Skip to main content

Uncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.Browse every model at this filtering level
moonshot/kimi-k3/chat

Kimi K3 is Moonshot AI's long-context agent model behind an OpenAI-compatible chat call. It reads 1,000,000 tokens, replies up to 1,048,576, with reasoning effort low, high or max, up to 128 tools and image input.

Input $2.70Output $13.50per 1 million tokensCached input $0.30
Run model

Workbench

These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.

  • Input types
    Text
    Output types
    Text
    Input
    $2.70 / 1 million tokens
    Cached input
    $0.30 / 1 million tokens
    Output
    $13.50 / 1 million tokens
    Context
    1M
    Max output
    1,048,576

    $2.70/13.50per 1 million tokens · input / output

    review-brief

    The small end of the range: a short structured answer. reasoning_effort is left out, so it runs at max; set it to low when briefs like this are all you need.

    • 1500
  • Input types
    Text
    Output types
    Text
    Input
    $2.70 / 1 million tokens
    Cached input
    $0.30 / 1 million tokens
    Output
    $13.50 / 1 million tokens
    Context
    1M
    Max output
    1,048,576

    $2.70/13.50per 1 million tokens · input / output

    whole-repo-rewrite

    A 120,000-token cap, just under the ceiling: what one migrated file returned in full actually costs.

    • 120000
  • Input types
    Text
    Output types
    Text
    Input
    $2.70 / 1 million tokens
    Cached input
    $0.30 / 1 million tokens
    Output
    $13.50 / 1 million tokens
    Context
    1M
    Max output
    1,048,576

    $2.70/13.50per 1 million tokens · input / output

    structured-extract

    response_format with the keys named in the system message. Validate the object in your application; sampling is fixed on this model, so there is no temperature to pin.

    • 8000

This example starts at Input $2.70 / Output $13.50 per 1 million tokens. The Playground updates the estimate when you change the settings.