotron model for efficient reasoning and deployable AI agents", "family": "nemotron", "release_date": "2024-08-21", "last_updated": "2024-08-26", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-nemotron-nano-12b-v2-vl", "source_id": "nvidia/nemotron-nano-12b-v2-vl", "source_metadata": { "name": "Nemotron Nano 12B v2 VL", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "family": "nemotron", "release_date": "2025-10-28", "last_updated": "2025-10-28", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 128000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-nemotron-nano-9b-v2", "source_id": "nvidia/nemotron-nano-9b-v2", "source_metadata": { "name": "Nemotron Nano 9B v2", "description": "Compact Nemotron model for efficient reasoning and deployable AI agents", "family": "nemotron", "release_date": "2025-08-18", "last_updated": "2025-08-18", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-nvidia-nemotron-voicechat", "source_id": "nvidia/nemotron-voicechat", "source_metadata": { "name": "Nemotron VoiceChat", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "family": "nemotron", "release_date": "2026-03-16", "last_updated": "2026-03-16", "knowledge_cutoff": null, "modalities": { "input": [ "text", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-3-5-turbo", "source_id": "openai/gpt-3.5-turbo", "source_metadata": { "name": "GPT-3.5-turbo", "description": "Compact GPT model for low-latency assistance and high-volume workloads", "family": "gpt", "release_date": "2023-03-01", "last_updated": "2023-11-06", "knowledge_cutoff": "2021-09-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": false, "temperature": true }, "limits": { "context": 16385, "input": null, "output": 4096 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-4", "source_id": "openai/gpt-4", "source_metadata": { "name": "GPT-4", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "family": "gpt", "release_date": "2023-11-06", "last_updated": "2024-04-09", "knowledge_cutoff": "2023-11", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 8192, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-4-turbo", "source_id": "openai/gpt-4-turbo", "source_metadata": { "name": "GPT-4 Turbo", "description": "Compact GPT model for low-latency assistance and high-volume workloads", "family": "gpt", "release_date": "2023-11-06", "last_updated": "2024-04-09", "knowledge_cutoff": "2023-12", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-4-1", "source_id": "openai/gpt-4.1", "source_metadata": { "name": "GPT-4.1", "description": "Long-lived GPT workhorse for coding, instruction following, and production apps", "family": "gpt", "release_date": "2025-04-14", "last_updated": "2025-04-14", "knowledge_cutoff": "2024-04", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1047576, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-4-1-mini", "source_id": "openai/gpt-4.1-mini", "source_metadata": { "name": "GPT-4.1 mini", "description": "Affordable GPT-4.1 lane for fast coding help and structured extraction", "family": "gpt-mini", "release_date": "2025-04-14", "last_updated": "2025-04-14", "knowledge_cutoff": "2024-04", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1047576, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-4-1-nano", "source_id": "openai/gpt-4.1-nano", "source_metadata": { "name": "GPT-4.1 nano", "description": "Tiny GPT-4.1 option for classification, routing, and very high-volume tasks", "family": "gpt-nano", "release_date": "2025-04-14", "last_updated": "2025-04-14", "knowledge_cutoff": "2024-04", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1047576, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-4o", "source_id": "openai/gpt-4o", "source_metadata": { "name": "GPT-4o", "description": "Omni-era GPT for multimodal chat, practical coding, and general assistants", "family": "gpt", "release_date": "2024-05-13", "last_updated": "2024-08-06", "knowledge_cutoff": "2023-09", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 16384 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-4o-2024-05-13", "source_id": "openai/gpt-4o-2024-05-13", "source_metadata": { "name": "GPT-4o (2024-05-13)", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "family": "gpt", "release_date": "2024-05-13", "last_updated": "2024-05-13", "knowledge_cutoff": "2023-09", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-4o-2024-08-06", "source_id": "openai/gpt-4o-2024-08-06", "source_metadata": { "name": "GPT-4o (2024-08-06)", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "family": "gpt", "release_date": "2024-08-06", "last_updated": "2024-08-06", "knowledge_cutoff": "2023-09", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 16384 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-4o-2024-11-20", "source_id": "openai/gpt-4o-2024-11-20", "source_metadata": { "name": "GPT-4o (2024-11-20)", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "family": "gpt", "release_date": "2024-11-20", "last_updated": "2024-11-20", "knowledge_cutoff": "2023-09", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 16384 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-4o-mini", "source_id": "openai/gpt-4o-mini", "source_metadata": { "name": "GPT-4o mini", "description": "Small omni GPT for cheap multimodal assistance and production-scale traffic", "family": "gpt-mini", "release_date": "2024-07-18", "last_updated": "2024-07-18", "knowledge_cutoff": "2023-09", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 16384 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5", "source_id": "openai/gpt-5", "source_metadata": { "name": "GPT-5", "description": "Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows", "family": "gpt", "release_date": "2025-08-07", "last_updated": "2025-08-07", "knowledge_cutoff": "2024-09-30", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-chat-latest", "source_id": "openai/gpt-5-chat-latest", "source_metadata": { "name": "GPT-5 Chat (latest)", "description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows", "family": "gpt-codex", "release_date": "2025-08-07", "last_updated": "2025-08-07", "knowledge_cutoff": "2024-09-30", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": false, "structured_output": true, "temperature": false }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-codex", "source_id": "openai/gpt-5-codex", "source_metadata": { "name": "GPT-5-Codex", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "family": "gpt-codex", "release_date": "2025-09-15", "last_updated": "2025-09-15", "knowledge_cutoff": "2024-09-30", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-image", "source_id": "openai/gpt-5-image", "source_metadata": { "name": "GPT-5 Image", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "family": "gpt", "release_date": "2025-10-14", "last_updated": "2025-10-14", "knowledge_cutoff": "2024-10-01", "modalities": { "input": [ "image", "text", "pdf" ], "output": [ "image", "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 400000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-image-mini", "source_id": "openai/gpt-5-image-mini", "source_metadata": { "name": "GPT-5 Image Mini", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "family": "gpt", "release_date": "2025-10-16", "last_updated": "2025-10-16", "knowledge_cutoff": null, "modalities": { "input": [ "pdf", "image", "text" ], "output": [ "image", "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 400000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-mini", "source_id": "openai/gpt-5-mini", "source_metadata": { "name": "GPT-5 Mini", "description": "Small GPT-5 for responsive agents, coding help, and everyday automation", "family": "gpt-mini", "release_date": "2025-08-07", "last_updated": "2025-08-07", "knowledge_cutoff": "2024-05-30", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-nano", "source_id": "openai/gpt-5-nano", "source_metadata": { "name": "GPT-5 Nano", "description": "Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs", "family": "gpt-nano", "release_date": "2025-08-07", "last_updated": "2025-08-07", "knowledge_cutoff": "2024-05-30", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-pro", "source_id": "openai/gpt-5-pro", "source_metadata": { "name": "GPT-5 Pro", "description": "Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning", "family": "gpt-pro", "release_date": "2025-10-06", "last_updated": "2025-10-06", "knowledge_cutoff": "2024-09-30", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 400000, "input": 272000, "output": 272000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-1", "source_id": "openai/gpt-5.1", "source_metadata": { "name": "GPT-5.1", "description": "Sharper GPT-5 generation for coding, product work, and tool-assisted tasks", "family": "gpt", "release_date": "2025-11-13", "last_updated": "2025-11-13", "knowledge_cutoff": "2024-09-30", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-1-chat-latest", "source_id": "openai/gpt-5.1-chat-latest", "source_metadata": { "name": "GPT-5.1 Chat", "description": "Chat-tuned GPT-5.1 for polished assistants, writing, and product conversations", "family": "gpt-codex", "release_date": "2025-11-13", "last_updated": "2025-11-13", "knowledge_cutoff": "2024-09-30", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 128000, "input": null, "output": 16384 