> ## 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 All Models
> Get all available models of every modality in a single list. Each entry is the same object the modality specific endpoint returns, identified by its `api` field. If authenticated with a Requesty API key, returns only the models approved for your organization. Otherwise, returns all public models.
```bash cURL theme={"dark"}
curl https://router.requesty.ai/v1/models/all \
-H "Authorization: Bearer YOUR_REQUESTY_API_KEY"
```
```python Python theme={"dark"}
import httpx
response = httpx.get(
"https://router.requesty.ai/v1/models/all",
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/all", {
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": "chat",
"id": "vertex/claude-sonnet-4-5",
"object": "model",
"created": 1747933971,
"updated": 1747933971,
"owned_by": "system",
"input_price": 3e-06,
"caching_price": 3.75e-06,
"cached_price": 3e-07,
"output_price": 1.5e-05,
"pricing": [
{
"prompt_tokens_threshold": 0,
"input_price": 3e-06,
"caching_price": 3.75e-06,
"caching_5m_price": 3.75e-06,
"caching_1h_price": 6e-06,
"cached_price": 3e-07,
"output_price": 1.5e-05
},
{
"prompt_tokens_threshold": 200000,
"input_price": 6e-06,
"caching_price": 7.5e-06,
"caching_5m_price": 7.5e-06,
"caching_1h_price": 1.2e-05,
"cached_price": 6e-07,
"output_price": 2.25e-05
}
],
"max_output_tokens": 64000,
"context_window": 200000,
"supports_caching": true,
"supports_vision": true,
"supports_computer_use": true,
"supports_reasoning": true,
"supports_image_generation": false,
"supports_tool_calling": true,
"supports_role_developer": false,
"supports_web_search": true,
"supports_output_json_object": true,
"supports_output_json_schema": true,
"description": "The first hybrid reasoning model on the market with the highest level of intelligence and capability with toggleable extended thinking. Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.",
"data_retention": false,
"data_retention_days": 0,
"data_used_for_training": false,
"privacy_comments": "N/A",
"geolocation": "global",
"open_weights": false,
"model_lab": "vertex",
"model_canonical_name": "tbd"
},
{
"api": "embedding",
"id": "vertex/google/gemini-embedding-2-preview",
"object": "model",
"created": 1774621394,
"updated": 1774621394,
"owned_by": "system",
"pricing": {
"input_text": 2e-07,
"input_audio": 6.4e-06,
"input_image": 4.651162791e-07,
"input_video": 1.19696969697e-05,
"input_document": 4.651162791e-07
},
"data_retention": true,
"data_retention_days": 0,
"data_used_for_training": true,
"privacy_comments": "",
"geolocation": "global"
},
{
"api": "image",
"id": "openai/gpt-image-2",
"object": "model",
"created": 1776868154,
"updated": 1776868154,
"owned_by": "system",
"pricing": {
"input_text": 5e-06,
"input_image": 8e-06,
"output_text": 1e-05,
"output_image": 3e-05
},
"data_retention": true,
"data_retention_days": 0,
"data_used_for_training": true,
"privacy_comments": "",
"geolocation": "global"
},
{
"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": 2.5e-06,
"output_token": 1e-05
},
"data_retention": true,
"data_retention_days": 0,
"data_used_for_training": true,
"privacy_comments": "",
"geolocation": "global"
},
{
"api": "speech",
"id": "openai/gpt-audio-mini",
"object": "model",
"created": 1776935721,
"updated": 1776935721,
"owned_by": "system",
"pricing": {
"input_token": 6e-07,
"output_token": 2.4e-06
},
"data_retention": true,
"data_retention_days": 0,
"data_used_for_training": true,
"privacy_comments": "",
"geolocation": "global"
},
{
"api": "speech",
"id": "openai/tts-1",
"object": "model",
"created": 1767023142,
"updated": 1767023142,
"owned_by": "system",
"pricing": {
"input_character": 1.5e-05
},
"data_retention": true,
"data_retention_days": 0,
"data_used_for_training": true,
"privacy_comments": "",
"geolocation": "global"
}
]
}
```
List every model Requesty routes to, across all modalities, in a single response. Each entry is the same object its modality specific endpoint returns, and the `api` field (`chat`, `embedding`, `image`, `transcription` or `speech`) tells them apart.
