GET

/v1/schemas/openrouter/video/videos%2Fopenai%2Fsora-2-pro

kind inputactivity videohash 672cc43c…extracted Sep 30, 2026version currentsource upstream spec ↗

Request body

16 properties · 1 required · 6 $defs
propertytypedescriptionconstraints
model*enumModel id (fixed for this model-constrained schema)openai/sora-2-pro
aspect_ratioenumAspect ratio of the generated video16:9 | 9:16
callback_urlstringURL to receive a webhook notification when the video generation job completes. Overrides the workspace-level default callback URL if set. Must be HTTPS.format: uri
creativityintegerCreativity level for video upscaling models only. This parameter is not supported by video generation models.
durationenumDuration of the generated video in seconds4 | 8 | 12 | 16 | 20 · n ≥ 1
generate_audiobooleanWhether to generate audio alongside the video. Defaults to the endpoint's generate_audio capability flag, false if not set.
input_referencesInputReference[]Reference assets to guide video generation. Accepts image, audio, and video references. Audio and video references are only honored by providers that support them (including BytePlus Seedance generation 2 and newer); other providers use image references and ig…
previous_job_idstringID of a completed video job to edit or extend, as returned by the submit response. The new job runs on the same model and endpoint that produced the previous one. Only models that support continuation accept this field.
promptstringText prompt describing the video to generate. Optional for models that support generating a video from image input alone; required by all other models.
providerobjectProvider-specific passthrough configuration Passthrough parameters allowed for this model: quality, style.
resolutionenumResolution of the generated video720p | 1080p
session_idstringA unique identifier for grouping related requests (e.g., a conversation or agent workflow). Used for observability grouping in Broadcast and private logging; never sent to the provider. If provided in both the request body and the x-session-id header, the body…length ≤ 256
sizeenumExact pixel dimensions of the generated video in "WIDTHxHEIGHT" format (e.g. "1280x720"). Interchangeable with resolution + aspect_ratio.1280x720 | 1080x1920 | 1920x1080 | 720x1280
traceTraceConfigMetadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations.
upscale_factornumberUpscale factor for video upscaling models only. This parameter is not supported by video generation models.n ≥ 0
userstringA unique identifier representing your end-user. Forwarded to Broadcast and private logging as the end-user id; never sent to the provider.length ≤ 256

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"openrouter","endpointId":"videos/openai/sora-2-pro","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}