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-1-codex", "source_id": "openai/gpt-5.1-codex", "source_metadata": { "name": "GPT-5.1 Codex", "description": "Codex GPT for repository edits, code review, and practical software agents", "family": "gpt-codex", "release_date": "2025-11-13", "last_updated": "2025-11-13", "knowledge_cutoff": "2024-09-30", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-1-codex-max", "source_id": "openai/gpt-5.1-codex-max", "source_metadata": { "name": "GPT-5.1 Codex Max", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "family": "gpt-codex", "release_date": "2025-11-13", "last_updated": "2025-11-13", "knowledge_cutoff": "2024-09-30", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-1-codex-mini", "source_id": "openai/gpt-5.1-codex-mini", "source_metadata": { "name": "GPT-5.1 Codex mini", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "family": "gpt-codex", "release_date": "2025-11-13", "last_updated": "2025-11-13", "knowledge_cutoff": "2024-09-30", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-2", "source_id": "openai/gpt-5.2", "source_metadata": { "name": "GPT-5.2", "description": "Reliable GPT generation for broad coding, writing, and tool-assisted product work", "family": "gpt", "release_date": "2025-12-11", "last_updated": "2025-12-11", "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-2-chat-latest", "source_id": "openai/gpt-5.2-chat-latest", "source_metadata": { "name": "GPT-5.2 Chat", "description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows", "family": "gpt-codex", "release_date": "2025-12-11", "last_updated": "2025-12-11", "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 128000, "input": null, "output": 16384 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-2-codex", "source_id": "openai/gpt-5.2-codex", "source_metadata": { "name": "GPT-5.2 Codex", "description": "Code-specialist GPT for repository edits, reviews, and long-running software agents", "family": "gpt-codex", "release_date": "2025-12-11", "last_updated": "2025-12-11", "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-2-pro", "source_id": "openai/gpt-5.2-pro", "source_metadata": { "name": "GPT-5.2 Pro", "description": "Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows", "family": "gpt-pro", "release_date": "2025-12-11", "last_updated": "2025-12-11", "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": false }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-3-chat-latest", "source_id": "openai/gpt-5.3-chat-latest", "source_metadata": { "name": "GPT-5.3 Chat (latest)", "description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows", "family": "gpt", "release_date": "2026-03-03", "last_updated": "2026-03-03", "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 16384 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-3-codex", "source_id": "openai/gpt-5.3-codex", "source_metadata": { "name": "GPT-5.3 Codex", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "family": "gpt-codex", "release_date": "2026-02-05", "last_updated": "2026-02-05", "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-3-codex-spark", "source_id": "openai/gpt-5.3-codex-spark", "source_metadata": { "name": "GPT-5.3 Codex Spark", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "family": "gpt-codex-spark", "release_date": "2026-02-05", "last_updated": "2026-02-05", "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 128000, "input": 100000, "output": 32000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-4", "source_id": "openai/gpt-5.4", "source_metadata": { "name": "GPT-5.4", "description": "Agent-ready GPT for coding and computer-use workflows at a lower cost", "family": "gpt", "release_date": "2026-03-05", "last_updated": "2026-03-05", "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1050000, "input": 922000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-4-image-2", "source_id": "openai/gpt-5.4-image-2", "source_metadata": { "name": "GPT-5.4 Image 2", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "family": "gpt", "release_date": "2026-04-21", "last_updated": "2026-04-21", "knowledge_cutoff": null, "modalities": { "input": [ "image", "text", "pdf" ], "output": [ "image", "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": false, "structured_output": true, "temperature": false }, "limits": { "context": 272000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-4-mini", "source_id": "openai/gpt-5.4-mini", "source_metadata": { "name": "GPT-5.4 mini", "description": "Strong small GPT for coding subagents, quick tool use, and high-volume work", "family": "gpt-mini", "release_date": "2026-03-17", "last_updated": "2026-03-17", "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-4-nano", "source_id": "openai/gpt-5.4-nano", "source_metadata": { "name": "GPT-5.4 nano", "description": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation", "family": "gpt-nano", "release_date": "2026-03-17", "last_updated": "2026-03-17", "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-4-pro", "source_id": "openai/gpt-5.4-pro", "source_metadata": { "name": "GPT-5.4 Pro", "description": "More exact GPT-5.4 tier for demanding professional reasoning and agent tasks", "family": "gpt-pro", "release_date": "2026-03-05", "last_updated": "2026-03-05", "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": false }, "limits": { "context": 1050000, "input": 922000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-5", "source_id": "openai/gpt-5.5", "source_metadata": { "name": "GPT-5.5", "description": "Default frontier GPT for coding, computer use, research, and knowledge work", "family": "gpt", "release_date": "2026-04-23", "last_updated": "2026-04-23", "knowledge_cutoff": "2025-12-01", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1050000, "input": 922000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-5-instant", "source_id": "openai/gpt-5.5-instant", "source_metadata": { "name": "GPT-5.5 Instant", "description": "Compact GPT model for low-latency assistance and high-volume workloads", "family": null, "release_date": "2026-05-05", "last_updated": "2026-05-28", "knowledge_cutoff": "2025-12-01", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-5-pro", "source_id": "openai/gpt-5.5-pro", "source_metadata": { "name": "GPT-5.5 Pro", "description": "Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding", "family": "gpt-pro", "release_date": "2026-04-23", "last_updated": "2026-04-23", "knowledge_cutoff": "2025-12-01", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1050000, "input": 922000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-6-cyber", "source_id": "openai/gpt-5.6-cyber", "source_metadata": { "name": "GPT-5.6 Cyber", "description": "Cybersecurity model for authorized vulnerability research and security testing", "family": "gpt", "release_date": "2026-08-07", "last_updated": "2026-08-07", "knowledge_cutoff": "2026-02-16", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 400000, "input": 272000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-6-luna", "source_id": "openai/gpt-5.6-luna", "source_metadata": { "name": "GPT-5.6 Luna", "description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads", "family": "gpt-luna", "release_date": "2026-07-09", "last_updated": "2026-07-09", "knowledge_cutoff": "2026-02-16", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1050000, "input": 922000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-6-sol", "source_id": "openai/gpt-5.6-sol", "source_metadata": { "name": "GPT-5.6 Sol", "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows", "family": "gpt-sol", "release_date": "2026-07-09", "last_updated": "2026-07-09", "knowledge_cutoff": "2026-02-16", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1050000, "input": 922000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-5-6-terra", "source_id": "openai/gpt-5.6-terra", "source_metadata": { "name": "GPT-5.6 Terra", "description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work", "family": "gpt-terra", "release_date": "2026-07-09", "last_updated": "2026-07-09", "knowledge_cutoff": "2026-02-16", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1050000, "input": 922000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-6-astra", "source_id": "openai/gpt-6-astra", "source_metadata": { "name": "GPT-6 Astra", "description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.", "family": "gpt-astra", "release_date": "2026-09-04", "last_updated": "2026-09-04", "knowledge_cutoff": "2026-04-30", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1050000, "input": 922000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-6-astra-fast", "source_id": "openai/gpt-6-astra-fast", "source_metadata": { "name": "GPT-6 Astra (Fast)", "description": "Fast variant of GPT-6 Astra for low-latency assistance and high-volume workloads.", "family": "gpt-astra", "release_date": "2026-09-04", "last_updated": "2026-09-04", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1050000, "input": 922000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-6-luna", "source_id": "openai/gpt-6-luna", "source_metadata": { "name": "GPT-6 Luna", "description": "OpenAI's most efficient model for focused, high-volume