mirror of
https://github.com/wassname/openrouter-python-sdk-retry-errors.git
synced 2026-07-29 11:23:49 +08:00
github-actions[bot]GitHubspeakeasybotspeakeasy-github[bot] <128539517+speakeasy-github[bot]@users.noreply.github.com>Co-authored-by: speakeasybot <bot@speakeasyapi.dev> Co-authored-by: speakeasy-github[bot] <128539517+speakeasy-github[bot]@users.noreply.github.com>
12 lines
7.8 KiB
Plaintext
12 lines
7.8 KiB
Plaintext
---
|
|
title: "BaseReasoningConfig"
|
|
---
|
|
|
|
## Fields
|
|
|
|
| Field | Type | Required | Description | Example |
|
|
| -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
| `context` | [OptionalNullable[components.ReasoningContext]](../components/reasoningcontext.mdx) | :heavy_minus_sign: | Controls which reasoning is available to the model. `auto` uses the model default (same as omitting); `all_turns` includes reasoning from earlier turns passed in input; `current_turn` limits to the current turn only. Only supported by OpenAI GPT-5.6 and newer. | all_turns |
|
|
| `effort` | [OptionalNullable[components.ReasoningEffort]](../components/reasoningeffort.mdx) | :heavy_minus_sign: | N/A | medium |
|
|
| `mode` | [OptionalNullable[components.ReasoningMode]](../components/reasoningmode.mdx) | :heavy_minus_sign: | Selects the reasoning mode. `standard` is the default; `pro` engages deeper reasoning on models that support it, billed at standard token rates. Only supported by OpenAI GPT-5.6 and newer. | standard |
|
|
| `summary` | [OptionalNullable[components.ReasoningSummaryVerbosity]](../components/reasoningsummaryverbosity.mdx) | :heavy_minus_sign: | N/A | auto | |