Skip to main content

Light — We add no content filter, but this model goes past its own limits only some of the time, even with a fiction-writing system prompt. Expect refusals and plan for retries. Legal and consent duties remain with the customer.Browse every model at this filtering level
zai/glm-5.3/chat

GLM 5.3 is Z.ai's full-size long-context chat model behind an OpenAI-compatible call. It reads up to 1,048,576 tokens, replies up to 131,072, with reasoning effort up to max, 128 tool schemas per request and JSON output.

Input $1.05Output $3.30per 1 million tokens25% below the publisher's list priceCached input $0.195Z.ai official priceInput $1.40Output $4.40
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
    $1.05 / 1 million tokens
    Cached input
    $0.195 / 1 million tokens
    Output
    $3.30 / 1 million tokens
    Context
    1,048,576
    Max output
    131,072

    $1.05/3.30per 1 million tokens · input / output

    contradiction-audit

    The case the window exists for: several documents at once, with the answer resting on a pair of passages far apart.

    • 32000
    • 0
    • max
  • Input types
    Text
    Output types
    Text
    Input
    $1.05 / 1 million tokens
    Cached input
    $0.195 / 1 million tokens
    Output
    $3.30 / 1 million tokens
    Context
    1,048,576
    Max output
    131,072

    $1.05/3.30per 1 million tokens · input / output

    incident-chain

    Mixed evidence - timeline, log, diff, transcript - reduced to one causal chain with citations.

    • 16000
    • 0.2
    • high
  • Input types
    Text
    Output types
    Text
    Input
    $1.05 / 1 million tokens
    Cached input
    $0.195 / 1 million tokens
    Output
    $3.30 / 1 million tokens
    Context
    1,048,576
    Max output
    131,072

    $1.05/3.30per 1 million tokens · input / output

    json-brief

    response_format plus temperature 0, which is what makes the reply safe to hand to a parser.

    • 16000
    • 0
    • max

This example starts at Input $1.05 / Output $3.30 per 1 million tokens. The Playground updates the estimate when you change the settings.