Liste complète et mise à jour en temps réel de tous les modèles disponibles sur OpenRouter
| Modèle | Créateur | Prix Input | Prix Output | Date de mise en ligne |
|---|---|---|---|---|
|
OpenAI: gpt-oss-120b (free)
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI d...
|
openai | Gratuit | Gratuit | 05/08/2025 |
|
OpenAI: gpt-oss-120b
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI d...
|
openai | $0.04 / 1M | $0.18 / 1M | 05/08/2025 |
|
OpenAI: gpt-oss-20b (free)
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. I...
|
openai | Gratuit | Gratuit | 05/08/2025 |
|
OpenAI: gpt-oss-20b
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. I...
|
openai | $0.03 / 1M | $0.14 / 1M | 05/08/2025 |
|
Anthropic: Claude Opus 4.1
Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance...
|
anthropic | $15.00 / 1M | $75.00 / 1M | 05/08/2025 |
|
Mistral: Codestral 2508
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in...
|
mistralai | $0.30 / 1M | $0.90 / 1M | 01/08/2025 |
|
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...
|
qwen | $0.07 / 1M | $0.27 / 1M | 31/07/2025 |
|
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...
|
qwen | $0.09 / 1M | $0.30 / 1M | 29/07/2025 |
|
Z.ai: GLM 4.5
GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leve...
|
z-ai | $0.60 / 1M | $2.20 / 1M | 25/07/2025 |
|
Z.ai: GLM 4.5 Air (free)
GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for a...
|
z-ai | Gratuit | Gratuit | 25/07/2025 |
|
Z.ai: GLM 4.5 Air
GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for a...
|
z-ai | $0.13 / 1M | $0.85 / 1M | 25/07/2025 |
|
Qwen: Qwen3 235B A22B Thinking 2507
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language m...
|
qwen | $0.15 / 1M | $1.50 / 1M | 25/07/2025 |
|
Z.ai: GLM 4 32B
GLM 4 32B is a cost-effective foundation language model. It can efficiently perform complex tasks an...
|
z-ai | $0.10 / 1M | $0.10 / 1M | 24/07/2025 |
|
Qwen: Qwen3 Coder 480B A35B (free)
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the ...
|
qwen | Gratuit | Gratuit | 23/07/2025 |
|
Qwen: Qwen3 Coder 480B A35B
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the ...
|
qwen | $0.22 / 1M | $1.80 / 1M | 23/07/2025 |
|
ByteDance: UI-TARS 7B
UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including de...
|
bytedance | $0.10 / 1M | $0.20 / 1M | 22/07/2025 |
|
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...
|
$0.10 / 1M | $0.40 / 1M | 22/07/2025 | |
|
Qwen: Qwen3 235B A22B Instruct 2507
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model...
|
qwen | $0.07 / 1M | $0.10 / 1M | 21/07/2025 |
|
Switchpoint Router
Switchpoint AI's router instantly analyzes your request and directs it to the optimal AI from an eve...
|
switchpoint | $0.85 / 1M | $3.40 / 1M | 11/07/2025 |
|
MoonshotAI: Kimi K2 0711
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, ...
|
moonshotai | $0.57 / 1M | $2.30 / 1M | 11/07/2025 |
|
Mistral: Devstral Medium
Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly ...
|
mistralai | $0.40 / 1M | $2.00 / 1M | 10/07/2025 |
|
Mistral: Devstral Small 1.1
Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, de...
|
mistralai | $0.10 / 1M | $0.30 / 1M | 10/07/2025 |
|
Venice: Uncensored (free)
Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-In...
|
cognitivecomputations | Gratuit | Gratuit | 09/07/2025 |
|
Tencent: Hunyuan A13B Instruct
Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent,...
|
tencent | $0.14 / 1M | $0.57 / 1M | 08/07/2025 |
|
Morph: Morph V3 Large
Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for pr...
|
morph | $0.90 / 1M | $1.90 / 1M | 07/07/2025 |
|
Morph: Morph V3 Fast
Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code tran...
