Files
openrouter-python-sdk-retry…/docs/components/messagesoutputconfig.mdx
T

14 lines
4.9 KiB
Plaintext

---
title: "MessagesOutputConfig"
---
Configuration for controlling output behavior. Supports the effort parameter and structured output format.
## Fields
| Field | Type | Required | Description | Example |
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `effort` | [OptionalNullable[components.MessagesOutputConfigEffort]](../components/messagesoutputconfigeffort.mdx) | :heavy_minus_sign: | How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer. Valid values are `low`, `medium`, `high`, `xhigh`, or `max`. | medium |
| `format_` | [OptionalNullable[components.MessagesOutputConfigFormat]](../components/messagesoutputconfigformat.mdx) | :heavy_minus_sign: | A schema to specify Claude's output format in responses. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs). | |
| `task_budget` | [OptionalNullable[components.TaskBudget]](../components/taskbudget.mdx) | :heavy_minus_sign: | Task budget for an agentic turn. The model sees a countdown of remaining tokens and uses it to prioritize work and wind down gracefully. Advisory — does not enforce a hard cap. | \{<br/>"total": 400000,<br/>"type": "tokens"<br/>} |