Skip to content
  12.  
    13. © 2023 – 2025 OpenRouter, Inc

    Mistral: Magistral Medium 2506 (thinking)Thinking variant

    mistralai/magistral-medium-2506:thinking

    Created Jun 8, 202540,960 context
    $2/M input tokens$5/M output tokens

    Magistral is Mistral's first reasoning model. It is ideal for general purpose use requiring longer thought processing and better accuracy than with non-reasoning LLMs. From legal research and financial forecasting to software development and creative storytelling — this model solves multi-step challenges where transparency and precision are critical.

    Providers for Magistral Medium 2506 (thinking)

    OpenRouter routes requests to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime.

    Performance for Magistral Medium 2506 (thinking)

    Compare different providers across OpenRouter

    Apps using Magistral Medium 2506 (thinking)

    Top public apps this week using this model

    Recent activity on Magistral Medium 2506 (thinking)

    Total usage per day on OpenRouter

    Uptime stats for Magistral Medium 2506 (thinking)

    Uptime stats for Magistral Medium 2506 (thinking) across all providers

    Sample code and API for Magistral Medium 2506 (thinking)

    OpenRouter normalizes requests and responses across providers for you.

    OpenRouter provides an OpenAI-compatible completion API to 400+ models & providers that you can call directly, or using the OpenAI SDK. Additionally, some third-party SDKs are available.

    In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.

    Using third-party SDKs

    For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.

    See the Request docs for all possible fields, and Parameters for explanations of specific sampling parameters.