> ## Documentation Index > Fetch the complete documentation index at: https://openrouter-d02e98a0-mintlify-5b6e02fd.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # MessagesOutputConfig - Python SDK > MessagesOutputConfig method reference The Python SDK and docs are currently in beta. Report issues on [GitHub](https://github.com/OpenRouterTeam/python-sdk/issues). 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.md) | :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.md) | :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.md) | :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. | `{"total": 400000,"type": "tokens"}` |