Fetch Models
GET/v1/models
Fetch all available models or use one or more filters
Request
Query Parameters
- llm
- voice
- chat
- openrouter
- providerAndSubtype
- enabledAndSubtype
- voices
- restrictions
Possible values: [llm
, vision
, embedding
, image
, voice
, moderation
, coding
, free
]
Filter by type of model.
Filter by type 'llm' language models
Example: llm
Filter by type 'voice' (tts and stt)
Example: voice
Possible values: [chat
, fill-mask
, question-answering
, tts
, stt
, multimodal
]
Filter by subtype of model.
Filter by subtype 'chat'
Example: chat
Filter by provider of the model.
Filter by provider 'openrouter'
Example: openrouter
Filter by a combination of provider and subtype.
Filter by provider 'openrouter' and subtype 'chat'
Example: provider=openrouter&subtype=chat
Possible values: [1
, 0
]
only show enabled chat models
only show enabled chat models
Example: enabled=1&subtype=chat
Retrieve a complete list of available voices. just use /v1/models?voices do not include any other value
Display list of voices for tts voice models, just use /v1/models?voices'
Example: voices
Retrieve a complete list of available Country Restrictions. just use /v1/models?restrictions do not include any other value
Display list of different provider supported countries lists, just use /v1/models?restrictions'
Example: restrictions
Responses
- 200
Models or voices list depending on query parameter used.
- application/json
- Schema
- Example (from schema)
- Models
- Voices
- Restrictions
Schema
- ModelResponse
- VoiceModelResponse
- RestrictionsResponse
- Array [
- ]
- Array [
- ]
- Array [
- ]
Type of the list
data object[]
Whether Model is enabled
Possible values: [llm
, vision
, embedding
, image
, voice
, moderation
, code
]
Type of the model
Subtype of the model
Provider of the model
The base model name
Provider specific identifier
Description of the Model
Max cumulative tokens supported by the model
Max tokens that this model can return in the response
Price for request - per unit. If not present, price only provided by the provider in query response
Price for response - per unit. If not present, price only provided by the provider in query response
Price unit, the number of price_type per price
Possible values: [token
, char
, request
, tokens
, image
, minute
, characters
, character
, provider
]
Type of the price
Average cost of the model, tracking actual usage. This is the average cost per 1000 characters
Average latency by combined prompt/response size, in the format: 2000/4000/8000/16000/32000/Average_Latency_per_1000_characters
Availability status of the model
Total count of queries for this model
Type of the response object, always a list.
data object[]
Provider of the voice model.
Model identifier.
Unique identifier for the voice.
Name of the voice.
Description of the voice characteristics.
Type of the response object, always a list.
data object[]
Unique identifier for the restrict table.
Name or description, usually the provider name.
JSON string of supported countries.
{
"object": "list",
"data": [
{
"enabled": 1,
"type": "llm",
"subtype": null,
"provider": "openrouter",
"model": "nous-capybara-7b",
"route": "nousresearch/nous-capybara-7b",
"description": "The Capybara series is a collection of datasets and models...",
"max_tokens": 4096,
"max_response_tokens": 4096,
"req_price": "0.0000001800000000",
"res_price": "0.0000001800000000",
"price_type": "token",
"price_unit": "1.00",
"avg_cost": "0.0000912966",
"latency": "1162/2145/6245/8234/18456/8162",
"available": 1,
"query_count": "310,000"
},
{
"...": "Additional models not shown..."
}
]
}
Example response for a models request
{
"object": "list",
"data": [
{
"enabled": 1,
"type": "llm",
"subtype": null,
"provider": "openrouter",
"model": "nous-capybara-7b",
"route": "nousresearch/nous-capybara-7b",
"description": "The Capybara series...",
"max_tokens": 4096,
"max_response_tokens": 4096,
"req_price": "0.0000001800000000",
"res_price": "0.0000001800000000",
"price_type": "token",
"price_unit": "1.00",
"avg_cost": "0.0000912966",
"latency": "1162/na/na/na/na/1162",
"available": 1,
"query_count": "310"
},
{
"...": "Additional models not shown..."
}
]
}
Example voice models response for a models query with the '?voices' parameter
{
"object": "list",
"data": [
{
"provider": "elevenlabs",
"model": "eleven_multilingual_v2",
"voice": "21m00Tcm4TlvDq8ikWAM",
"name": "Rachel",
"description": "accent: american, description: calm, age: young, gender: female, use case: narration"
},
{
"provider": "elevenlabs",
"model": "eleven_turbo_v2",
"voice": "zrHiDhphv9ZnVXBqCLjz",
"name": "Mimi",
"description": "accent: english-swedish, description: childish, age: young, gender: female, use case: animation"
},
{
"...": "Additional models not shown..."
}
]
}
Example country restrictions response for a models query with the '?restrictions' parameter
{
"object": "list",
"data": [
{
"restrict_id": 2,
"name": "openai",
"countries": "{\"countries\":[{\"name\":\"Albania\",\"alpha-2\":\"AL\"},{\"name\":\"Algeria\",\"alpha-2\":\"DZ\"},{\"name\":\"Afghanistan\",\"alpha-2\":\"AF\"}]}"
},
{
"restrict_id": 3,
"name": "anthropic",
"countries": "{\"countries\":[{\"name\":\"Germany\",\"alpha-2\":\"DE\"},{\"name\":\"France\",\"alpha-2\":\"FR\"},{\"name\":\"Spain\",\"alpha-2\":\"ES\"}]}"
},
{
"...": "Additional restrictions not shown..."
}
]
}