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
z-ai logoz-ai

Z.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
Entrée: $0.6Sortie: $2.2par million de tokens
Voir la fiche du modèle →
z-ai logoz-ai

Z.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
Entrée: $0.13Sortie: $0.85par million de tokens
Voir la fiche du modèle →
qwen logoqwen

Qwen: 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
128K
Entrée
text
Sortie
text
Entrée: $0.45Sortie: $3.5par million de tokens
Voir la fiche du modèle →
qwen logoqwen

Qwen: 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
Entrée: $0.3Sortie: $1par million de tokens
Voir la fiche du modèle →
bytedance logobytedance

ByteDance: 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
Entrée: $0.1Sortie: $0.2par million de tokens
Voir la fiche du modèle →
google logogoogle

Google: 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
Entrée: $0.1Sortie: $0.4par million de tokens
Voir la fiche du modèle →
qwen logoqwen

Qwen: 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
Entrée: $0.14Sortie: $0.8par million de tokens
Voir la fiche du modèle →
moonshotai logomoonshotai

MoonshotAI: 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
Entrée: $0.57Sortie: $2.3par million de tokens
Voir la fiche du modèle →
cognitivecomputations logocognitivecomputations

Venice: 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
Entrée: $0.2Sortie: $0.9par million de tokens
Voir la fiche du modèle →
morph logomorph

Morph: 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
Entrée: $0.9Sortie: $1.9par million de tokens
Voir la fiche du modèle →
morph logomorph

Morph: Morph V3 Large (batch)

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
Entrée: $0.45Sortie: $0.95par million de tokens
Voir la fiche du modèle →
morph logomorph

Morph: 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
262K
Entrée
text
Sortie
text
Entrée: $0.8Sortie: $1.2par million de tokens
Voir la fiche du modèle →
morph logomorph

Morph: Morph V3 Fast (batch)

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
Entrée: $0.4Sortie: $0.6par million de tokens
Voir la fiche du modèle →
mistralai logomistralai

Mistral: Mistral Small 3.2 24B

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...

Contexte
256K
Entrée
image · text
Sortie
text
Entrée: $0.075Sortie: $0.2par million de tokens
Voir la fiche du modèle →
google logogoogle

Google: Gemini 2.5 Flash

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...

Contexte
1.0M
Entrée
file · image · text · audio · video
Sortie
text
Entrée: $0.3Sortie: $2.5par million de tokens
Voir la fiche du modèle →
google logogoogle

Google: Gemini 2.5 Pro

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Contexte
1.0M
Entrée
text · image · file · audio · video
Sortie
text
Entrée: $1.25Sortie: $10par million de tokens
Voir la fiche du modèle →
openai logoopenai

OpenAI: o3 Pro

The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...

Contexte
200K
Entrée
text · file · image
Sortie
text
Entrée: $20Sortie: $80par million de tokens
Voir la fiche du modèle →
google logogoogle

Google: Gemini 2.5 Pro Preview 06-05

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Contexte
1.0M
Entrée
file · image · text · audio
Sortie
text
Entrée: $1.25Sortie: $10par million de tokens
Voir la fiche du modèle →
deepseek logodeepseek

DeepSeek: R1 0528

May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

Contexte
164K
Entrée
text
Sortie
text
Entrée: $0.571Sortie: $2.286par million de tokens
Voir la fiche du modèle →
mistralai logomistralai

Mistral: Mistral Medium 3

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...

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

Meta: Llama Guard 4 12B

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...

Contexte
164K
Entrée
image · text
Sortie
text
Entrée: $0.18Sortie: $0.18par million de tokens
Voir la fiche du modèle →
qwen logoqwen

Qwen: Qwen3 30B A3B

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

Contexte
41K
Entrée
text
Sortie
text
Entrée: $0.12Sortie: $0.5par million de tokens
Voir la fiche du modèle →
qwen logoqwen

Qwen: Qwen3 14B

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

Contexte
41K
Entrée
text
Sortie
text
Entrée: $0.12Sortie: $0.24par million de tokens
Voir la fiche du modèle →
qwen logoqwen

Qwen: Qwen3 32B

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

Contexte
131K
Entrée
text
Sortie
text
Entrée: $0.08Sortie: $0.28par million de tokens
Voir la fiche du modèle →