|
morph | $0.80 / 1M | $1.20 / 1M | 07/07/2025 |
|
Baidu: 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 serie...
|
baidu | $0.42 / 1M | $1.25 / 1M | 30/06/2025 |
|
Baidu: ERNIE 4.5 300B A47B
ERNIE-4.5-300B-A47B is a 300B parameter Mixture-of-Experts (MoE) language model developed by Baidu a...
|
baidu | $0.28 / 1M | $1.10 / 1M | 30/06/2025 |
|
Mistral: Mistral Small 3.2 24B
Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for ins...
|
mistralai | $0.08 / 1M | $0.20 / 1M | 20/06/2025 |
|
MiniMax: MiniMax M1
MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-effi...
|
minimax | $0.40 / 1M | $2.20 / 1M | 17/06/2025 |
|
Google: Gemini 2.5 Flash
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced re...
|
$0.30 / 1M | $2.50 / 1M | 17/06/2025 | |
|
Google: Gemini 2.5 Pro
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, math...
|
$1.25 / 1M | $10.00 / 1M | 17/06/2025 | |
|
OpenAI: o3 Pro
The o-series of models are trained with reinforcement learning to think before they answer and perfo...
|
openai | $20.00 / 1M | $80.00 / 1M | 10/06/2025 |
|
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, math...
|
$1.25 / 1M | $10.00 / 1M | 05/06/2025 | |
|
DeepSeek: R1 0528
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI...
|
deepseek | $0.50 / 1M | $2.15 / 1M | 28/05/2025 |
|
Anthropic: Claude Opus 4
Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustai...
|
anthropic | $15.00 / 1M | $75.00 / 1M | 22/05/2025 |
|
Anthropic: Claude Sonnet 4
Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in...
|
anthropic | $3.00 / 1M | $15.00 / 1M | 22/05/2025 |
|
Google: Gemma 3n 4B
Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as pho...
|
$0.06 / 1M | $0.12 / 1M | 20/05/2025 | |
|
Mistral: Mistral Medium 3
Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-...
|
mistralai | $0.40 / 1M | $2.00 / 1M | 07/05/2025 |
|
Google: Gemini 2.5 Pro Preview 05-06
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, math...
|
$1.25 / 1M | $10.00 / 1M | 07/05/2025 | |
|
Arcee AI: Spotlight
Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine�...
|
arcee-ai | $0.18 / 1M | $0.18 / 1M | 05/05/2025 |
|
Arcee AI: Maestro Reasoning
Maestro Reasoning is Arcee's flagship analysis model: a 32 B‑parameter derivative of Qwen 2.5‑32...
|
arcee-ai | $0.90 / 1M | $3.30 / 1M | 05/05/2025 |
|
Arcee AI: Virtuoso Large
Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cro...
|
arcee-ai | $0.75 / 1M | $1.20 / 1M | 05/05/2025 |
|
Arcee AI: Coder Large
Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained o...
|
arcee-ai | $0.50 / 1M | $0.80 / 1M | 05/05/2025 |
|
Meta: Llama Guard 4 12B
Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety ...
|
meta-llama | $0.18 / 1M | $0.18 / 1M | 30/04/2025 |
|
Qwen: Qwen3 30B A3B
Qwen3, the latest generation in the Qwen large language model series, features both dense and mixtur...
|
qwen | $0.09 / 1M | $0.45 / 1M | 28/04/2025 |
|
Qwen: Qwen3 8B
Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both re...
|
qwen | $0.05 / 1M | $0.40 / 1M | 28/04/2025 |
|
Qwen: Qwen3 14B
Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both ...
|
qwen | $0.10 / 1M | $0.24 / 1M | 28/04/2025 |
|
Qwen: Qwen3 32B
Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both...
|
qwen | $0.08 / 1M | $0.28 / 1M | 28/04/2025 |
|
Qwen: Qwen3 235B A22B
Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B...
|
qwen | $0.46 / 1M | $1.82 / 1M | 28/04/2025 |