Mistral logoMistral

    deepseek-v4-1-flash-1017

    Auto-router

    mistral/deepseek-v4-1-flash-1017

    ChatVisionToolsSystem prompt
    Use this model

    Context

    1M

    Max output

    —

    Input / 1M

    $0.30

    Output / 1M

    $1.20

    Cached / 1M

    $0.007

    Cutoff

    unknown

    About this model

    DeepSeek V4.1 Flash 1017 is a third-party open-weight model from DeepSeek, hosted by Mistral, with text and image input. Ideal for long-context coding and agentic workflows. Served without Mistral modifications.

    Best suited for

    • Long-context coding
    • Agentic workflows
    • Function calling / tool use
    • Structured outputs

    Built-in tools

    Gtwy web search

    Hosted by the gateway — enable them per request without wiring your own endpoint.

    Capabilities

    Vision

    Accepts images alongside text in the same message.

    Tools

    Native function calling, so agents can invoke your endpoints.

    System prompt

    Honours a dedicated system role, separate from the user turn.

    Supported parameters

    additional_parameters

    Use this model

    OpenAI-SDK compatible, with gateway fallback and routing across providers.

    Other Mistral models

    ModelContextMax outputInputOutputCapabilities
    zai-glm-5-3-flash

    Chat

    1M—$0.15$0.50Tools, System prompt
    mistral-large-4-0

    Chat

    1M—$0.70$2.10Vision, Files, Tools, System prompt
    zai-glm-5-3

    Chat

    1M128K$1.40$4.40Tools, System prompt
    ministral-8b-2512

    Chat

    256K33K$0.15$0.15Vision, Files, Tools, System prompt
    mistral-large-2512

    Chat

    256K131K$0.50$1.50Vision, Files, Tools, System prompt
    mistral-small-latest

    Chat

    128K128K$0.15$0.60Vision, Tools, System prompt
    codestral-latest

    Chat

    256K40K$0.30$0.90Vision, Tools, System prompt
    mistral-medium-latest

    Chat

    128K128K$1.50$7.50Vision, Tools, System prompt

    Pricing & provider details

    Mistral logo

    Mistral

    mistral/deepseek-v4-1-flash-1017

    Input · per 1M
    $0.30
    Output · per 1M
    $1.20
    Cached input · per 1M
    $0.007
    Context window
    1,000,000 tokens
    Max output
    —
    Knowledge cutoff
    unknown
    Auto-router
    Supported

    Start building today

    Route deepseek-v4-1-flash-1017 — and every other model in the catalogue — through one endpoint, with failover built in.