When authenticated with an API key, returns only the models approved for your organization. Without authentication, returns all publicly available models.
## OpenAPI
````yaml GET /v1/models/all
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/all:
servers:
- url: https://router.requesty.ai
description: Inference router endpoint
get:
summary: List available models across all modalities
description: >-
Get all available models of every modality in a single list. Each entry
is the same object the modality specific endpoint returns, identified by
its `api` field. If authenticated with a Requesty API key, returns only
the models approved for your organization. Otherwise, returns all public
models.
operationId: listAllModels
responses:
'200':
description: List of available models
content:
application/json:
schema:
$ref: '#/components/schemas/AllModelsResponse'
example:
object: list
data:
- api: chat
id: vertex/claude-sonnet-4-5
object: model
created: 1747933971
updated: 1747933971
owned_by: system
input_price: 0.000003
caching_price: 0.00000375
cached_price: 3.e-7
output_price: 0.000015
pricing:
- prompt_tokens_threshold: 0
input_price: 0.000003
caching_price: 0.00000375
caching_5m_price: 0.00000375
caching_1h_price: 0.000006
cached_price: 3.e-7
output_price: 0.000015
- prompt_tokens_threshold: 200000
input_price: 0.000006
caching_price: 0.0000075
caching_5m_price: 0.0000075
caching_1h_price: 0.000012
cached_price: 6.e-7
output_price: 0.0000225
max_output_tokens: 64000
context_window: 200000
supports_caching: true
supports_vision: true
supports_computer_use: true
supports_reasoning: true
supports_image_generation: false
supports_tool_calling: true
supports_role_developer: false
supports_web_search: true
supports_output_json_object: true
supports_output_json_schema: true
description: >-
The first hybrid reasoning model on the market with the
highest level of intelligence and capability with
toggleable extended thinking. Top-tier results in
reasoning, coding, multilingual tasks, long-context
handling, honesty, and image processing.
data_retention: false
data_retention_days: 0
data_used_for_training: false
privacy_comments: N/A
geolocation: global
open_weights: false
model_lab: vertex
model_canonical_name: tbd
- api: embedding
id: vertex/google/gemini-embedding-2-preview
object: model
created: 1774621394
updated: 1774621394
owned_by: system
pricing:
input_text: 2.e-7
input_audio: 0.0000064
input_image: 4.651162791e-7
input_video: 0.0000119696969697
input_document: 4.651162791e-7
data_retention: true
data_retention_days: 0
data_used_for_training: true
privacy_comments: ''
geolocation: global
- api: image
id: openai/gpt-image-2
object: model
created: 1776868154
updated: 1776868154
owned_by: system
pricing:
input_text: 0.000005
input_image: 0.000008
output_text: 0.00001
output_image: 0.00003
data_retention: true
data_retention_days: 0
data_used_for_training: true
privacy_comments: ''
geolocation: global
- 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
- api: speech
id: openai/gpt-audio-mini
object: model
created: 1776935721
updated: 1776935721
owned_by: system
pricing:
input_token: 6.e-7
output_token: 0.0000024
data_retention: true
data_retention_days: 0
data_used_for_training: true
privacy_comments: ''
geolocation: global
- api: speech
id: openai/tts-1
object: model
created: 1767023142
updated: 1767023142
owned_by: system
pricing:
input_character: 0.000015
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:
AllModelsResponse:
type: object
required:
- object
- data
properties:
object:
type: string
enum:
- list
description: The object type, always 'list'
data:
type: array
description: >-
The list of available models across every modality. Use the `api`
field to tell the entries apart.
items:
oneOf:
- $ref: '#/components/schemas/Model'
- $ref: '#/components/schemas/EmbeddingModel'
- $ref: '#/components/schemas/ImageModel'
- $ref: '#/components/schemas/TranscriptionModel'
- $ref: '#/components/schemas/SpeechModel'
discriminator:
propertyName: api
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.