tasks", "family": "gpt-luna", "release_date": "2026-09-22", "last_updated": "2026-09-22", "knowledge_cutoff": "2026-05-18", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1050000, "input": 922000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-6-sol", "source_id": "openai/gpt-6-sol", "source_metadata": { "name": "GPT-6 Sol", "description": "OpenAI model for complex coding and agentic workflows", "family": "gpt-sol", "release_date": "2026-09-22", "last_updated": "2026-09-22", "knowledge_cutoff": "2026-04-20", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1050000, "input": 922000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-6-1-sol", "source_id": "openai/gpt-6.1-sol", "source_metadata": { "name": "GPT-6.1 Sol", "description": "Near-Astra performance for complex coding, computer use, and professional work at a lower cost.", "family": "gpt-sol", "release_date": "2026-09-29", "last_updated": "2026-09-29", "knowledge_cutoff": "2026-04-30", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1050000, "input": 922000, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-image-1", "source_id": "openai/gpt-image-1", "source_metadata": { "name": "GPT-Image-1", "description": "OpenAI image model for production generation, edits, and brand-safe visual workflows", "family": "gpt-image", "release_date": "2025-04-24", "last_updated": "2025-04-24", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 0, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-image-1-5", "source_id": "openai/gpt-image-1.5", "source_metadata": { "name": "GPT-Image-1.5", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "family": "gpt-image", "release_date": "2025-11-25", "last_updated": "2025-11-25", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 0, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-image-2", "source_id": "openai/gpt-image-2", "source_metadata": { "name": "GPT-Image-2", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "family": "gpt-image", "release_date": "2026-04-21", "last_updated": "2026-04-21", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 0, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-image-2-5-flare", "source_id": "openai/gpt-image-2.5-flare", "source_metadata": { "name": "GPT Image 2.5 Flare", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "family": "gpt-image", "release_date": "2026-09-08", "last_updated": "2026-09-08", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 0, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-image-2-5-sunburst", "source_id": "openai/gpt-image-2.5-sunburst", "source_metadata": { "name": "GPT Image 2.5 Sunburst", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "family": "gpt-image", "release_date": "2026-09-08", "last_updated": "2026-09-08", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 0, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-oss-120b", "source_id": "openai/gpt-oss-120b", "source_metadata": { "name": "GPT OSS 120B", "description": "Open GPT reasoning model for self-hosted agents and controllable deployments", "family": "gpt-oss", "release_date": "2025-08-05", "last_updated": "2025-08-05", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/openai/gpt-oss-120b" } ] } }, { "id": "model-openai-gpt-oss-20b", "source_id": "openai/gpt-oss-20b", "source_metadata": { "name": "GPT OSS 20B", "description": "Open GPT reasoning model for self-hosted agents and controllable deployments", "family": "gpt-oss", "release_date": "2025-08-05", "last_updated": "2025-08-05", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/openai/gpt-oss-20b" } ] } }, { "id": "model-openai-gpt-oss-safeguard-120b", "source_id": "openai/gpt-oss-safeguard-120b", "source_metadata": { "name": "GPT OSS Safeguard 120B", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "family": "gpt-oss", "release_date": "2025-10-29", "last_updated": "2025-10-29", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/openai/gpt-oss-safeguard-120b" } ] } }, { "id": "model-openai-gpt-oss-safeguard-20b", "source_id": "openai/gpt-oss-safeguard-20b", "source_metadata": { "name": "GPT OSS Safeguard 20B", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "family": "gpt-oss", "release_date": "2025-10-29", "last_updated": "2025-10-29", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/openai/gpt-oss-safeguard-20b" } ] } }, { "id": "model-openai-gpt-realtime-2-1", "source_id": "openai/gpt-realtime-2.1", "source_metadata": { "name": "GPT-Realtime-2.1", "description": "Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior", "family": "gpt", "release_date": "2026-07-06", "last_updated": "2026-07-06", "knowledge_cutoff": "2024-09-30", "modalities": { "input": [ "text", "audio", "image" ], "output": [ "text", "audio" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": false }, "limits": { "context": 128000, "input": 96000, "output": 32000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-gpt-realtime-whisper", "source_id": "openai/gpt-realtime-whisper", "source_metadata": { "name": "GPT Realtime Whisper", "description": "Streaming speech-to-text model for low-latency transcript deltas from live audio", "family": "whisper", "release_date": "2026-05-07", "last_updated": "2026-05-07", "knowledge_cutoff": null, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 16000, "input": null, "output": 2000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-o1", "source_id": "openai/o1", "source_metadata": { "name": "o1", "description": "O-series reasoning model for hard analysis, math, coding, and planning", "family": "o", "release_date": "2024-12-05", "last_updated": "2024-12-05", "knowledge_cutoff": "2023-09", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 200000, "input": null, "output": 100000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-o1-pro", "source_id": "openai/o1-pro", "source_metadata": { "name": "o1-pro", "description": "O-series reasoning model for hard analysis, math, coding, and planning", "family": "o-pro", "release_date": "2025-03-19", "last_updated": "2025-03-19", "knowledge_cutoff": "2023-09", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 200000, "input": null, "output": 100000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-o3", "source_id": "openai/o3", "source_metadata": { "name": "o3", "description": "Deliberate o-series reasoner for hard math, coding, and multi-step analysis", "family": "o", "release_date": "2025-04-16", "last_updated": "2025-04-16", "knowledge_cutoff": "2024-05", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 200000, "input": null, "output": 100000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-o3-deep-research", "source_id": "openai/o3-deep-research", "source_metadata": { "name": "o3-deep-research", "description": "Research model for long-horizon investigation, synthesis, and analytical reports", "family": "o", "release_date": "2024-06-26", "last_updated": "2024-06-26", "knowledge_cutoff": "2024-05", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": false }, "limits": { "context": 200000, "input": null, "output": 100000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-o3-mini", "source_id": "openai/o3-mini", "source_metadata": { "name": "o3-mini", "description": "Smaller o-series reasoner for economical coding, math, and planning tasks", "family": "o-mini", "release_date": "2024-12-20", "last_updated": "2025-01-29", "knowledge_cutoff": "2024-05", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 200000, "input": null, "output": 100000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-o3-pro", "source_id": "openai/o3-pro", "source_metadata": { "name": "o3-pro", "description": "High-effort o3 tier for difficult technical reasoning and careful answers", "family": "o-pro", "release_date": "2025-06-10", "last_updated": "2025-06-10", "knowledge_cutoff": "2024-05", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 200000, "input": null, "output": 100000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-o4-mini", "source_id": "openai/o4-mini", "source_metadata": { "name": "o4-mini", "description": "Fast o-series model for compact reasoning, coding, and tool use", "family": "o-mini", "release_date": "2025-04-16", "last_updated": "2025-04-16", "knowledge_cutoff": "2024-05", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 200000, "input": null, "output": 100000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-o4-mini-deep-research", "source_id": "openai/o4-mini-deep-research", "source_metadata": { "name": "o4-mini-deep-research", "description": "Research model for long-horizon investigation, synthesis, and analytical reports", "family": "o-mini", "release_date": "2024-06-26", "last_updated": "2024-06-26", "knowledge_cutoff": "2024-05", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": false }, "limits": { "context": 200000, "input": null, "output": 100000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-whisper-large-v3", "source_id": "openai/whisper-large-v3", "source_metadata": { "name": "Whisper 3 Large", "description": "Open Whisper checkpoint for robust multilingual transcription and captioning", "family": "whisper", "release_date": "2024-10-01", "last_updated": "2024-10-01", "knowledge_cutoff": null, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": null }, "limits": { "context": 448, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openai-whisper-large-v3-turbo", "source_id": "openai/whisper-large-v3-turbo", "source_metadata": { "name": "Whisper