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-opus-5.5/chat

Claude Opus 5.5 chat from Anthropic, released 22 September 2026, through an OpenAI-compatible endpoint. It takes up to 1,000,000 tokens and returns up to 128,000, always thinks, offers low, medium or high effort and up to 128 tool definitions.

Input $3.60Output $18per 1 million tokens10% below the publisher's list priceCached input $0.18Cache write $4.50Anthropic official priceInput $4Output $20
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
    $3.60 / 1 million tokens
    Cached input
    $0.18 / 1 million tokens
    Output
    $18 / 1 million tokens
    Context
    1M
    Max output
    128K

    $3.60/18per 1 million tokens · input / output

    persona-continuity

    Continuing a long exchange. History, persona and established limits all travel with the request, with no summarisation layer in between - that is what decides whether the character still remembers, thirty turns in, what it said.

    • 6000
  • Input types
    Text
    Output types
    Text
    Input
    $3.60 / 1 million tokens
    Cached input
    $0.18 / 1 million tokens
    Output
    $18 / 1 million tokens
    Context
    1M
    Max output
    128K

    $3.60/18per 1 million tokens · input / output

    long-running-refactor

    A change that spans several files with dependencies between the steps. What is tight here is not output length but whether it remembers the decision it made first, so the whole context stays in the request and effort goes up to high.

    • 16000
    • high
  • Input types
    Text
    Output types
    Text
    Input
    $3.60 / 1 million tokens
    Cached input
    $0.18 / 1 million tokens
    Output
    $18 / 1 million tokens
    Context
    1M
    Max output
    128K

    $3.60/18per 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.

    • 4096
    • auto
    • low

This example starts at Input $3.60 / Output $18 per 1 million tokens. The Playground updates the estimate when you change the settings.