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-4.1 Mini
GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...
- Contexte
- 1.0M
- Entrée
- image · text · file
- Sortie
- text
openaiOpenAI: GPT-4.1 Mini (batch)
GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...
- Contexte
- 1.0M
- Entrée
- image · text · file
- Sortie
- text
openaiOpenAI: GPT-4.1 Nano
For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...
- Contexte
- 1.0M
- Entrée
- image · text · file
- Sortie
- text
openaiOpenAI: GPT-4.1 Nano (batch)
For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...
- Contexte
- 1.0M
- Entrée
- image · text · file
- Sortie
- text
meta-llamaMeta: Llama 4 Maverick
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
- Contexte
- 1.0M
- Entrée
- text · image
- Sortie
- text
meta-llamaMeta: Llama 4 Scout
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
- Contexte
- 1.3M
- Entrée
- text · image
- Sortie
- text
deepseekDeepSeek: DeepSeek V3 0324
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well...
- Contexte
- 164K
- Entrée
- text
- Sortie
- text
openaiOpenAI: o1-pro
The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...
- Contexte
- 200K
- Entrée
- text · image · file
- Sortie
- text
mistralaiMistral: Mistral Small 3.1 24B
Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...
- Contexte
- 128K
- Entrée
- text · image
- Sortie
- text
googleGoogle: Gemma 3 4B
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
- Contexte
- 131K
- Entrée
- text · image
- Sortie
- text
googleGoogle: Gemma 3 12B
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
- Contexte
- 131K
- Entrée
- text · image
- Sortie
- text
cohereCohere: Command A
Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...
- Contexte
- 256K
- Entrée
- text
- Sortie
- text
rekaaiReka Flash 3
Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...
- Contexte
- 66K
- Entrée
- text
- Sortie
- text
googleGoogle: Gemma 3 27B
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
- Contexte
- 131K
- Entrée
- text · image
- Sortie
- text
thedrummerTheDrummer: Skyfall 36B V2
Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.
- Contexte
- 33K
- Entrée
- text
- Sortie
- text
perplexityPerplexity: Sonar Reasoning Pro
Note: Sonar Pro pricing includes Perplexity search pricing. See details here Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...
- Contexte
- 128K
- Entrée
- text · image
- Sortie
- text
perplexityPerplexity: Sonar Pro
Note: Sonar Pro pricing includes Perplexity search pricing. See details here For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...
- Contexte
- 200K
- Entrée
- text · image
- Sortie
- text
perplexityPerplexity: Sonar Deep Research
Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...
- Contexte
- 128K
- Entrée
- text
- Sortie
- text
mistralaiMistral: Saba
Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...
- Contexte
- 33K
- Entrée
- text · file
- Sortie
- text
openaiOpenAI: o3 Mini High
OpenAI o3-mini-high is the same model as o3-mini with reasoningeffort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...
- Contexte
- 200K
- Entrée
- text · file
- Sortie
- text
aion-labsAionLabs: Aion-RP 1.0 (8B)
Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...
- Contexte
- 33K
- Entrée
- text
- Sortie
- text
qwenQwen: Qwen2.5 VL 72B Instruct
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
- Contexte
- 128K
- Entrée
- text · image
- Sortie
- text
qwenQwen: Qwen-Plus
Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.
- Contexte
- 1M
- Entrée
- text
- Sortie
- text
openaiOpenAI: o3 Mini
OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the reasoningeffort parameter, which can be set to...
- Contexte
- 200K
- Entrée
- text · file
- Sortie
- text