> ## Documentation Index
> Fetch the complete documentation index at: https://docs.requesty.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# List Transcription Models
> Get all available transcription models. If authenticated with a Requesty API key, returns only the models approved for your organization. Otherwise, returns all public models. Aliases and routing policies are chat-only and are never returned here.
```bash cURL theme={"dark"}
curl https://router.requesty.ai/v1/models/transcription \
-H "Authorization: Bearer YOUR_REQUESTY_API_KEY"
```
```python Python theme={"dark"}
import httpx
response = httpx.get(
"https://router.requesty.ai/v1/models/transcription",
headers={"Authorization": "Bearer YOUR_REQUESTY_API_KEY"},
)
for model in response.json()["data"]:
print(model["id"])
```
```typescript TypeScript theme={"dark"}
const response = await fetch("https://router.requesty.ai/v1/models/transcription", {
headers: { Authorization: `Bearer ${process.env.REQUESTY_API_KEY}` },
});
const { data } = await response.json();
for (const model of data) {
console.log(model.id);
}
```
```json Response 200 theme={"dark"}
{
"object": "list",
"data": [
{
"api": "transcription",
"id": "openai/whisper-1",
"object": "model",
"created": 1767023142,
"updated": 1767023142,
"owned_by": "system",
"pricing": {
"input_second": 0.0001
},
"data_retention": true,
"data_retention_days": 30,
"data_used_for_training": false,
"privacy_comments": "",
"geolocation": "global"
},
{
"api": "transcription",
"id": "openai/gpt-4o-transcribe",
"object": "model",
"created": 1767023142,
"updated": 1767023142,
"owned_by": "system",
"pricing": {
"input_token": 2.5e-06,
"output_token": 1e-05
},
"data_retention": true,
"data_retention_days": 30,
"data_used_for_training": false,
"privacy_comments": "",
"geolocation": "global"
}
]
}
```
List the transcription models available through the [`/v1/audio/transcriptions`](/api-reference/endpoint/audio-transcriptions-create) endpoint.
When authenticated with an API key, returns only the models approved for your organization. Without authentication, returns all publicly available models. Aliases and routing policies exist for chat only, so they never appear here.
Pricing is per audio second (`input_second`) or per token (`input_token` and `output_token`), depending on the model.
## OpenAPI
````yaml GET /v1/models/transcription
openapi: 3.0.3
info:
title: Requesty Inference API
description: >-
Requesty Inference API for AI model routing. OpenAI-compatible endpoints for
chat completions, embeddings, images, audio, and more.
version: 1.0.0
servers:
- url: https://router.requesty.ai
description: Inference router endpoint
security:
- BearerAuth: []
paths:
/v1/models/transcription:
servers:
- url: https://router.requesty.ai
description: Inference router endpoint
get:
summary: List available transcription models
description: >-
Get all available transcription models. If authenticated with a Requesty
API key, returns only the models approved for your organization.
Otherwise, returns all public models. Aliases and routing policies are
chat-only and are never returned here.
operationId: listTranscriptionModels
responses:
'200':
description: List of available models
content:
application/json:
schema:
$ref: '#/components/schemas/TranscriptionModelsResponse'
example:
object: list
data:
- api: transcription
id: openai/whisper-1
object: model
created: 1767023142
updated: 1767023142
owned_by: system
pricing:
input_second: 0.0001
data_retention: true
data_retention_days: 0
data_used_for_training: true
privacy_comments: ''
geolocation: global
- api: transcription
id: openai/gpt-4o-transcribe
object: model
created: 1767023142
updated: 1767023142
owned_by: system
pricing:
input_token: 0.0000025
output_token: 0.00001
data_retention: true
data_retention_days: 0
data_used_for_training: true
privacy_comments: ''
geolocation: global
'400':
description: Bad request - malformed payload or invalid parameters.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'401':
description: Unauthorized - missing or empty Authorization header.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'402':
description: Payment required - organization balance exhausted.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'403':
description: Forbidden - invalid token or model not in access list.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'404':
description: Not found - provider/model not supported.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'429':
description: Rate limit exceeded. Retry after the Retry-After header value.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'500':
description: Internal server error.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'502':
description: Bad gateway - upstream provider returned an invalid response.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
security:
- BearerAuth: []
- {}
components:
schemas:
TranscriptionModelsResponse:
type: object
required:
- object
- data
properties:
object:
type: string
enum:
- list
description: The object type, always 'list'
data:
type: array
items:
$ref: '#/components/schemas/TranscriptionModel'
description: The list of available transcription models
ErrorResponse:
type: object
required:
- error
properties:
error:
type: object
required:
- origin
- message
properties:
origin:
type: string
enum:
- router
- provider
description: >-
Whether the error originated from Requesty's router or an
upstream provider.
message:
type: string
description: Human-readable error description.
TranscriptionModel:
type: object
properties:
api:
type: string
enum:
- transcription
description: The modality of the model, always 'transcription'
id:
type: string
description: The model identifier (e.g., 'openai/whisper-1')
object:
type: string
enum:
- model
description: The object type, always 'model'
created:
type: integer
description: The Unix timestamp (in seconds) when the model was created
updated:
type: integer
description: The Unix timestamp (in seconds) when the model was last updated
owned_by:
type: string
description: The system or organization that owns the model
example: system
pricing:
type: object
description: >-
Prices for the model. Token prices and `input_second` are mutually
exclusive, depending on the model's pricing scheme.
properties:
input_token:
type: number
format: float
description: Price per input token in USD
output_token:
type: number
format: float
description: Price per output token in USD
input_second:
type: number
format: float
description: Price per second of input audio in USD
data_retention:
type: boolean
description: Whether the provider retains request data
data_retention_days:
type: integer
description: Number of days the provider retains request data
data_used_for_training:
type: boolean
description: Whether the provider may use request data for training
privacy_comments:
type: string
description: Additional privacy notes for the model
geolocation:
type: string
description: Region the model is served from, e.g. 'us' or 'eu'
securitySchemes:
BearerAuth:
type: http
scheme: bearer
description: API key for authentication
````