GET /v1/models returns the models your API key can call, with the model ID to put in the model field.
The list can change over time, so refresh it regularly instead of hard-coding it.
Key points
- Endpoint: GET /v1/models.
- The response only includes models you are allowed to call.
- Each entry has a display_name and an owned_by naming the model maker (anthropic, openai, google…); combos show xpncore.
- Models with a 1M context also list an <id>[1M] entry that accepts up to 1,000,000 input tokens.
- In a combo, one member model serves each request from start to finish.
- Requests using a feature the model does not support (for example images on a text-only model) are rejected.
Example request
GET /v1/models
curl --request GET 'https://api.xpncore.com/v1/models' \
--max-time 35 \
--header "Authorization: Bearer $API_KEY"