4. Endpoint Overview#
All endpoints are mounted under the /v1 prefix (locally: http://183.240.79.21:52099/v1).
| Capability | Method | Path | Description |
|---|---|---|---|
| List available models | GET | /v1/models | Returns the models this key may access |
| Chat completions | POST | /v1/chat/completions | Primary endpoint; supports streaming |
| Responses | POST | /v1/responses | OpenAI Responses API compatible |
| Text embeddings | POST | /v1/embeddings | Generates embedding vectors |
| Image generation | POST | /v1/images/generations | Text to image |
| Image editing | POST | /v1/images/edits | Image-to-image / inpainting (multipart) |
| Speech synthesis | POST | /v1/audio/speech | TTS; returns an audio byte stream |
| Speech recognition | POST | /v1/audio/transcriptions | STT / Whisper (multipart) |
| Rerank | POST | /v1/rerank | Re-ranks documents by relevance |
| Anthropic messages | POST | /v1/messages | Anthropic Messages API compatible |
| Create video task | POST | /v1/video/create, /v1/videos | Asynchronous |
| MJ image generation | POST | /v1/mj/submit/imagine, /v1/mj/submit/blend, /v1/mj/submit/action | Asynchronous |
| Query task | GET | /v1/tasks/{id} | Poll task status |
| Task list | GET | /v1/tasks | Paginated / filterable |
| Cancel task | POST | /v1/tasks/{id}/cancel | Cancels and unfreezes quota |
The model list returned by
GET /v1/modelsis authoritative — the models actually available depend on your account permissions and platform configuration.