Large v3 Turbo", "description": "Speech transcription model for accurate audio-to-text and captioning workflows", "family": "whisper", "release_date": "2024-10-01", "last_updated": "2024-10-01", "knowledge_cutoff": null, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": null }, "limits": { "context": 448, "input": null, "output": 448 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-openbmb-minicpm5-1b", "source_id": "openbmb/minicpm5-1b", "source_metadata": { "name": "MiniCPM5-1B", "description": "Dense 1B-class open-source model for on-device and resource-constrained use, with native long-context support, Think / No Think chat modes, and tool calling", "family": null, "release_date": "2026-05-19", "last_updated": "2026-05-19", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": "apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/openbmb/MiniCPM5-1B" } ] } }, { "id": "model-openbmb-minicpm5-2b", "source_id": "openbmb/minicpm5-2b", "source_metadata": { "name": "MiniCPM5-2B", "description": "Dense 2B-class open-source model for on-device and resource-constrained use, with native long-context support, tool calling, and agentic tasks", "family": null, "release_date": "2026-09-06", "last_updated": "2026-09-12", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": "apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/openbmb/MiniCPM5-2B" } ] } }, { "id": "model-paddlepaddle-paddleocr-vl", "source_id": "paddlepaddle/paddleocr-vl", "source_metadata": { "name": "PaddleOCR VL", "description": "Compact vision-language model for multilingual document parsing, OCR, tables, formulas, and charts", "family": null, "release_date": "2025-10-16", "last_updated": "2025-10-16", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/PaddlePaddle/PaddleOCR-VL" } ] } }, { "id": "model-perceptron-perceptron-mk1", "source_id": "perceptron/perceptron-mk1", "source_metadata": { "name": "Perceptron Mk1", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "family": null, "release_date": "2026-05-12", "last_updated": "2026-05-12", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 32768, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-perplexity-sonar", "source_id": "perplexity/sonar", "source_metadata": { "name": "Sonar", "description": "Fast web-grounded Sonar for current answers, citations, and lightweight retrieval", "family": "sonar", "release_date": "2024-01-01", "last_updated": "2025-09-01", "knowledge_cutoff": "2025-09-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-perplexity-sonar-deep-research", "source_id": "perplexity/sonar-deep-research", "source_metadata": { "name": "Sonar Deep Research", "description": "Sonar search model for autonomous research and citation-backed long-form reports", "family": "sonar", "release_date": "2025-02-01", "last_updated": "2025-09-01", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 128000, "input": null, "output": 32768 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-perplexity-sonar-pro", "source_id": "perplexity/sonar-pro", "source_metadata": { "name": "Sonar Pro", "description": "Deeper Sonar search model with broader retrieval and stronger synthesis", "family": "sonar-pro", "release_date": "2024-01-01", "last_updated": "2025-09-01", "knowledge_cutoff": "2025-09-01", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-perplexity-sonar-reasoning-pro", "source_id": "perplexity/sonar-reasoning-pro", "source_metadata": { "name": "Sonar Reasoning Pro", "description": "Web-grounded Sonar for multi-step research questions that need cited reasoning", "family": "sonar-reasoning", "release_date": "2024-01-01", "last_updated": "2025-09-01", "knowledge_cutoff": "2025-09-01", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-phocinae-phocinae-largha-150m-v1", "source_id": "phocinae/phocinae-largha-150m-v1", "source_metadata": { "name": "Phocinae Largha 150M v1", "description": "Encoder decision model that answers typed questions (noul, choice, score) over text with calibrated probabilities, on CPU and GPU", "family": null, "release_date": "2026-10-08", "last_updated": "2026-10-09", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": false }, "limits": { "context": 8192, "input": null, "output": 0 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [ { "label": "Model card", "url": "https://huggingface.co/Phocinae/Phocinae-Largha-150M-v1", "type": "model_card" } ], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Phocinae/Phocinae-Largha-150M-v1" } ] } }, { "id": "model-poolside-laguna-m-1", "source_id": "poolside/laguna-m.1", "source_metadata": { "name": "Laguna M.1", "description": "Poolside's open-weight model for agentic coding and long-horizon work", "family": "laguna", "release_date": "2026-04-28", "last_updated": "2026-06-13", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-poolside-laguna-s-2-1", "source_id": "poolside/laguna-s-2.1", "source_metadata": { "name": "Laguna S 2.1", "description": "Agentic coding model from Poolside in the XS size class for local deployment", "family": "laguna", "release_date": "2026-07-21", "last_updated": "2026-07-21", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-poolside-laguna-xs-2-1", "source_id": "poolside/laguna-xs-2.1", "source_metadata": { "name": "Laguna XS 2.1", "description": "Agentic coding model from Poolside in the XS size class for local deployment", "family": "laguna", "release_date": "2026-07-02", "last_updated": "2026-07-02", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-poolside-laguna-xs-2", "source_id": "poolside/laguna-xs.2", "source_metadata": { "name": "Laguna XS.2", "description": "Agentic coding model from Poolside in the XS size class for local deployment", "family": "laguna", "release_date": "2026-04-28", "last_updated": "2026-06-13", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-quiverai-arrow-2", "source_id": "quiverai/arrow-2", "source_metadata": { "name": "Arrow 2", "description": "Fast SVG generation model for creation, vectorization, editing, and animation", "family": null, "release_date": "2026-09-16", "last_updated": "2026-09-16", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": null }, "limits": { "context": 131072, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-quiverai-arrow-2-telos", "source_id": "quiverai/arrow-2-telos", "source_metadata": { "name": "Arrow 2 Telos", "description": "High-fidelity SVG generation model for complex vector work and long-context refinement", "family": null, "release_date": "2026-09-16", "last_updated": "2026-09-16", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": null }, "limits": { "context": 1050000, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-rekaai-reka-edge", "source_id": "rekaai/reka-edge", "source_metadata": { "name": "Reka Edge", "description": "Multimodal model for analyzing text, images, documents, and rich media", "family": "reka", "release_date": "2026-03-20", "last_updated": "2026-03-20", "knowledge_cutoff": null, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 16384, "input": null, "output": 14745 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-rekaai-reka-flash-3", "source_id": "rekaai/reka-flash-3", "source_metadata": { "name": "Reka Flash 3", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "family": "reka", "release_date": "2025-03-12", "last_updated": "2025-03-12", "knowledge_cutoff": "2025-01-31", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 65536, "input": null, "output": 58982 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-relace-relace-apply-3", "source_id": "relace/relace-apply-3", "source_metadata": { "name": "Relace Apply 3", "description": "General-purpose chat model for instruction following, writing, and analysis", "family": null, "release_date": "2025-09-26", "last_updated": "2025-09-26", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": false, "temperature": false }, "limits": { "context": 256000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-relace-relace-search", "source_id": "relace/relace-search", "source_metadata": { "name": "Relace Search", "description": "Tool-capable chat model for instruction following and agentic application workflows", "family": null, "release_date": "2025-12-08", "last_updated": "2025-12-08", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-sakana-fugu", "source_id": "sakana/fugu", "source_metadata": { "name": "Fugu", "description": "Multi-agent model for routing expert agents across complex analytical tasks", "family": "fugu", "release_date": "2026-06-15", "last_updated": "2026-06-15", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1000000, "input": null, "output": null }, "reported_open_weights": false, "reported_license": null, "links": [ { "label": "Official model catalog", "url": "https://raw.githubusercontent.com/SakanaAI/fugu/refs/heads/main/configs/files/fugu.json", "type": "docs" } ], "weights": [] } }, { "id": "model-sakana-fugu-max", "source_id": "sakana/fugu-max", "source_metadata": { "name": "Fugu Max", "description": "Multi-agent model for routing expert agents across complex analytical tasks", "family": "fugu", "release_date": "2026-09-11", "last_updated": "2026-09-11", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1000000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-sakana-fugu-ultra", "source_id": "sakana/fugu-ultra", "source_metadata": { "name": "Fugu