Create video (Omni and Veo formats)
This series supports OpenAI video generation formats (see the link Video generation Sora compatible formats).
This API topic page explains the video formats related to Omni and Veo, as well as the current gateway support status for the native Veo format.
For external use of the current Veo series, please use OpenAI Sora compatibility mode: POST /v1/videos.
The reserved path for Google native mode is: POST /v1beta/models/{model}:predictLongRunning. The current gateway is not yet connected to the native task dispatch pipeline of Veo, so calls using the native [[TERM_1]] request body are not yet supported.
Note: The endpoints supported by the gemini-omni model are the Sora compatible format POST /v1/videos or the Seedance format POST /api/v3/contents/generations/tasks; this page does not support Google native Veo predictLongRunning endpoints.
Authorizations
Use Bearer Token authentication.
Format: Authorization: Bearer sk-xxxxxx
Path Parameters
Veo Model name.
veo3, veo3-fast, veo3-fast-frames, veo3-frames, veo3-pro, veo3-pro-frames, veo3.1, veo3.1-4k, veo3.1-components, veo3.1-fast, veo3.1-pro, veo3.1-pro-4k "veo3.1-fast"
Response
Reserved success response structure. Currently provided for protocol documentation only; actual calls are not supported.
The operation name, used for subsequent status queries.
"models/veo3.1-fast/operations/abc123"
