Moonshot logoMoonshot

    kimi-k2.7-code

    moonshot/kimi-k2.7-code

    ChatVisionFilesToolsSystem prompt
    Use this model

    Context

    262K

    Max output

    262K

    Input / 1M

    $0.95

    Output / 1M

    $4.00

    Cached / 1M

    $0.19

    Cutoff

    —

    About this model

    Kimi K2.7 Code is Moonshot AI's dedicated coding model. It follows instructions more reliably in long contexts and completes coding tasks with higher success rates than prior Kimi models, using a native multimodal mixture-of-experts architecture (32B active / ~1T total parameters) with always-on extended reasoning.

    Best suited for

    • Long-context, end-to-end coding and agentic software engineering tasks
    • Multi-turn coding dialogue with preserved reasoning across turns
    • Long-horizon code generation, debugging, and refactoring
    • Tool-calling coding agents with structured/JSON outputs

    Built-in tools

    Web searchGtwy 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_tokens

    The maximum number of tokens to generate for the chat completion. Maps to max_completion_tokens.

    parallel_tool_calls

    Enables parallel execution of tools, allowing multiple tools to run simultaneously.

    response_type

    Defines the format or type of the generated response.

    service_tier
    stream

    Sends the response in real-time as it's being generated.

    tool_choice

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

    tools

    Lists tool definitions or capabilities available to the model.

    Use this model

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

    Other Moonshot models

    ModelContextMax outputInputOutputCapabilities
    kimi-k3.1-pro-highspeed

    Chat

    1.0M—$4.00$20.00Vision, Tools, System prompt
    kimi-k3.1-pro

    Chat

    1.0M—$2.00$10.00Vision, Tools, System prompt
    kimi-k2.7-code-highspeed

    Chat

    262K262K$1.90$8.00Vision, Files, Tools, System prompt
    kimi-k3

    Chat

    1.0M1.0M$3.00$15.00Vision, Tools, System prompt
    kimi-k2.6

    Chat

    262K262K$0.95$4.00Vision, Files, Tools, System prompt

    Pricing & provider details

    Moonshot logo

    Moonshot

    moonshot/kimi-k2.7-code

    Input · per 1M
    $0.95
    Output · per 1M
    $4.00
    Cached input · per 1M
    $0.19
    Context window
    262,144 tokens
    Max output
    262,144 tokens
    Knowledge cutoff
    —
    Auto-router
    Not supported

    Start building today

    Route kimi-k2.7-code — and every other model in the catalogue — through one endpoint, with failover built in.