API reference

{
  "id": "cmpl-…",
  "object": "chat.completion",
  "model": "<model>",
  "choices": [{
    "index": 0,
    "message": { "role": "assistant", "content": "…" },
    "finish_reason": "stop"
  }],
  "usage": { "prompt_tokens": N, "completion_tokens": N, "total_tokens": N },
  "x_openalchemy": {
    "request_id": "req_…",
    "tier": "s",
    "worker_id": "…",
    "engine_latency_ms": …,
    "usage": { "input_tokens": N, "output_tokens": N, "cost": "0.0008" }
  }
}

// Same shape as /v1/chat/completions.
// x_openalchemy.usage.image_tokens is the per-request image token total.

{
  "object": "list",
  "data": [
    { "object": "embedding", "embedding": [0.0123, -0.045, …], "index": 0 },
    …
  ],
  "model": "<model>",
  "usage": { "prompt_tokens": N, "total_tokens": N },
  "x_openalchemy": { "usage": { "input_tokens": N, "cost": "…" } }
}

{
  "results": [
    { "index": 2, "relevance_score": 0.97 },
    { "index": 0, "relevance_score": 0.81 },
    …
  ],
  "x_openalchemy": {
    "usage": {
      "query_tokens": Q,
      "document_tokens": Σ,
      "total_tokens": Q + Σ,
      "cost": "…"
    }
  }
}

// json:
{ "text": "…transcript…" }

// verbose_json (adds duration + segments):
{ "text": "…", "duration": 12.34, "language": "en", "segments": [ … ] }

// srt / vtt: plain text subtitle file in the matching format.

// Body is binary audio (Content-Type: audio/wav).
// Inspect the response headers:
//   X-Openalchemy-Request-Id
//   X-Openalchemy-Audio-Seconds
//   X-Openalchemy-Cost
//   X-Engine-Request-Id   (pass to /v1/audio/speech/cancel)

// 202 Accepted (empty body)

// GET /v1/audio/voices
{ "data": [
  { "id": "en_alice", "name": "en_alice", "kind": "builtin", "language": "en" },
  { "id": "my_voice", "name": "my_voice", "kind": "cloned",  "language": "ja" }
] }

// POST /v1/audio/voices
{ "id": "my_voice", "name": "my_voice", "kind": "cloned", "language": "ja", "status": "ready" }

// embed → audio bytes; headers:
//   X-OpenAlchemy-Request-Id, X-OpenAlchemy-Cost,
//   X-Watermark-Message, X-Audio-Seconds

// detect →
{ "watermarked": true, "confidence": 0.98, "message": 4242,
  "x_openalchemy": { "request_id": "req_…", "worker_id": "…",
                     "usage": { "audio_seconds": 12, "cost": "…" } } }

{
  "created": 1713833628,
  "data": [{ "b64_json": "<base64 PNG>" }],
  "x_openalchemy": {
    "request_id": "…", "worker_id": "…", "provider": "local",
    "usage": { "images": 1, "cost": "…" }
  }
}

{
  "created": 1713833628,
  "data": [{ "b64_json": "<base64 PNG>" }],
  "x_openalchemy": {
    "request_id": "…", "worker_id": "…", "provider": "local",
    "usage": { "images": 1, "cost": "…" }
  }
}

// POST /v1/videos → 202
{ "id": "video_…", "object": "video", "status": "queued", "model": "minimax-h3",
  "mode": "t2v", "duration": 5, "resolution": "768P", "estimated_credits": "…" }

// GET /v1/videos/{id}
{ "id": "video_…", "object": "video",
  "status": "running",      // queued | running | uploading | succeeded | failed | cancelled
  "stage": "rendering",     // queued | evicting | uploading_frames | rendering | decoding | storing; null once finished
  "progress": 37,           // sampling percent 0–100 (0 until sampling starts, 100 when succeeded)
  "credits": null,          // settled credits once succeeded
  "output": null,           // when succeeded:
  //  { "mime_type": "video/mp4", "duration": 5, "width": 1344, "height": 768, "fps": 24,
  //    "has_audio": true, "bytes": 2400000, "seed": 7, "expires_at": 1760600000,
  //    "url": "https://…signed…", "url_expires_in": 900 }
  "error": null }           // { "code", "message" } when failed / cancelled

// GET /v1/videos?limit=20&after=video_…&status=succeeded
{ "object": "list", "data": [ /* same shape as GET /v1/videos/{id} */ ],
  "has_more": true, "first_id": "video_…", "last_id": "video_…" }

// GET /v1/videos/availability?model=minimax-h3
{ "object": "video.availability", "model": "minimax-h3",
  "available": true, "workers_online": 2, "workers_free": 1, "queue_depth": 0 }

{
  "text": "…full recognised text…",
  // PaddleOCR — per-line text, confidence and box:
  "lines": [ { "text": "…", "score": 0.99, "box": [[x0,y0],[x1,y1],[x2,y2],[x3,y3]] } ],
  "page_count": 1,
  // PDFs — one entry per page:
  "pages": [ { "page_num": 1, "text": "…" } ],
  "x_openalchemy": { "request_id": "req_…", "worker_id": "…", "usage": { "pages": 1, "cost": "…" } }
}

{
  "model": "segformer-b2-clothes",
  "width": 1000, "height": 1500,
  // label: Dress | Upper-clothes | Skirt | Pants | Bag | Shoes | Hat | Scarf | Belt
  "garments": [
    { "label": "Upper-clothes", "x": 473.2, "y": 739.5, "x_norm": 0.4732, "y_norm": 0.493,
      "area_ratio": 0.0417, "bbox": [376.3, 534.7, 578.3, 931.6] }
  ],
  "x_openalchemy": { "request_id": "req_…", "worker_id": "…", "usage": { "images": 1, "cost": "…" } }
}