List models filtered by user provider preferences, privacy settings, and guardrails
List models filtered by user provider preferences, privacy settings, and guardrails. Returns text-output models by default; pass output_modalities (a comma-separated list of text, image, embeddings, audio, video, rerank, speech, transcription, or all) to include other modalities. If requesting through a regional hostname, the results will be filtered to models that satisfy in-region routing for that region.
Query parameters
Number of records to skip for pagination. When both offset and limit are omitted, the full list is returned
Number of records to skip for pagination. When both offset and limit are omitted, the full list is returned
Maximum number of records to return (max 1000). When both offset and limit are omitted, the full list is returned
Maximum number of records to return (max 1000). When both offset and limit are omitted, the full list is returned
Filter models by output modality. Accepts a comma-separated list of modalities (text, image, embeddings, audio, video, rerank, decisions, speech, transcription) or "all" to include all models. Defaults to "text".
Filter models by output modality. Accepts a comma-separated list of modalities (text, image, embeddings, audio, video, rerank, decisions, speech, transcription) or "all" to include all models. Defaults to "text".
Response
Returns a list of models filtered by user provider preferences
Example response
{
"data": [
{
"architecture": {
"input_modalities": [
"text"
],
"instruct_type": "chatml",
"modality": "text->text",
"output_modalities": [
"text"
],
"tokenizer": "GPT"
},
"canonical_slug": "openai/gpt-4",
"context_length": 8192,
"created": 1692901234,
"default_parameters": null,
"description": "GPT-4 is a large multimodal model that can solve difficult problems with greater accuracy.",
"expiration_date": null,
"id": "openai/gpt-4",
"knowledge_cutoff": null,
"links": {
"details": "/api/v1/models/openai/gpt-4/endpoints"
},
"name": "GPT-4",
"per_request_limits": null,
"pricing": {
"completion": "0.00006",
"image": "0",
"prompt": "0.00003",
"request": "0"
},
"supported_parameters": [
"temperature",
"top_p",
"max_tokens",
"frequency_penalty",
"presence_penalty"
],
"supported_voices": null,
"top_provider": {
"context_length": 8192,
"is_moderated": true,
"max_completion_tokens": 4096
}
}
],
"links": {
"next": "/api/v1/models?offset=500&limit=500"
},
"total_count": 150
}Changes
Changed in 13 of the 303 revisions of this API.13426
- ●
added the new
decisionsenum value to the////response property for the response statusresponse-property-enum-value-added
- ●
- ○
added the new optional
queryrequest parameteroutput_modalitiesnew-optional-request-parameter
- ○
- ○
added the optional property
/////to the response with the statusresponse-optional-property-added
- ○
- ○
added the optional property
//to the response with the statusresponse-optional-property-added
- ○
- ○
added the non-success response with the status
response-non-success-status-added
- ○
- ●
added the new
predictionenum value to the///response property for the response statusresponse-property-enum-value-added
- ●
- ○
added the optional property
/////to the response with the statusresponse-optional-property-added
- ○
added the optional property
/////to the response with the statusresponse-optional-property-added
- ○
- ○
added the optional property
///to the response with the statusresponse-optional-property-added
- ○
- ○
added the new optional
queryrequest parameterlimitnew-optional-request-parameter
- ○
added the new optional
queryrequest parameteroffsetnew-optional-request-parameter
- ○
added the required property
to the response with the statusresponse-required-property-added
- ○
added the required property
to the response with the statusresponse-required-property-added
- ○
- ○
added the optional property
///to the response with the statusresponse-optional-property-added
- ○