Error

A valid request URL is required to generate request examples

{
  "stream_id": "<string>",
  "webrtc": {
    "type": "answer",
    "sdp": "<string>"
  },
  "lease": {},
  "turn_servers": [
    {}
  ],
  "livekit": {}
}

{
  "error": "<string>",
  "request_id": "<string>",
  "details": null
}

{
  "error": "<string>",
  "request_id": "<string>",
  "details": null
}

{
  "error": "<string>",
  "request_id": "<string>",
  "details": null
}

{
  "error": "<string>",
  "request_id": "<string>",
  "details": null
}

{
  "error": "<string>",
  "request_id": "<string>",
  "details": null
}

{
  "error": "<string>",
  "request_id": "<string>",
  "details": null
}

Streams

Create stream

Create a new video inference stream. Returns connection details for the chosen transport.

Workflow: Create stream → connect video source → receive results on WebSocket → send keepalives → close when done.

Transport options:

Native (default, recommended): Omit source. Response includes livekit.url and livekit.token for publishing video.
WebRTC: Set source.type: 'webrtc' with an SDP offer. Response includes webrtc answer and turn_servers.
LiveKit: Set source.type: 'livekit' with your room URL and token.

Processing modes:

Clip mode: Send target_fps, clip_length_seconds, delay_seconds for temporal analysis (motion, actions).
Frame mode: Send interval_seconds for static analysis (OCR, object detection).

Limits: 5 concurrent streams per API key. Requires credits.

POST

streams

Error

A valid request URL is required to generate request examples

{
  "stream_id": "<string>",
  "webrtc": {
    "type": "answer",
    "sdp": "<string>"
  },
  "lease": {},
  "turn_servers": [
    {}
  ],
  "livekit": {}
}

{
  "error": "<string>",
  "request_id": "<string>",
  "details": null
}

{
  "error": "<string>",
  "request_id": "<string>",
  "details": null
}

{
  "error": "<string>",
  "request_id": "<string>",
  "details": null
}

{
  "error": "<string>",
  "request_id": "<string>",
  "details": null
}

{
  "error": "<string>",
  "request_id": "<string>",
  "details": null
}

{
  "error": "<string>",
  "request_id": "<string>",
  "details": null
}

The v0.2 API is deprecated. New integrations should use v1.

Authorizations

Authorization

string

header

required

Provide your API key in the Authorization header as 'Bearer <api_key>'

Body

application/json

Create a new video inference stream.

Minimal example (frame mode, native transport):

{
  "processing": { "interval_seconds": 2.0 },
  "inference": { "prompt": "Describe what you see", "model": "Qwen/Qwen3.5-9B" }
}

processing

ClipProcessingConfig · object

required

Clip mode processing config. Samples frames into short video clips for temporal analysis (motion, actions, events).

Provide target_fps directly, or the legacy fps + sampling_ratio pair (not both).

ClipProcessingConfig
FrameProcessingConfig

Show child attributes

inference

StreamInferenceConfig · object

required

What the AI model should do with the video.

Show child attributes

source

WebRTCSourceConfig · object

Legacy WebRTC source. Send an SDP offer and receive an SDP answer in the response.

WebRTCSourceConfig
LiveKitSourceConfig
NativeSourceConfig

Show child attributes

webrtc

WebRtcOffer · object | null

(Legacy) WebRTC offer. Use source instead.

Show child attributes

mode

enum<string> | null

Processing mode. Auto-detected from processing config if omitted. 'clip' for video clips, 'frame' for single images.

Available options:

clip,

frame

client

StreamClientMeta · object | null

Optional client metadata for request tracking.

Show child attributes

Response

Stream created. Use stream_id for all subsequent operations.

Returned after successfully creating a stream. Contains connection details specific to the chosen transport.

stream_id

string

required

Unique stream identifier. Use this for keepalive, close, prompt update, and WebSocket connection.

webrtc

WebRtcAnswer · object | null

SDP answer for WebRTC sources. Null for native/livekit sources.

Show child attributes

lease

Lease · object | null

Stream lease info including ttl_seconds. Send keepalives before TTL expires.

turn_servers

Turn Servers · object[] | null

TURN server credentials for WebRTC sources. Null for native/livekit sources.

Show child attributes

livekit

Livekit · object | null

LiveKit connection details (url + token) for native sources. Connect to this room to publish video.

Show child attributes