You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit acc4319
Browse filesBrowse the repository at this point in the historyBrowse files
Copy file name to clipboardExpand all lines: .speakeasy/out.openapi.yaml
+10Lines changed: 10 additions & 0 deletions
Original file line number
Diff line number
Diff line change
@@ -2904,6 +2904,7 @@ components:
2904
2904
cost_quality_tradeoff: 7
2905
2905
enabled: true
2906
2906
id: 'auto-router'
2907
+
pin_model: false
2907
2908
properties:
2908
2909
allowed_models:
2909
2910
description: 'List of model patterns to filter which models the auto-router can route between. Supports wildcards (e.g., "anthropic/*" matches all Anthropic models). When not specified, uses the default supported models list.'
@@ -2927,6 +2928,10 @@ components:
2927
2928
enum:
2928
2929
- 'auto-router'
2929
2930
type: 'string'
2931
+
pin_model:
2932
+
description: 'When true, reuses the model from the most recent assistant message''s `model` attribute for subsequent turns. Defaults to false.'
2933
+
example: false
2934
+
type: 'boolean'
2930
2935
required:
2931
2936
- 'id'
2932
2937
type: 'object'
@@ -4469,6 +4474,7 @@ components:
4469
4474
description: 'Assistant message for requests and responses'
4470
4475
example:
4471
4476
content: 'The capital of France is Paris.'
4477
+
model: 'openai/gpt-4o'
4472
4478
role: 'assistant'
4473
4479
properties:
4474
4480
audio:
@@ -4483,6 +4489,10 @@ components:
4483
4489
description: 'Assistant message content'
4484
4490
images:
4485
4491
$ref: '#/components/schemas/ChatAssistantImages'
4492
+
model:
4493
+
description: 'Model that generated this assistant message'
Copy file name to clipboardExpand all lines: docs/components/autorouterplugin.mdx
+2-1Lines changed: 2 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -9,4 +9,5 @@ title: "AutoRouterPlugin"
9
9
| `allowed_models` | List[*str*] | :heavy_minus_sign: | List of model patterns to filter which models the auto-router can route between. Supports wildcards (e.g., "anthropic/*" matches all Anthropic models). When not specified, uses the default supported models list. | [<br/>"anthropic/*",<br/>"openai/gpt-4o",<br/>"google/*"<br/>] |
10
10
| `cost_quality_tradeoff` | *Optional[int]* | :heavy_minus_sign: | Controls cost vs. quality routing tradeoff (0β10). 0 = pure quality (best model regardless of cost), 10 = maximize for cost (cheapest model wins). Intermediate values blend quality and cost signals continuously. Defaults to 7. | 7 |
11
11
| `enabled` | *Optional[bool]* | :heavy_minus_sign: | Set to false to disable the auto-router plugin for this request. Defaults to true. | |
| `pin_model` | *Optional[bool]* | :heavy_minus_sign: | When true, reuses the model from the most recent assistant message's `model` attribute for subsequent turns. Defaults to false. | false |
0 commit comments