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
Copy file name to clipboardExpand all lines: .speakeasy/out.openapi.yaml
+43-3Lines changed: 43 additions & 3 deletions
Original file line number
Diff line number
Diff line change
@@ -9434,7 +9434,7 @@ components:
9434
9434
type: integer
9435
9435
size:
9436
9436
description: >-
9437
-
Optional. A convenience shorthand for output dimensions — pass a tier ("2K", "4K") or explicit pixels ("2048x2048") and we normalize it to the right dimensions for the chosen provider. Interchangeable with resolution + aspect_ratio; use those directly for enumerated, per-model discoverable values. Conflicting size + resolution/aspect_ratiois rejected.
9437
+
Optional. A convenience shorthand for output dimensions — pass a tier ("2K", "4K") or explicit pixels ("2048x2048") and we normalize it to the right dimensions for the chosen provider. A tier size is equivalent to setting `resolution` and combines with `aspect_ratio`. An explicit pixel size is authoritative: a mismatched `resolution` or `aspect_ratio` alongside it is rejected with a 400.
9438
9438
example: 2K
9439
9439
type: string
9440
9440
stream:
@@ -17356,6 +17356,7 @@ components:
17356
17356
enabled: true
17357
17357
id: pareto-router
17358
17358
min_coding_score: 0.8
17359
+
price_source: prompt
17359
17360
properties:
17360
17361
enabled:
17361
17362
description: Set to false to disable the pareto-router plugin for this request. Defaults to true.
@@ -17366,12 +17367,20 @@ components:
17366
17367
type: string
17367
17368
min_coding_score:
17368
17369
description: >-
17369
-
Minimum desired coding score between 0 and 1, where 1 is best. Higher values select from stronger coding models (sourced from Artificial Analysis coding percentiles). Maps internally to one of three tiers (low, medium, high). Omit to use the router default tier.
17370
+
Minimum coding quality score between 0 and 1. Maps to internal quality tiers: >= 0.66 → high (top coding models), >= 0.33 → medium (strong modern flagships), < 0.33 → low (capable coders above the median). Omit to default to the highest tier (equivalent to >= 0.66).
17370
17371
example: 0.8
17371
17372
format: double
17372
17373
maximum: 1
17373
17374
minimum: 0
17374
17375
type: number
17376
+
price_source:
17377
+
description: >-
17378
+
Price source for the Pareto frontier cost axis. "prompt" uses catalog list price (endpoint.pricing.prompt). "weighted_avg" uses traffic-weighted effective input price from ClickHouse, falling back to prompt price for models without traffic data. Defaults to "prompt".
17379
+
enum:
17380
+
- prompt
17381
+
- weighted_avg
17382
+
type: string
17383
+
x-speakeasy-unknown-values: allow
17375
17384
required:
17376
17385
- id
17377
17386
type: object
@@ -23705,7 +23714,8 @@ paths:
23705
23714
- $ref: "#/components/parameters/AppCategories"
23706
23715
/audio/transcriptions:
23707
23716
post:
23708
-
description: Transcribes audio into text. Accepts base64-encoded audio input and returns the transcribed text.
23717
+
description: >-
23718
+
Transcribes audio into text. Accepts base64-encoded audio input as JSON or an OpenAI-style multipart/form-data file upload, and returns the transcribed text.
23709
23719
operationId: createAudioTranscriptions
23710
23720
requestBody:
23711
23721
content:
@@ -23718,6 +23728,36 @@ paths:
23718
23728
model: openai/whisper-large-v3
23719
23729
schema:
23720
23730
$ref: '#/components/schemas/STTRequest'
23731
+
multipart/form-data:
23732
+
example:
23733
+
file: audio.wav
23734
+
language: en
23735
+
model: openai/whisper-large-v3
23736
+
schema:
23737
+
properties:
23738
+
file:
23739
+
description: >-
23740
+
The audio file to transcribe. The format is derived from the filename extension or the file part content type. Max 25 MB; send larger files as base64 JSON via input_audio.
23741
+
format: binary
23742
+
type: string
23743
+
language:
23744
+
description: The language of the input audio (ISO-639-1).
23745
+
type: string
23746
+
model:
23747
+
description: The model to use for transcription.
23748
+
type: string
23749
+
response_format:
23750
+
description: The response format. Only "json" is supported.
0 commit comments