Every model.One place.

Mistral Code Latest is Mistral's direct API alias for codestral-2508, a low-latency coding model for code generation, completion, fill-in-the-middle workflows, function calling, and structured output.

Model ID

mistral-code-latest

Discovery tier

Balanced

Context window

256,000 tokens

Mistral Medium 3 delivers frontier performance while being an order of magnitude less expensive. For instance, the model performs at or above 90% of Claude Sonnet 3.7 on benchmarks across the board at a significantly lower cost. On performance, Mistral Medium 3 also surpasses leading open models such as Llama 4 Maverick and enterprise models such as Cohere Command A. On pricing, the model beats cost leaders such as DeepSeek v3, both in API and self-deployed systems.

Model ID

mistralai/mistral-medium-3

Discovery tier

Balanced

Context window

131,072 tokens

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 in

Model ID

mistralai/mistral-medium-3.1

Discovery tier

Balanced

Context window

131,072 tokens

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.

Model ID

mistralai/codestral-2508

Discovery tier

Balanced

Context window

256,000 tokens

Upgrade to Mistral's flagship model. It is fluent in English, French, Spanish, German, and Italian, with high grammatical accuracy, with a long context window.

Model ID

mistralai/mistral-large

Discovery tier

Balanced

Context window

128,000 tokens

Mistral Large 4 is an open-weight multimodal mixture-of-experts model with 1.05T total and 49B active parameters, built for reasoning, coding, tool use, and structured output. It supports a 512K-token context window.

Model ID

mistralai/mistral-large-4

Discovery tier

Open weights

Context window

524,288 tokens

Mistral Small 3 24B (2501) hosted by IONOS in Berlin, Germany. Zero data retention.

Model ID

mistralai/mistral-small-24b-instruct-2501

Discovery tier

Open weights

Context window

32,768 tokens

Mistral Code Agent Latest is Mistral's direct API alias for devstral-2512, an agentic coding model built for autonomous software engineering, tool use, and long-running code tasks.

Model ID

mistral-code-agent-latest

Discovery tier

Open weights

Context window

262,144 tokens

Mistral Medium 3.5 with reasoning enabled by default (reasoning_effort=high), for complex coding, agentic, and multi-step reasoning prompts.

Model ID

mistralai/mistral-medium-3.5:thinking

Discovery tier

Open weights

Context window

256,000 tokens

Mistral Medium 3.5 is a 128B dense open-weights flagship model for instruction-following, reasoning, coding, long-horizon agentic work, tool use, structured output, and multimodal prompts. It supports a 256k context window and configurable reasoning effort.

Model ID

mistralai/mistral-medium-3.5

Discovery tier

Open weights

Context window

256,000 tokens

Mistral Small 4 with reasoning enabled (reasoning_effort=high). A hybrid MoE model with deep step-by-step reasoning for complex prompts, coding, and multi-step problem solving.

Model ID

mistralai/mistral-small-4-119b-2603:thinking

Discovery tier

Open weights

Context window

262,144 tokens

Mistral Small 4 is a hybrid MoE model that unifies instruct, reasoning, and coding behavior in a single multimodal model. It supports text and image input, native function calling, JSON output, and per-request reasoning effort controls.

Model ID

mistralai/mistral-small-4-119b-2603

Discovery tier

Open weights

Context window

262,144 tokens

Cydonia 24B v4.3 continues TheDrummer's Cydonia series with updated tuning on Mistral Small and a 128K context window.

Model ID

TheDrummer/Cydonia-24B-v4.3

Discovery tier

Open weights

Context window

131,072 tokens

Magidonia 24B v4.3 is a new 24B Drummer finetune built for rich, creative roleplay.

Model ID

TheDrummer/Magidonia-24B-v4.3

Discovery tier

Open weights

Context window

32,768 tokens

Mixtral 8x22B is a powerful sparse Mixture of Experts (MoE) model with 141B total parameters and 39B active per token. Features a 64K context window, exceptional math performance, and cost-efficient inference. Supports English, French, German, Spanish, and Italian. Apache 2.0 licensed.

Model ID

mistralai/mixtral-8x22b-instruct-v0.1

Discovery tier

Open weights

Context window

65,536 tokens

Devstral 2 123B is a 123 billion parameter model from Mistral AI optimized for coding and development tasks. Features advanced reasoning capabilities for software engineering workflows.

Model ID

mistralai/devstral-2-123b-instruct-2512

Discovery tier

Open weights

Context window

262,144 tokens

ReadyArt's MS3.2 Omega Directive 24B unslopped mix tuned for rich roleplay and storytelling.

Model ID

ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0

Discovery tier

Open weights

Context window

32,768 tokens

Ministral 14B is a powerful 14B parameter model from Mistral AI with vision capabilities, offering frontier performance in a compact size.

Model ID

mistralai/ministral-14b-2512

Discovery tier

Open weights

Context window

262,144 tokens

Ministral 3B is a tiny, efficient 3B parameter model from Mistral AI with vision capabilities, designed for edge deployment.

Model ID

mistralai/ministral-3b-2512

Discovery tier

Open weights

Context window

131,072 tokens

Ministral 8B is an efficient 8B parameter model from Mistral AI with vision capabilities, designed for edge deployment.

Model ID

mistralai/ministral-8b-2512

Discovery tier

Open weights

Context window

262,144 tokens