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
xai/grok-4.3/chat

Grok 4.3 is xAI's chat model behind an OpenAI-compatible call, taking text and image parts in one message array. It reads 1,000,000 tokens, replies up to 900,000, and offers five reasoning-effort levels including none.

Input $1.25Output $2.50per 1 million tokensCached input $0.20Prompts of 200K tokens or moreInput $2.50Output $5
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
    $1.25 / 1 million tokens
    Cached input
    $0.20 / 1 million tokens
    Output
    $2.50 / 1 million tokens
    Context
    1M
    Max output
    900K

    $1.25/2.50per 1 million tokens · input / output

    evaluation-plan

    A text-only request that raises reasoning_effort to high, above this model's default of low, because the plan has to be worked out rather than looked up.

    • 3000
    • 0.3
    • high
  • Input types
    Text
    Output types
    Text
    Input
    $1.25 / 1 million tokens
    Cached input
    $0.20 / 1 million tokens
    Output
    $2.50 / 1 million tokens
    Context
    1M
    Max output
    900K

    $1.25/2.50per 1 million tokens · input / output

    screenshot-triage

    Two image_url parts at detail high beside the question, in one user turn, with effort left at the default low.

    • 2000
    • 0.2

This example starts at Input $1.25 / Output $2.50 per 1 million tokens. The Playground updates the estimate when you change the settings.