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-haiku-5.5/chat

Claude Haiku 5.5 chat from Anthropic, released 7 October 2026, through an OpenAI-compatible endpoint. It takes up to 1,000,000 tokens of text and images, returns up to 128,000, and accepts up to 128 tool definitions with forced or automatic tool calls.

Input $0.10Output $0.50per 1 million tokensCached input $0.10Cache write $0.10Prompts over 100K tokensInput $0.50Output $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
    $0.10 / 1 million tokens
    Cached input
    $0.10 / 1 million tokens
    Output
    $0.50 / 1 million tokens
    Context
    1M
    Max output
    128K

    $0.10/0.50per 1 million tokens · input / output

    companion-turn

    A short companion-chat turn: the persona and house rules travel in the system message, the reply length is set in words because max_tokens does not cut the reply here, and the history follows oldest first.

    • 1024
  • Input types
    Text
    Output types
    Text
    Input
    $0.10 / 1 million tokens
    Cached input
    $0.10 / 1 million tokens
    Output
    $0.50 / 1 million tokens
    Context
    1M
    Max output
    128K

    $0.10/0.50per 1 million tokens · input / output

    ticket-router

    Routing with a forced tool call: tool_choice names route_ticket, so the answer always arrives as a queue and a priority you can act on, never as free text.

    • 512
  • Input types
    Text
    Output types
    Text
    Input
    $0.10 / 1 million tokens
    Cached input
    $0.10 / 1 million tokens
    Output
    $0.50 / 1 million tokens
    Context
    1M
    Max output
    128K

    $0.10/0.50per 1 million tokens · input / output

    invoice-fields

    Extraction into a fixed shape: the tool's parameters are the fields you want, the system message says to leave out anything not present, and tool_choice forces the call.

    • 1024
    • required
  • Input types
    Text
    Output types
    Text
    Input
    $0.10 / 1 million tokens
    Cached input
    $0.10 / 1 million tokens
    Output
    $0.50 / 1 million tokens
    Context
    1M
    Max output
    128K

    $0.10/0.50per 1 million tokens · input / output

    thread-notes

    Compressing a long conversation into notes for a later turn or a larger model: the whole thread travels as written and the system message fixes the format of the notes.

    • 2048

This example starts at Input $0.10 / Output $0.50 per 1 million tokens. The Playground updates the estimate when you change the settings.