Models and utility endpoints
Models
Section titled “Models”| Endpoint | Models | Default |
|---|---|---|
/v1/decide |
purplemist-flash-1.0 |
purplemist-flash-1.0 |
/v1/extract |
mist-extract-1.0, mist-extract-flash-1.0 |
mist-extract-1.0 |
/v1/language-id |
lid-neural-608, lid-lite-608 |
lid-neural-608 |
/v1/diacritize |
diacnet-2.0, diacnet-mini-2.0, diactag-2.0 |
diacnet-2.0 |
/v1/questions/generate |
mist-qg-1.5b |
mist-qg-1.5b |
All of them are open-weight and published on Hugging Face, with model cards covering training data, benchmarks and limitations.
Utility endpoints
Section titled “Utility endpoints”| Endpoint | Key | What it does |
|---|---|---|
GET /v1/models |
no | Lists every model with its endpoint, status (available / coming soon), billing unit and languages. |
GET /v1/languages |
no | The 25 question-generation languages. |
GET /health |
no | {"status": "ok", ...} |
POST /v1/warmup |
yes | Starts services in the background. See Cold starts and warm-up. |
curl "$OLAVERSE_URL/v1/models"