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-4.5/chat

Grok 4.5 is xAI's coding model for agentic software and engineering work, behind an OpenAI-compatible chat call. It takes up to 500,000 tokens in, replies up to 450,000, and reasoning effort goes up to xhigh.

Input $2Output $6per 1 million tokensCached input $0.30Prompts of 200K tokens or moreInput $4Output $12
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 / 1 million tokens
    Cached input
    $0.30 / 1 million tokens
    Output
    $6 / 1 million tokens
    Context
    500K
    Max output
    450K

    $2/6per 1 million tokens · input / output

    evaluation-plan

    A plain text request at high effort - the shape an engineering loop sends most: a system prompt that fixes the output format, one task, no images.

    • 3000
    • 0.3
    • high
  • Input types
    Text
    Output types
    Text
    Input
    $2 / 1 million tokens
    Cached input
    $0.30 / 1 million tokens
    Output
    $6 / 1 million tokens
    Context
    500K
    Max output
    450K

    $2/6per 1 million tokens · input / output

    screenshot-triage

    Two image_url parts at detail high beside the question, in one user turn.

    • 2000
    • 0.2

This example starts at Input $2 / Output $6 per 1 million tokens. The Playground updates the estimate when you change the settings.