Mistral Small 4

Mistral Small 4 unifies the capabilities of Magistral (reasoning), Pixtral (multimodal), and Devstral (agentic coding) into a single efficient model. It handles complex analysis, software development, and visual tasks within the same workflow at $0.15/$0.60 per million tokens.

Mistral Small Creative

Mistral Small Creative is an experimental small model designed for creative writing, narrative generation, roleplay and character-driven dialogue, general-purpose instruction following, and conversational agents.

Mistral: Devstral 2 2512

Mistral: Devstral 2 2512 model integrated via automation on 2025-12-09

Mistral Large 3 2512

Mistral Large 3 2512 model integrated via automation on 2025-12-01

Mistral Devstral Medium

Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves 61.6% on SWE-Bench Verified, placing it ahead of Gemini 2.5 Pro and GPT-4.1 in code-related tasks, at a fraction of the cost.

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 state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases. The model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3.1 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.

Mistral Small 4

Mistral Small 4 unifies the capabilities of Magistral (reasoning), Pixtral (multimodal), and Devstral (agentic coding) into a single efficient model. It handles complex analysis, software development, and visual tasks within the same workflow at $0.15/$0.60 per million tokens.

Mistral Small Creative

Mistral Small Creative is an experimental small model designed for creative writing, narrative generation, roleplay and character-driven dialogue, general-purpose instruction following, and conversational agents.

Mistral: Devstral 2 2512

Mistral: Devstral 2 2512 model integrated via automation on 2025-12-09

Mistral Large 3 2512

Mistral Large 3 2512 model integrated via automation on 2025-12-01

Mistral Devstral Medium

Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves 61.6% on SWE-Bench Verified, placing it ahead of Gemini 2.5 Pro and GPT-4.1 in code-related tasks, at a fraction of the cost.

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 state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases. The model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3.1 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.