DocsSecuritySign in
    Get started
    Minimax logoMinimax

    MiniMax-M3.1-Flash

    Auto-router

    minimax/MiniMax-M3.1-Flash

    ChatVisionFilesToolsSystem prompt
    Use this model

    Context

    1M

    Max output

    524K

    Input / 1M

    $0.15

    Output / 1M

    $0.60

    Cached / 1M

    $0.015

    Cutoff

    unknown

    About this model

    MiniMax-M3.1-Flash is MiniMax's speed- and cost-optimised text model with a 1M token context window, listed in the MiniMax text generation supported-models table.

    Best suited for

    • High-volume, latency-sensitive tasks
    • Long-context conversations (up to 1M tokens)
    • Cost-efficient general-purpose AI applications

    Built-in tools

    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.

    Files

    Accepts file attachments — PDFs, transcripts, spreadsheets.

    Tools

    Native function calling, so agents can invoke your endpoints.

    System prompt

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

    Supported parameters

    max_tokensMax Tokens Limit

    Specifies the maximum number of text units (tokens) allowed in a response, limiting its length.

    tools

    Lists tool definitions or capabilities available to the model.

    tool_choice

    Decides whether to use tools or just the model for generating responses.

    response_type

    Defines the format or type of the generated response.

    creativity_level

    Controls randomness (temperature). Higher values (0.8) make output more random, lower values (0.2) more focused and deterministic.

    log_probabilityLog Probabilities

    Whether to return log probabilities of the output tokens.

    probability_cutoff

    Nucleus sampling parameter. The model considers tokens with top_p probability mass.

    Use this model

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

    Other Minimax models

    ModelContextMax outputInputOutputCapabilities
    MiniMax-M3

    Chat

    		1M524K$0.30$1.20Vision, Files, Tools, System prompt
    MiniMax-M2.7

    Chat

    		205K128K$0.30$1.20Vision, Files, Tools, System prompt
    MiniMax-M2.7-highspeed

    Chat

    		205K128K$0.60$2.40Vision, Files, Tools, System prompt
    minimax-m3

    Chat

    		1M524K$0.30$1.20Vision, Files, Tools, System prompt, Reasoning
    MiniMax-M2

    Chat

    		205K128K$0.30$1.20Files, Tools, System prompt
    minimax-m2.1-highspeed

    Chat

    		205K128K$0.60$2.40Files, Tools, System prompt
    minimax-m2.1

    Chat

    		205K128K$0.30$1.20Files, Tools, System prompt
    minimax-m2.5-highspeed

    Chat

    		205K128K$0.60$2.40Files, Tools, System prompt
    minimax-m2.5

    Chat

    		205K128K$0.30$1.20Files, Tools, System prompt

    Pricing & provider details

    Minimax logo

    Minimax

    minimax/MiniMax-M3.1-Flash

    Input · per 1M
    $0.15
    Output · per 1M
    $0.60
    Cached input · per 1M
    $0.015
    Context window
    1,000,000 tokens
    Max output
    524,288 tokens
    Knowledge cutoff
    unknown
    Auto-router
    Supported

    Start building today

    Route MiniMax-M3.1-Flash — and every other model in the catalogue — through one endpoint, with failover built in.

    Get started freeAll models