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
- 534
- fournisseurs
- 75
- dernière synchronisation
- 31 août 2026
minimaxMiniMax: MiniMax M2.7 (free)
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...
- Contexte
- 197K
- Entrée
- text
- Sortie
- text
openaiOpenAI: GPT-5.4 Nano
GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...
- Contexte
- 400K
- Entrée
- file · image · text
- Sortie
- text
openaiOpenAI: GPT-5.4 Mini
GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...
- Contexte
- 400K
- Entrée
- file · image · text
- Sortie
- text
mistralaiMistral: Mistral Small 4
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
- Contexte
- 262K
- Entrée
- text · image
- Sortie
- text
mistralaiMistral: Mistral Small 4 (batch)
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
- Contexte
- 262K
- Entrée
- text · image
- Sortie
- text
perplexityPerplexity: Embed V1 4B
pplx-embed-v1 -4B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 4B parameter model maximizing retrieval...
- Contexte
- 32K
- Entrée
- text
- Sortie
- embeddings
perplexityPerplexity: Embed V1 0.6B
pplx-embed-v1-0.6B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 0.6B parameter model targeting lightweight, low-latency...
- Contexte
- 32K
- Entrée
- text
- Sortie
- embeddings
nvidiaNVIDIA: Nemotron 3 Super
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
- Contexte
- 1M
- Entrée
- text
- Sortie
- text
nvidiaNVIDIA: Nemotron 3 Super (free)
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
- Contexte
- 262K
- Entrée
- text
- Sortie
- text
bytedance-seedByteDance Seed: Seed-2.0-Lite
Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...
- Contexte
- 262K
- Entrée
- text · image · video
- Sortie
- text
qwenQwen: Qwen3.5-9B
Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...
- Contexte
- 262K
- Entrée
- text · image · video
- Sortie
- text
qwenQwen: Qwen3.5-9B (batch)
Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...
- Contexte
- 262K
- Entrée
- text · image · video
- Sortie
- text
openaiOpenAI: GPT-5.4 Pro
GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...
- Contexte
- 1.1M
- Entrée
- text · image · file
- Sortie
- text
openaiOpenAI: GPT-5.4
GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...
- Contexte
- 1.1M
- Entrée
- text · image · file
- Sortie
- text
inceptionInception: Mercury 2
Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
- Contexte
- 128K
- Entrée
- text
- Sortie
- text
googleGoogle: Gemini 3.1 Flash Lite Preview
Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...
- Contexte
- 1.0M
- Entrée
- text · image · video · file · audio
- Sortie
- text
bytedance-seedByteDance Seed: Seed-2.0-Mini
Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...
- Contexte
- 262K
- Entrée
- text · image · video
- Sortie
- text
googleGoogle: Nano Banana 2 (Gemini 3.1 Flash Image Preview)
Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...
- Contexte
- 66K
- Entrée
- image · text
- Sortie
- image · text
qwenQwen: Qwen3.5-35B-A3B
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
- Contexte
- 262K
- Entrée
- text · image · video
- Sortie
- text
qwenQwen: Qwen3.5-27B
The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...
- Contexte
- 262K
- Entrée
- text · image · video
- Sortie
- text
qwenQwen: Qwen3.5-122B-A10B
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...
- Contexte
- 262K
- Entrée
- text · image · video
- Sortie
- text
qwenQwen: Qwen3.5-Flash
The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...
- Contexte
- 1M
- Entrée
- text · image · video
- Sortie
- text
googleGoogle: Gemini 3.1 Pro Preview Custom Tools
Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...
- Contexte
- 1.0M
- Entrée
- text · audio · image · video · file
- Sortie
- text
nvidiaNVIDIA: Llama Nemotron Embed VL 1B V2 (free)
The Llama Nemotron Embed VL 1B V2 embedding model is optimized for multimodal question-answering retrieval. The model can embed 'documents' in the form of image, text, or image and text...
- Contexte
- 131K
- Entrée
- text · image
- Sortie
- embeddings