Model:
type: object
properties:
api:
type: string
description: The modality of the model, e.g. 'chat'
id:
type: string
description: The model identifier (e.g., 'openai/gpt-5-mini')
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
input_price:
type: number
format: float
description: Price per input token in USD
caching_price:
type: number
format: float
description: Price per token for caching in USD
cached_price:
type: number
format: float
description: Price per cached token in USD
output_price:
type: number
format: float
description: Price per output token in USD
pricing_scheme:
type: string
description: Pricing scheme hint when the model is not priced per token
pricing:
type: array
description: >-
Pricing bands, ordered by prompt token threshold. A band applies
once the prompt exceeds its `prompt_tokens_threshold`.
items:
$ref: '#/components/schemas/PricingBand'
max_output_tokens:
type: integer
description: Maximum number of output tokens the model can generate
context_window:
type: integer
description: Maximum context window size in tokens
supports_caching:
type: boolean
description: Whether the model supports caching
supports_vision:
type: boolean
description: Whether the model supports vision/image inputs
supports_computer_use:
type: boolean
description: Whether the model supports computer use capabilities
supports_reasoning:
type: boolean
description: Whether the model supports reasoning capabilities
supports_image_generation:
type: boolean
description: Whether the model can generate images
supports_tool_calling:
type: boolean
description: Whether the model supports tool/function calling
supports_role_developer:
type: boolean
description: Whether the model supports the `developer` message role
supports_web_search:
type: boolean
description: Whether the model supports web search via the `web_search` tool type
supports_output_json_object:
type: boolean
description: >-
Whether the model supports `response_format` with `{ "type":
"json_object" }`
supports_output_json_schema:
type: boolean
description: >-
Whether the model supports strict structured outputs via
`response_format` with `{ "type": "json_schema" }`
description:
type: string
description: A description of the model's capabilities and use cases
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'
retires_at:
type: string
format: date-time
description: >-
When the model is scheduled to be retired, in ISO 8601 format. After
this date, requests to the model fail. Null if no retirement is
scheduled.
open_weights:
type: boolean
description: Whether the model's weights are openly available
model_lab:
type: string
description: The lab that trained the model
model_canonical_name:
type: string
description: >-
The canonical name of the underlying model, shared across the
providers that serve it
EmbeddingModel:
type: object
properties:
api:
type: string
enum:
- embedding
description: The modality of the model, always 'embedding'
id:
type: string
description: The model identifier (e.g., 'openai/text-embedding-3-small')
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. Only the fields relevant to the model's
pricing scheme are returned.
properties:
input_text:
type: number
format: float
description: Price per input text token in USD
input_audio:
type: number
format: float
description: Price per input audio token in USD
input_image:
type: number
format: float
description: Price per input image token in USD
input_video:
type: number
format: float
description: Price per input video token in USD
input_document:
type: number
format: float
description: Price per input document token 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'
ImageModel:
type: object
properties:
api:
type: string
enum:
- image
description: The modality of the model, always 'image'
id:
type: string
description: The model identifier (e.g., 'openai/gpt-image-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. Only the fields relevant to the model's
pricing scheme are returned.
properties:
input_text:
type: number
format: float
description: Price per input text token in USD
input_image:
type: number
format: float
description: Price per input image token in USD
output_text:
type: number
format: float
description: Price per output text token in USD
output_image:
type: number
format: float
description: Price per output image token 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'
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'
SpeechModel:
type: object
properties:
api:
type: string
enum:
- speech
description: The modality of the model, always 'speech'
id:
type: string
description: The model identifier (e.g., 'openai/tts-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_character` 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_character:
type: number
format: float
description: Price per input character 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'
PricingBand:
type: object
properties:
prompt_tokens_threshold:
type: integer
description: Prompt token count from which this band applies
input_price:
type: number
format: float
description: Price per input token in USD
caching_price:
type: number
format: float
description: Price per token for writing to the cache in USD
caching_5m_price:
type: number
format: float
description: Price per token for a 5 minute cache write in USD
caching_1h_price:
type: number
format: float
description: Price per token for a 1 hour cache write in USD
cached_price:
type: number
format: float
description: Price per cached input token in USD
output_price:
type: number
format: float
description: Price per output token in USD
pricing_scheme:
type: string
description: Pricing scheme hint for this band
securitySchemes:
BearerAuth:
type: http
scheme: bearer
description: API key for authentication
````