Skip to content
Black Forest Labs logo

FLUX 3 Video

Text-to-Video • Black Forest Labs

View as MarkdownAgent setup
  • Third-party

FLUX 3 Video is Black Forest Labs' video generation model. It generates video from a text prompt (t2v), animates one or more reference images (i2v), or continues an existing clip (v2v), with synchronized audio, up to fhd resolution, and 5-20 second durations.

Model Info
Terms and Licenselink
More informationlink
PricingView pricing in the Cloudflare dashboard

Usage

const response = await env.AI.run(
  'black-forest-labs/flux-3-video',
  {
    mode: 't2v',
    prompt:
      'A cozy ramen shop on a rainy Tokyo night, steam rising from the broth. Rain patter and quiet kitchen sounds.',
    resolution: 'hd',
    duration: 5,
    generate_audio: true,
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "black-forest-labs/flux-3-video",
  "input": {
    "mode": "t2v",
    "prompt": "A cozy ramen shop on a rainy Tokyo night, steam rising from the broth. Rain patter and quiet kitchen sounds.",
    "resolution": "hd",
    "duration": 5,
    "generate_audio": true
  }
}'
{
  "state": "Completed",
  "result": {
    "video": "https://examples.aig.cloudflare.com/black-forest-labs/flux-3-video/text-to-video.mp4"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}

Parameters

Schema variant
mode
stringrequiredconst: t2v
prompt
stringrequiredminLength: 1Free-form prompt describing the video.
aspect_ratio
stringenum: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16Output aspect ratio. `auto` (default) picks one from the prompt and any references.
resolution
stringenum: hd, fhd`hd` (default) or `fhd` for a higher-resolution result finished by the video upsampler.
generate_audio
booleanGenerate synchronized audio alongside the video. Defaults to true.
safety_tolerance
integerminimum: 0maximum: 4Tolerance for input/output harm moderation, 0 (strictest) to 4. Defaults to 2. Sexual content is capped at level 3 and hate content at level 2 regardless of the requested tolerance; requests with conditioning media are capped at level 2.
draft
booleanGenerate a fast, low-cost preview instead of a final render, at a reduced flat price. Only available at hd resolution.
video
stringformat: uriSigned URL to the generated mp4 (24fps, with audio by default). Expires ~2 hours after ready — download promptly.
draft_cache
stringDraft-mode cache bundle URL, only present for draft: true requests.

API Schemas (Raw)

Input
Output

Was this helpful?