Ultra", "description": "Quality-first multi-agent model for hard research, analysis, and competitions", "family": "fugu", "release_date": "2026-06-15", "last_updated": "2026-06-15", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1000000, "input": null, "output": null }, "reported_open_weights": false, "reported_license": null, "links": [ { "label": "Official model catalog", "url": "https://raw.githubusercontent.com/SakanaAI/fugu/refs/heads/main/configs/files/fugu.json", "type": "docs" } ], "weights": [] } }, { "id": "model-sakana-fugu-ultra-v2", "source_id": "sakana/fugu-ultra-v2", "source_metadata": { "name": "Fugu Ultra v2", "description": "Quality-first multi-agent model for hard research, analysis, and competitions", "family": "fugu", "release_date": "2026-09-11", "last_updated": "2026-09-11", "knowledge_cutoff": "2026-08-28", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1000000, "input": null, "output": 128000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-sakana-sakana-namazu", "source_id": "sakana/sakana-namazu", "source_metadata": { "name": "Sakana Namazu", "description": "Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows", "family": "sakana-namazu", "release_date": "2026-08-03", "last_updated": "2026-08-03", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [ { "label": "Official product page", "url": "https://sakana.ai/namazu/", "type": "announcement" }, { "label": "Official model documentation", "url": "https://console.sakana.ai/models?model=sakana-namazu", "type": "docs" } ], "weights": [] } }, { "id": "model-sao10k-l3-lunaris-8b", "source_id": "sao10k/l3-lunaris-8b", "source_metadata": { "name": "Llama 3 8B Lunaris", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "family": "llama", "release_date": "2024-08-13", "last_updated": "2024-08-13", "knowledge_cutoff": "2023-12-31", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 8192, "input": null, "output": 7372 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-sao10k-l3-1-euryale-70b", "source_id": "sao10k/l3.1-euryale-70b", "source_metadata": { "name": "Llama 3.1 Euryale 70B v2.2", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "family": "llama", "release_date": "2024-08-28", "last_updated": "2024-08-28", "knowledge_cutoff": "2023-12-31", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-sao10k-l3-3-euryale-70b", "source_id": "sao10k/l3.3-euryale-70b", "source_metadata": { "name": "Llama 3.3 Euryale 70B", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "family": "llama", "release_date": "2024-12-18", "last_updated": "2024-12-18", "knowledge_cutoff": "2023-12-31", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-sarvam-sarvam-105b", "source_id": "sarvam/sarvam-105b", "source_metadata": { "name": "Sarvam 105B", "description": "Flagship Indian-language reasoning model for enterprise multilingual applications", "family": "sarvam", "release_date": "2025-09-01", "last_updated": "2025-09-01", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-sarvam-sarvam-30b", "source_id": "sarvam/sarvam-30b", "source_metadata": { "name": "Sarvam 30B", "description": "Efficient Indian-language reasoning model for chat, coding, and multilingual work", "family": "sarvam", "release_date": "2026-02-18", "last_updated": "2026-02-18", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 128000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-sdaia-allam-2-7b", "source_id": "sdaia/allam-2-7b", "source_metadata": { "name": "ALLaM-2-7b", "description": "ALLaM-2-7b instruction tuned model by SDAIA", "family": null, "release_date": "2025-01-23", "last_updated": "2025-01-23", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 4096, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/ALLaM-AI/ALLaM-2.0-7B-Instruct" } ] } }, { "id": "model-stepfun-step-3-5-flash", "source_id": "stepfun/step-3.5-flash", "source_metadata": { "name": "Step 3.5 Flash", "description": "StepFun flash lane for quick multimodal reasoning and coding assistance", "family": null, "release_date": "2026-01-29", "last_updated": "2026-02-13", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 256000, "input": 256000, "output": 256000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/stepfun-ai/Step-3.5-Flash" } ] } }, { "id": "model-stepfun-step-3-5-flash-2603", "source_id": "stepfun/step-3.5-flash-2603", "source_metadata": { "name": "Step 3.5 Flash 2603", "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "family": null, "release_date": "2026-04-02", "last_updated": "2026-04-02", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 256000, "input": 256000, "output": 256000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/stepfun-ai/Step-3.5-Flash" } ] } }, { "id": "model-stepfun-step-3-7-flash", "source_id": "stepfun/step-3.7-flash", "source_metadata": { "name": "Step 3.7 Flash", "description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts", "family": null, "release_date": "2026-05-29", "last_updated": "2026-05-29", "knowledge_cutoff": "2026-03-01", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 256000, "input": 256000, "output": 256000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/stepfun-ai/Step-3.7-Flash" } ] } }, { "id": "model-stepfun-step-5-preview", "source_id": "stepfun/step-5-preview", "source_metadata": { "name": "Step 5 Preview", "description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window", "family": null, "release_date": "2026-09-16", "last_updated": "2026-09-20", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": null }, "limits": { "context": 1000000, "input": 1000000, "output": 1000000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-swiss-ai-apertus-70b", "source_id": "swiss-ai/apertus-70b", "source_metadata": { "name": "Apertus 70B", "description": "Fully open 70B multilingual LLM supporting 1800+ languages with 65K context. Trained on 15T tokens of compliant open data. Apache 2.0, EU AI Act compliant.", "family": null, "release_date": "2025-09-02", "last_updated": "2025-09-02", "knowledge_cutoff": "2025-09", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 65536, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [ { "label": "Paper", "url": "https://arxiv.org/abs/2509.14233", "type": "paper" } ], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/swiss-ai/Apertus-70B-Instruct-2509" } ] } }, { "id": "model-swiss-ai-apertus-8b", "source_id": "swiss-ai/apertus-8b", "source_metadata": { "name": "Apertus 8B", "description": "Fully open 8B multilingual LLM supporting 1800+ languages with 65K context. Trained on compliant open data. Apache 2.0, EU AI Act compliant.", "family": null, "release_date": "2025-09-02", "last_updated": "2025-09-02", "knowledge_cutoff": "2025-09", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 65536, "input": null, "output": 8192 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [ { "label": "Paper", "url": "https://arxiv.org/abs/2509.14233", "type": "paper" } ], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509" } ] } }, { "id": "model-tencent-hy-mt2-1-8b", "source_id": "tencent/hy-mt2-1.8b", "source_metadata": { "name": "Hy-MT2-1.8B", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "family": "Hy", "release_date": "2026-08-20", "last_updated": "2026-08-20", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": false, "temperature": true }, "limits": { "context": 8192, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-tencent-hy-mt2-30b-a3b", "source_id": "tencent/hy-mt2-30b-a3b", "source_metadata": { "name": "Hy-MT2-30B-A3B", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "family": "Hy", "release_date": "2026-08-20", "last_updated": "2026-08-20", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 8192, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-tencent-hy-mt2-7b", "source_id": "tencent/hy-mt2-7b", "source_metadata": { "name": "Hy-MT2-7B", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "family": "Hy", "release_date": "2026-08-19", "last_updated": "2026-08-19", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 8192, "input": null, "output": 4096 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-tencent-hy3", "source_id": "tencent/hy3", "source_metadata": { "name": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "family": "Hy", "release_date": "2026-07-06", "last_updated": "2026-07-06", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 256000, "input": 192000, "output": 128000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/tencent/Hy3" } ] } }, { "id": "model-tencent-hy3-preview", "source_id": "tencent/hy3-preview", "source_metadata": { "name": "Hy3 preview", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "family": "Hy", "release_date": "2026-04-20", "last_updated": "2026-04-20", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 64000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/tencent/Hy3-preview" } ] } }, { "id": "model-tencent-hy4-preview", "source_id": "tencent/hy4-preview", "source_metadata": { "name": "Hy4 preview", "description": "A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.", "family": "Hy", "release_date": "2026-08-28", "last_updated": "2026-08-28", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1024000, "input": null, "output": 64000 