Video generation API

Veo / Google

Google Veo 3.1 — state-of-the-art video generation with Standard, Fast, and Lite tiers.

Provider: Google8 models

Available models

Model key	Display name	Capability	Atlas Cloud slug
`veo_3_1_t2v`	Veo 3.1 T2V	text-to-video	google/veo3.1/text-to-video
`veo_3_1_i2v`	Veo 3.1 I2V	image-to-video	google/veo3.1/image-to-video
`veo_3_1_ref2vid`	Veo 3.1 Ref2Vid	reference-to-video	google/veo3.1/reference-to-video
`veo_3_1_fast_t2v`	Veo 3.1 Fast T2V	text-to-video	google/veo3.1-fast/text-to-video
`veo_3_1_fast_i2v`	Veo 3.1 Fast I2V	image-to-video	google/veo3.1-fast/image-to-video
`veo_3_1_lite_t2v`	Veo 3.1 Lite T2V	text-to-video	google/veo3.1-lite/text-to-video
`veo_3_1_lite_i2v`	Veo 3.1 Lite I2V	image-to-video	google/veo3.1-lite/image-to-video
`veo_3_1_lite_start_end`	Veo 3.1 Lite Start-End	start-end-frame	google/veo3.1-lite/start-end-frame-to-video

Endpoint

POST /api/generate

Request body

Parameter	Type	Required	Description
`modelKey`	string	✓	One of the model keys listed above
`prompt`	string	✓	Text description of the image to generate
`inputUrl`	string		Input image URL (for edit/i2i models)
`aspectRatio`	string		`"1:1"`, `"16:9"`, `"9:16"`, etc.
`imageQuality`	string		`"Low"`, `"Medium"`, `"High"`
`styleRef`	string \| string[]		Style reference image URL(s)
`charRef`	string \| string[]		Character reference image URL(s)
`brandId`	string		Brand DNA ID for brand-consistent generation

Code example

curl -X POST https://api.oyefilmy.com/api/generate \
  -H "Authorization: Bearer of_live_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "modelKey": "veo_3_1_t2v",
    "prompt": "A cinematic timelapse of clouds rolling over a cityscape transitioning from day to night"
  }'

Response

{
  "success": true,
  "predictionId": "pred_abc123...",
  "status": "processing",
  "model": "google/veo3.1/text-to-video",
  "creditCost": 5
}

Veo 3.1 delivers Google's highest quality video. Fast is ~2x faster. Lite is most cost-effective. Start-End mode generates video transitioning between two keyframe images.

← All image models

Back to image generation overview

Webhooks

Receive results automatically