Skip to main content

Softened — This model answers instead of refusing, but requests beyond its own limits come back toned down, even with a fiction-writing system prompt. The call still succeeds and is still billed, so read the reply rather than trusting the status code.Browse every model at this filtering level
anthropic/claude-sonnet-4.5/chat

Claude Sonnet 4.5 chat from Anthropic through an OpenAI-compatible endpoint. It takes up to 198,000 tokens of text and image context and returns up to 64,000, with temperature and top_p control, up to 128 tool definitions and SSE streaming.

Input $2.70Output $13.50per 1 million tokens10% below the publisher's list priceCached input $0.27Cache write $3.30Anthropic official priceInput $3Output $15
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
    $2.70 / 1 million tokens
    Cached input
    $0.27 / 1 million tokens
    Output
    $13.50 / 1 million tokens
    Context
    198K
    Max output
    64K

    $2.70/13.50per 1 million tokens · input / output

    bulk-classification

    The cheap end of the range: a fixed system message, and only the material changes. JSON is asked for in the prompt because there is no response_format, so validate what comes back.

    • 2000
  • Input types
    Text
    Output types
    Text
    Input
    $2.70 / 1 million tokens
    Cached input
    $0.27 / 1 million tokens
    Output
    $13.50 / 1 million tokens
    Context
    198K
    Max output
    64K

    $2.70/13.50per 1 million tokens · input / output

    tool-loop

    One agent turn with tools. Tool results stay in the thread and count against the window, so a long chain needs a trimming rule of your own.

    • 4000
  • Input types
    Text
    Output types
    Text
    Input
    $2.70 / 1 million tokens
    Cached input
    $0.27 / 1 million tokens
    Output
    $13.50 / 1 million tokens
    Context
    198K
    Max output
    64K

    $2.70/13.50per 1 million tokens · input / output

    mid-length-analysis

    One analysis with the material supplied in full, the shape a 198,000-token window handles without a retrieval layer in front of it.

    • 6000

This example starts at Input $2.70 / Output $13.50 per 1 million tokens. The Playground updates the estimate when you change the settings.