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-thedrummer-cydonia-24b-v4-1", "source_id": "thedrummer/cydonia-24b-v4.1", "source_metadata": { "name": "Cydonia 24B V4.1", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "family": null, "release_date": "2025-09-27", "last_updated": "2025-09-27", "knowledge_cutoff": "2024-04-30", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 117964 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-thedrummer-skyfall-36b-v2", "source_id": "thedrummer/skyfall-36b-v2", "source_metadata": { "name": "Skyfall 36B V2", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "family": null, "release_date": "2025-03-10", "last_updated": "2025-03-10", "knowledge_cutoff": "2024-06-30", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 32768, "input": null, "output": 29491 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-thedrummer-unslopnemo-12b", "source_id": "thedrummer/unslopnemo-12b", "source_metadata": { "name": "UnslopNemo 12B", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "family": null, "release_date": "2024-11-08", "last_updated": "2024-11-08", "knowledge_cutoff": "2024-04-30", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 1024000, "input": null, "output": 819200 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-thinkingmachines-inkling", "source_id": "thinkingmachines/inkling", "source_metadata": { "name": "Inkling", "description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio", "family": "ling", "release_date": "2026-07-15", "last_updated": "2026-07-15", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 1048576 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/thinkingmachines/Inkling" } ] } }, { "id": "model-thinkingmachines-inkling-small", "source_id": "thinkingmachines/inkling-small", "source_metadata": { "name": "Inkling Small", "description": "Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio", "family": "ling", "release_date": "2026-07-30", "last_updated": "2026-07-30", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 1048576 }, "reported_open_weights": true, "reported_license": "Apache-2.0", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/thinkingmachines/Inkling-Small" } ] } }, { "id": "model-trendyol-asure-12b", "source_id": "trendyol/asure-12b", "source_metadata": { "name": "Trendyol Asure 12B", "description": "Turkish-language multimodal instruct model built on Gemma 3 12B for e-commerce text, chat, and image-text tasks", "family": "gemma", "release_date": "2026-02-19", "last_updated": "2026-02-20", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": null }, "reported_open_weights": true, "reported_license": "Gemma", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/Trendyol/Trendyol-LLM-Asure-12B" } ] } }, { "id": "model-typesafe-jev-latest", "source_id": "typesafe/jev-latest", "source_metadata": { "name": "Jev", "description": "System One model for fast, typed probabilistic decisions over text or structured state", "family": null, "release_date": "2026-09-15", "last_updated": "2026-09-15", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": false }, "limits": { "context": 64000, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-unbiased-pareto", "source_id": "unbiased/pareto", "source_metadata": { "name": "Pareto", "description": "Blended multimodal model that runs multiple language models in parallel and returns a synthesized answer", "family": null, "release_date": "2026-09-17", "last_updated": "2026-09-17", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-undi95-remm-slerp-l2-13b", "source_id": "undi95/remm-slerp-l2-13b", "source_metadata": { "name": "ReMM SLERP 13B", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "family": null, "release_date": "2023-07-22", "last_updated": "2023-07-22", "knowledge_cutoff": "2023-06-30", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": true, "temperature": true }, "limits": { "context": 6144, "input": null, "output": 5529 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-upstage-solar-pro2", "source_id": "upstage/solar-pro2", "source_metadata": { "name": "Solar Pro 2", "description": "Flagship model for demanding analysis, coding, and production agent workflows", "family": "solar-pro", "release_date": "2025-05-20", "last_updated": "2025-05-20", "knowledge_cutoff": "2025-03", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 65536, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-upstage-solar-pro3", "source_id": "upstage/solar-pro3", "source_metadata": { "name": "Solar Pro 3", "description": "Flagship model for demanding analysis, coding, and production agent workflows", "family": "solar-pro", "release_date": "2026-01", "last_updated": "2026-01", "knowledge_cutoff": "2025-03", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-upstage-solar-pro4", "source_id": "upstage/solar-pro4", "source_metadata": { "name": "Solar Pro 4", "description": "Upstage's flagship model, specialized for agentic use", "family": "solar-pro", "release_date": "2026-08-06", "last_updated": "2026-08-06", "knowledge_cutoff": "2026-02", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 524288, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-vispark-vision-large", "source_id": "vispark/vision-large", "source_metadata": { "name": "Vision Large", "description": "Most capable Vision model for complex reasoning, detailed media analysis, and structured output over a 1M-token context window.", "family": null, "release_date": "2024-05-15", "last_updated": "2026-09", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-vispark-vision-medium", "source_id": "vispark/vision-medium", "source_metadata": { "name": "Vision Medium", "description": "Balanced multimodal model pairing a 1M-token context window with deeper reasoning for analysis, content creation, and tool use across text, image, audio, video, and PDF inputs.", "family": null, "release_date": "2024-05-15", "last_updated": "2026-09", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-vispark-vision-small", "source_id": "vispark/vision-small", "source_metadata": { "name": "Vision Small", "description": "Fast, low-cost multimodal model for understanding text, images, audio, video, and PDFs, with tool calling and a 1M-token context window.", "family": null, "release_date": "2024-05-15", "last_updated": "2026-09", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 65536 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-vivgrid-viv-fast", "source_id": "vivgrid/viv-fast", "source_metadata": { "name": "Viv Fast", "description": "Fast coding model", "family": null, "release_date": "2026-09-21", "last_updated": "2026-09-21", "knowledge_cutoff": "2026-09", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": false }, "limits": { "context": 1000000, "input": null, "output": 256000 }, "reported_open_weights": false, "reported_license": null, "links": [ { "label": "Model docs", "url": "https://docs.vivgrid.com/models/viv-fast" } ], "weights": [] } }, { "id": "model-writer-palmyra-x4", "source_id": "writer/palmyra-x4", "source_metadata": { "name": "Palmyra X4", "description": "Enterprise language model for workflow automation, coding, data analysis, and tool use", "family": "palmyra", "release_date": "2024-10-09", "last_updated": "2025-04-28", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 4096 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-writer-palmyra-x5", "source_id": "writer/palmyra-x5", "source_metadata": { "name": "Palmyra X5", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "family": "palmyra", "release_date": "2025-04-28", "last_updated": "2025-04-28", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 8192 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-4-fast-non-reasoning", "source_id": "xai/grok-4-fast-non-reasoning", "source_metadata": { "name": "X-Ai/Grok-4-Fast-Non-Reasoning", "description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "family": null, "release_date": "2025-12-18", "last_updated": "2025-12-18", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 2000000, "input": null, "output": 2000000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-4-fast-reasoning", "source_id": "xai/grok-4-fast-reasoning", "source_metadata": { "name": "X-Ai/Grok-4-Fast-Reasoning", "description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "family": null, "release_date": "2025-12-18", "last_updated": "2025-12-18", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 2000000, "input": null, "output": 2000000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-4-1-fast", "source_id": "xai/grok-4.1-fast", "source_metadata": { "name": "Grok 4.1 Fast", "description": "xAI's fast agentic tool-calling model with a 2M context window; non-reasoning variant for low-latency responses", "family": "grok", "release_date": "2025-11-19", "last_updated": "2025-11-19", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 2000000, "input": null, "output": 30000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-4-1-fast-reasoning", "source_id": "xai/grok-4.1-fast-reasoning", "source_metadata": { "name": "Grok 4.1 Fast (Reasoning)", "description": "xAI's fast agentic tool-calling model with a 2M context window and built-in reasoning", "family": "grok", "release_date": "2025-11-19", "last_updated": "2025-11-19", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 