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
anthropic/claude-sonnet-5.5/chat

Claude Sonnet 5.5 chat from Anthropic, released 28 September 2026, through an OpenAI-compatible endpoint. It takes up to 1,000,000 tokens and returns up to 128,000, with reasoning effort from none to max and up to 128 tool definitions.

Input $2Output $10per 1 million tokensCached input $0.20Cache write $2.50
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
    $0.20 / 1 million tokens
    Output
    $10 / 1 million tokens
    Context
    1M
    Max output
    128K

    $2/10per 1 million tokens · input / output

    canal-mystery-turn

    An interactive-fiction turn at reasoning_effort none: the narrator's rules and the story so far travel with the request, the reply is kept short, and each turn ends on a choice for the player. Move to low or medium when a turn has to reconcile clues planted much earlier.

    • 900
    • none
  • Input types
    Text
    Output types
    Text
    Input
    $2 / 1 million tokens
    Cached input
    $0.20 / 1 million tokens
    Output
    $10 / 1 million tokens
    Context
    1M
    Max output
    128K

    $2/10per 1 million tokens · input / output

    station-crew-scene

    Three voices in one scene with the whole prior exchange attached. reasoning_effort is left out, so the default medium applies; the system message pins down how each character speaks so the three stay distinct.

    • 2000
  • Input types
    Text
    Output types
    Text
    Input
    $2 / 1 million tokens
    Cached input
    $0.20 / 1 million tokens
    Output
    $10 / 1 million tokens
    Context
    1M
    Max output
    128K

    $2/10per 1 million tokens · input / output

    manuscript-next-chapter

    Voice rules in the system message and the chapters so far in the user turn, then a request for the next chapter. medium effort and a max_tokens well above the chapter length, because thinking comes out of the same budget.

    • 6000
    • medium
  • Input types
    Text
    Output types
    Text
    Input
    $2 / 1 million tokens
    Cached input
    $0.20 / 1 million tokens
    Output
    $10 / 1 million tokens
    Context
    1M
    Max output
    128K

    $2/10per 1 million tokens · input / output

    extract-with-tool

    Machine-readable output without forcing a tool: the tool's parameters carry the schema, tool_choice stays on auto, and the system message tells the model to answer by calling it. Effort at low, because the work is reading, not reasoning.

    • 2048
    • auto
    • low
  • Input types
    Text
    Output types
    Text
    Input
    $2 / 1 million tokens
    Cached input
    $0.20 / 1 million tokens
    Output
    $10 / 1 million tokens
    Context
    1M
    Max output
    128K

    $2/10per 1 million tokens · input / output

    review-against-repo

    A code review with the repository and the change in one request. Effort goes to high because each finding depends on following calls across files, and max_tokens is raised so thinking does not crowd out the report.

    • 16000
    • high

This example starts at Input $2 / Output $10 per 1 million tokens. The Playground updates the estimate when you change the settings.