docs: Mintlify MDX docs + docs.json; bump Speakeasy to 1.787.0 (#382)

This commit is contained in:
Matt Apperson
2026-06-30 16:13:28 -04:00
committed by GitHub
parent 778e2e36fb
commit babeffc9aa
2100 changed files with 50407 additions and 16612 deletions
+16
View File
@@ -0,0 +1,16 @@
---
title: "ModelReasoning"
---
Reasoning effort configuration. Omitted for non-reasoning models and dynamic router models.
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `default_effort` | [OptionalNullable[components.DefaultEffort]](../components/defaulteffort.mdx) | :heavy_minus_sign: | N/A | medium |
| `default_enabled` | *Optional[bool]* | :heavy_minus_sign: | Default reasoning enabled state when the client does not set `reasoning.enabled`. | |
| `mandatory` | *bool* | :heavy_check_mark: | When true, reasoning cannot be disabled and effort "none" is rejected. | |
| `supported_efforts` | List[[Nullable[components.ReasoningEffort]](../components/reasoningeffort.mdx)] | :heavy_minus_sign: | Allowed reasoning effort values for this model, in descending effort order (highest first). Null means no allowlist — all gateway effort values are accepted. | |
| `supports_max_tokens` | *Optional[bool]* | :heavy_minus_sign: | Present and `true` when the model accepts `reasoning.max_tokens` in requests (Anthropic-style) instead of or in addition to `reasoning.effort`. Omitted otherwise. | |