2000000, "input": null, "output": 30000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-4-20-0309-non-reasoning", "source_id": "xai/grok-4.20-0309-non-reasoning", "source_metadata": { "name": "Grok 4.20 (Non-Reasoning)", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "family": "grok", "release_date": "2026-03-09", "last_updated": "2026-03-09", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 30000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-4-20-0309-reasoning", "source_id": "xai/grok-4.20-0309-reasoning", "source_metadata": { "name": "Grok 4.20 (Reasoning)", "description": "Reasoning Grok for document-heavy analysis and long-horizon tool use", "family": "grok", "release_date": "2026-03-09", "last_updated": "2026-03-09", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 30000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-4-3", "source_id": "xai/grok-4.3", "source_metadata": { "name": "Grok 4.3", "description": "xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk", "family": "grok", "release_date": "2026-04-17", "last_updated": "2026-04-17", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 30000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-4-5", "source_id": "xai/grok-4.5", "source_metadata": { "name": "Grok 4.5", "description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk", "family": "grok", "release_date": "2026-07-08", "last_updated": "2026-07-08", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 500000, "input": null, "output": 500000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-4-6", "source_id": "xai/grok-4.6", "source_metadata": { "name": "Grok 4.6", "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", "family": "grok", "release_date": "2026-08-12", "last_updated": "2026-08-12", "knowledge_cutoff": "2026-02-01", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 500000, "input": null, "output": 500000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-4-7", "source_id": "xai/grok-4.7", "source_metadata": { "name": "Grok 4.7", "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", "family": "grok", "release_date": "2026-09-21", "last_updated": "2026-09-21", "knowledge_cutoff": "2026-05", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 500000, "input": null, "output": 500000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-build-0-1", "source_id": "xai/grok-build-0.1", "source_metadata": { "name": "Grok Build 0.1", "description": "Fast Grok coding model tuned for agentic engineering and iterative edits", "family": "grok-build", "release_date": "2026-04-16", "last_updated": "2026-04-16", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 256000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-code-fast-1", "source_id": "xai/grok-code-fast-1", "source_metadata": { "name": "x-AI/Grok-Code-Fast 1", "description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "family": null, "release_date": "2025-09-02", "last_updated": "2025-09-02", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": false, "temperature": true }, "limits": { "context": 256000, "input": null, "output": 10000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-imagine-image", "source_id": "xai/grok-imagine-image", "source_metadata": { "name": "Grok Imagine Image", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "family": "grok", "release_date": "2026-01-28", "last_updated": "2026-01-28", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "image", "pdf" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 16000, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-imagine-image-2-0", "source_id": "xai/grok-imagine-image-2.0", "source_metadata": { "name": "Grok Imagine Image 2.0", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "family": "grok", "release_date": "2026-08-07", "last_updated": "2026-08-07", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 8000, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-imagine-image-quality", "source_id": "xai/grok-imagine-image-quality", "source_metadata": { "name": "Grok Imagine Image Quality", "description": "Higher-fidelity Grok Imagine image model for prompt-driven generation, editing, and visual design workflows", "family": "grok", "release_date": "2026-04-03", "last_updated": "2026-04-03", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 16000, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-imagine-video-1-5", "source_id": "xai/grok-imagine-video-1.5", "source_metadata": { "name": "Grok Imagine Video 1.5", "description": "Video model for image-to-video generation, editing, and extension workflows", "family": "grok", "release_date": "2026-05-30", "last_updated": "2026-05-30", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 1024, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-imagine-video-1-5-lite", "source_id": "xai/grok-imagine-video-1.5-lite", "source_metadata": { "name": "Grok Imagine Video 1.5 Lite", "description": "Cost-efficient video model for text-to-video and image-to-video generation", "family": "grok", "release_date": "2026-10-01", "last_updated": "2026-10-01", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 1024, "input": null, "output": 0 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-voice-stt-1-0", "source_id": "xai/grok-voice-stt-1.0", "source_metadata": { "name": "Grok Voice STT 1.0", "description": "Grok Voice STT 1.0 is xAI's speech-to-text model. It supports transcription with word-level timestamps, optional speaker diarization, and multichannel audio.", "family": null, "release_date": "2026-08-04", "last_updated": "2026-08-04", "knowledge_cutoff": null, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 15000, "input": null, "output": 15000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xai-grok-voice-tts-1-0", "source_id": "xai/grok-voice-tts-1.0", "source_metadata": { "name": "Grok Voice TTS 1.0", "description": "Convert text into spoken audio with a single API call. The API supports a rich set of expressive voices, inline speech tags for fine-grained delivery control, and output formats from high-fidelity MP3 to telephony-optimized μ-law.", "family": null, "release_date": "2026-07-31", "last_updated": "2026-07-31", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "capabilities": { "attachment": false, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 15000, "input": null, "output": 15000 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xiaomi-mimo-v2-flash", "source_id": "xiaomi/mimo-v2-flash", "source_metadata": { "name": "MiMo-V2-Flash", "description": "MiMo flash model for fast multimodal assistance and agent workflows", "family": "mimo", "release_date": "2025-12-16", "last_updated": "2026-02-04", "knowledge_cutoff": "2024-12-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 65536 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash" } ] } }, { "id": "model-xiaomi-mimo-v2-omni", "source_id": "xiaomi/mimo-v2-omni", "source_metadata": { "name": "MiMo-V2-Omni", "description": "MiMo omni model for text, image, video, audio, and agents", "family": "mimo", "release_date": "2026-03-18", "last_updated": "2026-03-18", "knowledge_cutoff": "2024-12", "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 262144, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xiaomi-mimo-v2-pro", "source_id": "xiaomi/mimo-v2-pro", "source_metadata": { "name": "MiMo-V2-Pro", "description": "Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks", "family": "mimo", "release_date": "2026-03-18", "last_updated": "2026-03-18", "knowledge_cutoff": "2024-12", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-xiaomi-mimo-v2-5", "source_id": "xiaomi/mimo-v2.5", "source_metadata": { "name": "MiMo-V2.5", "description": "Open MiMo model for multimodal coding agents and long-context automation", "family": "mimo", "release_date": "2026-04-22", "last_updated": "2026-04-22", "knowledge_cutoff": "2024-12", "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/XiaomiMiMo/MiMo-V2.5" } ] } }, { "id": "model-xiaomi-mimo-v2-5-pro", "source_id": "xiaomi/mimo-v2.5-pro", "source_metadata": { "name": "MiMo-V2.5-Pro", "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution", "family": "mimo", "release_date": "2026-04-22", "last_updated": "2026-04-22", "knowledge_cutoff": "2024-12", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro" } ] } }, { "id": "model-xiaomi-mimo-v2-5-pro-ultraspeed", "source_id": "xiaomi/mimo-v2.5-pro-ultraspeed", "source_metadata": { "name": "MiMo-V2.5-Pro-UltraSpeed", "description": "MiMo pro model for strong multimodal reasoning and agent execution", "family": "mimo", "release_date": "2026-06-08", "last_updated": "2026-06-09", "knowledge_cutoff": "2024-12", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro-FP4-DFlash" } ] } }, { "id": "model-xiaomi-mimo-v2-6-flash", "source_id": "xiaomi/mimo-v2.6-flash", "source_metadata": { "name": "MiMo-V2.6-Flash", "description": "MiMo Flash model for multimodal coding agents and long-context automation", "family": "mimo", "release_date": "2026-09-22", "last_updated": "2026-09-22", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL" } ] } }, { "id": "model-xiaomi-mimo-v2-6-pro", "source_id": "xiaomi/mimo-v2.6-pro", "source_metadata": { "name": "MiMo-V2.6-Pro", "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution", "family": "mimo", "release_date": "2026-09-22", "last_updated": "2026-09-22", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL" } ] } }, { "id": "model-xiaomi-mimo-v2-6-pro-ultraspeed", "source_id": "xiaomi/mimo-v2.6-pro-ultraspeed", "source_metadata": { "name": "MiMo-V2.6-Pro-UltraSpeed", "description": "MiMo