Skip to main content
GET
/
v1
/
models
Models
curl --request GET \
  --url https://api.compose.market/v1/models \
  --header 'Content-Type: application/json' \
  --data '
{
  "q": "<string>",
  "provider": "<string>",
  "modality": "<string>",
  "operation": "<string>",
  "limit": 123,
  "cursor": "<string>"
}
'
{
  "object": "list",
  "data": [
    {
      "modelId": "gpt-5.5",
      "provider": "azure",
      "name": "gpt-5.5"
    }
  ],
  "total": 1,
  "next_cursor": null
}

Documentation Index

Fetch the complete documentation index at: https://docs.compose.market/llms.txt

Use this file to discover all available pages before exploring further.

Model routes use public catalog IDs. Duplicate upstream model names are resolved by the generated catalog, so callers send the public ID shown by these endpoints.

​
Routes

MethodPathAuthDescription
GET/v1/modelsNoneNative generated model catalog.
GET/v1/models/allNoneExtended catalog when bundled.
GET/v1/models/{model}NoneOne native model card.
GET/v1/models/{model}/paramsNoneOptional parameter metadata for one model.
POST/v1/models/searchNoneSearch and filter native model cards.
GET/api/modelsNonePublic catalog proxy backed by the models service.
GET/api/pricingNoneCompact pricing table from the bundled inference catalog.

​
Search body

​
q
string
Search text matched against model metadata.
​
provider
string
Provider slug. Invalid providers return 400.
​
modality
string
Canonical modality such as text, image, audio, video, or embedding.
​
operation
string
Canonical operation for the selected modality.
​
limit
number
Maximum models to return.
​
cursor
string
Cursor returned by the previous search page.

​
Response

​
object
string
list for list and search routes.
​
data
array
Model cards from the generated catalog.
​
next_cursor
string
Search cursor when more results are available.
{
  "object": "list",
  "data": [
    {
      "modelId": "gpt-5.5",
      "provider": "azure",
      "name": "gpt-5.5"
    }
  ],
  "total": 1,
  "next_cursor": null
}