Veo Video

The Veo series currently provides two integration methods: the OpenAI-compatible /v1/videos route, and the unified video /v1/video/create and /v1/video/query.

OpenAI Format

Use POST /v1/videos to submit, POST /v1/videos/{video_id}/remix to remix, and GET /v1/videos/{task_id} to query. Reference images are expressed through input_reference.

Veo Video Generation

POST /v1/videos, submit Veo tasks in OpenAI style.

Video remix

POST /v1/videos/{video_id}/remix, submit a remix based on an existing video.

Veo Task Query

GET /v1/videos/{task_id}, OpenAI-style video object query.

Current Models (OpenAI Format)

  • veo_3_1
  • veo_3_1-fast
  • veo_3_1-extend (remix)

Unified Video

Use POST /v1/video/create to create a task and GET /v1/video/query?id= to query. Reference images are passed in through the images array.

Create Video

POST /v1/video/create, submit Veo tasks in unified video format.

Query Task

GET /v1/video/query, query status and results by task id.

Common Models (Unified Video)

  • veo3.1-fast-components, etc. The actual available models on the channel shall prevail.

Comparison

ItemOpenAI FormatUnified Video
CreatePOST /v1/videosPOST /v1/video/create
RemixPOST /v1/videos/{video_id}/remix
QueryGET /v1/videos/{task_id}GET /v1/video/query?id=
Reference Imagesinput_referenceimages
Aspect Ratiosize, metadatasize, orientation, aspect_ratio
Durationseconds / durationduration