RADAR DES MODÈLES IA

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
740
fournisseurs
101
dernière synchronisation
20 nov. 2026
740 modèles
qwen logoqwen

Qwen: Qwen3 VL 235B A22B Instruct

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...

Contexte
262K
Entrée
text · image
Sortie
text
Entrée: $0.21Sortie: $1.9par million de tokens
Voir la fiche du modèle →
deepseek logodeepseek

DeepSeek: DeepSeek V3.1 Terminus

DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...

Contexte
164K
Entrée
text
Sortie
text
Entrée: $0.27Sortie: $1par million de tokens
Voir la fiche du modèle →
qwen logoqwen

Qwen: Qwen3 Coder Flash

Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...

Contexte
1M
Entrée
text
Sortie
text
Entrée: $0.195Sortie: $0.975par million de tokens
Voir la fiche du modèle →
qwen logoqwen

Qwen: Qwen3 Next 80B A3B Instruct

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...

Contexte
262K
Entrée
text
Sortie
text
Entrée: $0.1Sortie: $1.1par million de tokens
Voir la fiche du modèle →
moonshotai logomoonshotai

MoonshotAI: Kimi K2 0905

Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

Contexte
262K
Entrée
text
Sortie
text
Entrée: $0.6Sortie: $2.5par million de tokens
Voir la fiche du modèle →
nousresearch logonousresearch

Nous: Hermes 4 405B

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...

Contexte
131K
Entrée
text
Sortie
text
Entrée: $1Sortie: $3par million de tokens
Voir la fiche du modèle →
deepseek logodeepseek

DeepSeek: DeepSeek V3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

Contexte
164K
Entrée
text
Sortie
text
Entrée: $0.25Sortie: $0.95par million de tokens
Voir la fiche du modèle →
mistralai logomistralai

Mistral: Mistral Medium 3.1

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...

Contexte
131K
Entrée
text · image · file
Sortie
text
Entrée: $0.44Sortie: $2.2par million de tokens
Voir la fiche du modèle →
z-ai logoz-ai

Z.ai: GLM 4.5V

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...

Contexte
66K
Entrée
text · image
Sortie
text
Entrée: $0.6Sortie: $1.8par million de tokens
Voir la fiche du modèle →
openai logoopenai

OpenAI: GPT-5

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...

Contexte
400K
Entrée
text · image · file
Sortie
text
Entrée: $1.25Sortie: $10par million de tokens
Voir la fiche du modèle →
openai logoopenai

OpenAI: GPT-5 (batch)

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...

Contexte
400K
Entrée
text · image · file
Sortie
text
Entrée: $0.625Sortie: $5par million de tokens
Voir la fiche du modèle →
openai logoopenai

OpenAI: GPT-5 Mini

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

Contexte
400K
Entrée
text · image · file
Sortie
text
Entrée: $0.25Sortie: $2par million de tokens
Voir la fiche du modèle →
openai logoopenai

OpenAI: GPT-5 Mini (batch)

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

Contexte
400K
Entrée
text · image · file
Sortie
text
Entrée: $0.125Sortie: $1par million de tokens
Voir la fiche du modèle →
openai logoopenai

OpenAI: GPT-5 Nano

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

Contexte
400K
Entrée
text · image · file
Sortie
text
Entrée: $0.05Sortie: $0.4par million de tokens
Voir la fiche du modèle →
openai logoopenai

OpenAI: GPT-5 Nano (batch)

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

Contexte
400K
Entrée
text · image · file
Sortie
text
Entrée: $0.025Sortie: $0.2par million de tokens
Voir la fiche du modèle →
openai logoopenai

OpenAI: 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
Entrée: $0.09Sortie: $0.36par million de tokens
Voir la fiche du modèle →
openai logoopenai

OpenAI: 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
Entrée: $0.0296Sortie: $0.136par million de tokens
Voir la fiche du modèle →
openai logoopenai

OpenAI: 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
Entrée: $0.018Sortie: $0.09par million de tokens
Voir la fiche du modèle →
openai logoopenai

OpenAI: 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
Entrée: $0.024Sortie: $0.112par million de tokens
Voir la fiche du modèle →
anthropic logoanthropic

Anthropic: 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
Entrée: $15Sortie: $75par million de tokens
Voir la fiche du modèle →
anthropic logoanthropic

Anthropic: 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
Entrée: $7.5Sortie: $37.5par million de tokens
Voir la fiche du modèle →
mistralai logomistralai

Mistral: 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
Entrée: $0.3Sortie: $0.9par million de tokens
Voir la fiche du modèle →
qwen logoqwen

Qwen: 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
Entrée: $0.15Sortie: $0.6par million de tokens
Voir la fiche du modèle →
qwen logoqwen

Qwen: 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
Entrée: $0.1Sortie: $0.3par million de tokens
Voir la fiche du modèle →