pro model for strong multimodal reasoning and agent execution", "family": "mimo", "release_date": "2026-09-21", "last_updated": "2026-09-21", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 1048576, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL" } ] } }, { "id": "model-zhipuai-autoglm-phone-9b-multilingual", "source_id": "zhipuai/autoglm-phone-9b-multilingual", "source_metadata": { "name": "AutoGLM Phone 9B Multilingual", "description": "Multilingual visual model for operating smartphone interfaces and mobile agents", "family": "glm", "release_date": "2025-12-10", "last_updated": "2025-12-10", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": true }, "limits": { "context": 65536, "input": null, "output": 65536 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/zai-org/AutoGLM-Phone-9B-Multilingual" } ] } }, { "id": "model-zhipuai-glm-4-5", "source_id": "zhipuai/glm-4.5", "source_metadata": { "name": "GLM-4.5", "description": "Hybrid-reasoning GLM release that made the 4.5 line broadly useful", "family": "glm", "release_date": "2025-07-28", "last_updated": "2025-07-28", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 98304 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/zai-org/GLM-4.5" } ] } }, { "id": "model-zhipuai-glm-4-5-air", "source_id": "zhipuai/glm-4.5-air", "source_metadata": { "name": "GLM-4.5-Air", "description": "Lighter GLM-4.5 variant for fast coding assistance and cheaper agents", "family": "glm-air", "release_date": "2025-07-28", "last_updated": "2025-07-28", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 98304 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/zai-org/GLM-4.5-Air" } ] } }, { "id": "model-zhipuai-glm-4-5-flash", "source_id": "zhipuai/glm-4.5-flash", "source_metadata": { "name": "GLM-4.5-Flash", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "family": "glm-flash", "release_date": "2025-07-28", "last_updated": "2025-07-28", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 131072, "input": null, "output": 98304 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-zhipuai-glm-4-5v", "source_id": "zhipuai/glm-4.5v", "source_metadata": { "name": "GLM-4.5V", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "family": "glm", "release_date": "2025-08-11", "last_updated": "2025-08-11", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 64000, "input": null, "output": 16384 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/zai-org/GLM-4.5V" } ] } }, { "id": "model-zhipuai-glm-4-6", "source_id": "zhipuai/glm-4.6", "source_metadata": { "name": "GLM-4.6", "description": "Late GLM-4 workhorse for coding agents, reasoning, and structured tasks", "family": "glm", "release_date": "2025-09-30", "last_updated": "2025-09-30", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 204800, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/zai-org/GLM-4.6" } ] } }, { "id": "model-zhipuai-glm-4-6v", "source_id": "zhipuai/glm-4.6v", "source_metadata": { "name": "GLM-4.6V", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "family": "glm", "release_date": "2025-12-08", "last_updated": "2025-12-08", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/zai-org/GLM-4.6V" } ] } }, { "id": "model-zhipuai-glm-4-6v-flash", "source_id": "zhipuai/glm-4.6v-flash", "source_metadata": { "name": "GLM-4.6V-Flash", "description": "Lightweight GLM vision model for visual reasoning, documents, and multimodal agents", "family": "glm-flash", "release_date": "2025-12-08", "last_updated": "2025-12-08", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 128000, "input": null, "output": 32768 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/zai-org/GLM-4.6V-Flash" } ] } }, { "id": "model-zhipuai-glm-4-7", "source_id": "zhipuai/glm-4.7", "source_metadata": { "name": "GLM-4.7", "description": "Mature GLM model for dependable coding, reasoning, and structured agent tasks", "family": "glm", "release_date": "2025-12-22", "last_updated": "2025-12-22", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 204800, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/zai-org/GLM-4.7" } ] } }, { "id": "model-zhipuai-glm-4-7-flash", "source_id": "zhipuai/glm-4.7-flash", "source_metadata": { "name": "GLM-4.7-Flash", "description": "Budget GLM lane for fast coding help, routing, and everyday automation", "family": "glm-flash", "release_date": "2026-01-19", "last_updated": "2026-01-19", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/zai-org/GLM-4.7-Flash" } ] } }, { "id": "model-zhipuai-glm-4-7-flashx", "source_id": "zhipuai/glm-4.7-flashx", "source_metadata": { "name": "GLM-4.7-FlashX", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "family": "glm-flash", "release_date": "2026-01-19", "last_updated": "2026-01-19", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/zai-org/GLM-4.7-Flash" } ] } }, { "id": "model-zhipuai-glm-5", "source_id": "zhipuai/glm-5", "source_metadata": { "name": "GLM-5", "description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows", "family": "glm", "release_date": "2026-02-12", "last_updated": "2026-02-12", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 204800, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/zai-org/GLM-5" } ] } }, { "id": "model-zhipuai-glm-5-turbo", "source_id": "zhipuai/glm-5-turbo", "source_metadata": { "name": "GLM-5-Turbo", "description": "Faster GLM-5 lane for coding agents that need lower latency", "family": "glm", "release_date": "2026-03-16", "last_updated": "2026-03-16", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-zhipuai-glm-5-1", "source_id": "zhipuai/glm-5.1", "source_metadata": { "name": "GLM-5.1", "description": "Strong GLM coding model for agentic engineering, terminals, and repository generation", "family": "glm", "release_date": "2026-04-07", "last_updated": "2026-04-07", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/zai-org/GLM-5.1" } ] } }, { "id": "model-zhipuai-glm-5-2", "source_id": "zhipuai/glm-5.2", "source_metadata": { "name": "GLM-5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "family": "glm", "release_date": "2026-06-13", "last_updated": "2026-06-13", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/zai-org/GLM-5.2" } ] } }, { "id": "model-zhipuai-glm-5-3", "source_id": "zhipuai/glm-5.3", "source_metadata": { "name": "GLM-5.3", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "family": "glm", "release_date": "2026-08-14", "last_updated": "2026-08-14", "knowledge_cutoff": null, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "attachment": false, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-zhipuai-glm-5-3-flash", "source_id": "zhipuai/glm-5.3-flash", "source_metadata": { "name": "GLM-5.3-Flash", "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", "family": "glm-flash", "release_date": "2026-08-26", "last_updated": "2026-08-26", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": true, "temperature": true }, "limits": { "context": 1000000, "input": null, "output": 131072 }, "reported_open_weights": true, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-zhipuai-glm-5v-turbo", "source_id": "zhipuai/glm-5v-turbo", "source_metadata": { "name": "GLM-5V-Turbo", "description": "Fast GLM vision model for screenshots, documents, and multimodal agent tasks", "family": "glm", "release_date": "2026-04-01", "last_updated": "2026-04-01", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "capabilities": { "attachment": true, "reasoning": true, "tool_call": true, "structured_output": null, "temperature": true }, "limits": { "context": 200000, "input": null, "output": 131072 }, "reported_open_weights": false, "reported_license": null, "links": [], "weights": [] } }, { "id": "model-zhipuai-glm-image", "source_id": "zhipuai/glm-image", "source_metadata": { "name": "GLM-Image", "description": "GLM-Image is an image generation model adopts a hybrid autoregressive + diffusion decoder architecture. In general image generation quality, GLM‑Image aligns with mainstream latent diffusion approaches, but it shows significant advantages in text-rendering and knowledge‑intensive generation scenarios. It performs especially well in tasks requiring precise semantic understanding and complex information expression, while maintaining strong capabilities in high‑fidelity and fine‑grained detail generation. In addition to text‑to‑image generation, GLM‑Image also supports a rich set of image‑to‑image tasks including image editing, style transfer, identity‑preserving generation, and multi‑subject consistency.", "family": null, "release_date": "2026-01-19", "last_updated": "2026-01-19", "knowledge_cutoff": null, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "capabilities": { "attachment": true, "reasoning": false, "tool_call": false, "structured_output": null, "temperature": false }, "limits": { "context": 10240, "input": null, "output": 0 }, "reported_open_weights": true, "reported_license": "MIT", "links": [], "weights": [ { "label": "Hugging Face", "url": "https://huggingface.co/zai-org/GLM-Image" } ] } } ] }