API reference
API reference
Eight OpenAI-compatible endpoints. Bearer auth. JSON in, JSON or stream out.
All endpoints require Authorization: Bearer qbt_.... Most live under https://api.qubittron.ai/v1/; TTS is at /api/v1/tts/text_to_audio.
| Endpoint | Path | Notes |
|---|---|---|
| List models | GET /v1/models | Discovery |
| Chat completions | POST /v1/chat/completions | Streaming optional |
| Completions | POST /v1/completions | Legacy text completions |
| Responses | POST /v1/responses | Requires store: false |
| Embeddings | POST /v1/embeddings | Single string or array |
| Image generation | POST /v1/images/generations | Returns base64 or URL |
| Audio transcriptions | POST /v1/audio/transcriptions | Multipart, 25 MB cap |
| Text to speech | POST /api/v1/tts/text_to_audio | NVIDIA Riva, language-routed |
Common patterns
Auth header
Authorization: Bearer qbt_<key>Error envelope
{ "error": { "message": "...", "type": "...", "code": "..." } }Status codes
400 (validation / unknown model), 401 (bad key), 402 (no balance), 413 (oversize upload), 429 (rate limited), 502 (upstream), 503 (transient internal — retry).
See Getting started for the full error table and rate-limit behavior.