MODEL RADAR · OPENROUTER
Comparer les modèles d’IA sur une même base.
Tous les modèles actuellement référencés par OpenRouter, avec des informations cohérentes sur les modalités, le contexte, les tarifs, la configuration et les fournisseurs.
- PORTÉE DU CATALOGUE
- TOUS PUBLICS
- modèles
- 631
- fournisseurs
- 86
- dernière synchronisation
- 29 sept. 2026
openaiOpenAI: gpt-oss-120b
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
- Contexte
- 131K
- Entrée
- text
- Sortie
- text
openaiOpenAI: gpt-oss-120b (batch)
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
- Contexte
- 131K
- Entrée
- text
- Sortie
- text
openaiOpenAI: gpt-oss-20b
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
- Contexte
- 131K
- Entrée
- text
- Sortie
- text
openaiOpenAI: gpt-oss-20b (batch)
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
- Contexte
- 131K
- Entrée
- text
- Sortie
- text
anthropicAnthropic: Claude Opus 4.1
Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...
- Contexte
- 200K
- Entrée
- image · text · file
- Sortie
- text
anthropicAnthropic: Claude Opus 4.1 (batch)
Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...
- Contexte
- 200K
- Entrée
- image · text · file
- Sortie
- text
mistralaiMistral: Codestral 2508
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Blog Post
- Contexte
- 256K
- Entrée
- text · file
- Sortie
- text
mistralaiMistral: Codestral 2508 (batch)
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Blog Post
- Contexte
- 256K
- Entrée
- text · file
- Sortie
- text
qwenQwen: Qwen3 Coder 30B A3B Instruct
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...
- Contexte
- 262K
- Entrée
- text
- Sortie
- text
qwenQwen: Qwen3 30B A3B Instruct 2507
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...
- Contexte
- 262K
- Entrée
- text
- Sortie
- text
z-aiZ.ai: GLM 4.5
GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...
- Contexte
- 131K
- Entrée
- text
- Sortie
- text
z-aiZ.ai: GLM 4.5 Air
GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...
- Contexte
- 131K
- Entrée
- text
- Sortie
- text
qwenQwen: Qwen3 235B A22B Thinking 2507
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
- Contexte
- 131K
- Entrée
- text
- Sortie
- text
qwenQwen: Qwen3 Coder 480B A35B
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...
- Contexte
- 262K
- Entrée
- text
- Sortie
- text
bytedanceByteDance: UI-TARS 7B
UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...
- Contexte
- 128K
- Entrée
- image · text
- Sortie
- text
googleGoogle: Gemini 2.5 Flash Lite
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...
- Contexte
- 1.0M
- Entrée
- text · image · file · audio · video
- Sortie
- text
googleGoogle: Gemini 2.5 Flash Lite (batch)
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...
- Contexte
- 1.0M
- Entrée
- text · image · file · audio · video
- Sortie
- text
qwenQwen: Qwen3 235B A22B Instruct 2507
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...
- Contexte
- 262K
- Entrée
- text
- Sortie
- text
moonshotaiMoonshotAI: Kimi K2 0711
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
- Contexte
- 131K
- Entrée
- text
- Sortie
- text
cognitivecomputationsVenice: Uncensored
Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...
- Contexte
- 128K
- Entrée
- text
- Sortie
- text
tencentTencent: Hunyuan A13B Instruct
Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...
- Contexte
- 131K
- Entrée
- text
- Sortie
- text
morphMorph: Morph V3 Large
Morph's high-accuracy apply model for complex code edits. 4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initialcode}</code>...
- Contexte
- 262K
- Entrée
- text
- Sortie
- text
morphMorph: Morph V3 Fast
Morph's fastest apply model for code edits. 10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initialcode}</code> <update>{editsnippet}</update>...
- Contexte
- 82K
- Entrée
- text
- Sortie
- text
baiduBaidu: ERNIE 4.5 VL 424B A47B
ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...
- Contexte
- 123K
- Entrée
- image · text
- Sortie
- text