Get API Key Get API
Docs

FLUX 3 Video Generation

- Asynchronous processing mode, returns a task ID for subsequent queries

  • Unified entry: text-to-video / image-to-video / video continuation / draft two-step
  • Output H.264 + AAC with synced audio, duration 5~20 seconds
  • Resolution hd / fhd, seven aspect ratios

Request example

curl --request POST \
  --url https://api.openveer.com/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "flux-3-video",
    "prompt": "An orange cat jumps onto a sunlit wooden table, its tail brushes a glass that wobbles but does not fall. Cinematic, shallow depth of field.",
    "duration": 5,
    "resolution": "hd",
    "aspect_ratio": "16:9"
  }'

Response example

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01J9HA7JPQ9A0Z6JZ3V8M9W6PZ"
    }
  ]
}

Authorization

Authorization string

All endpoints require Bearer Token authentication

Get your API Key from the API Key Management Page:

Authorization: Bearer YOUR_API_KEY

Generation Modes

flux-3-video is a unified entry: mode is inferred from fields, or set explicitly with mode.

Mode Trigger Notes
Text-to-video (t2v) prompt only Pure text
Image-to-video (i2v) image_urls Keyframes; see below
Video continuation (v2v) video_url / video_urls Higher unit price; if both image and video are set, continuation wins
Draft → final draft:true or draft_from_task_id Cheap preview, then full-price final

mode values: t2v / i2v / v2v / draft_enhance, or official spellings text-to-video / image-continuation / video-continuation. Explicit mode has highest priority.

Image-to-video keyframe semantics

Order in image_urls is semantic — do not sort or dedupe:

Count Meaning
1 Start frame
2 First start, second end frame
3\~10 First start, last end, middle frames evenly spaced (set duration explicitly)

Request Parameters

model string

Fixed value: flux-3-video

nsfw_check boolean

Whether to run content moderation before submitting the video task.

  • true: use omni-moderation-latest to review prompts and input images
  • false or omitted: do not send a moderation request, adding no moderation cost or latency (default)
prompt string

Prompt. Must not be sent when using draft_from_task_id (rejected if present).

duration integer

Duration in seconds, integer 5\~20, default 5

Warning



duration: "auto" is not supported (billing needs a fixed second count). Omit, "auto", or non-integers → treated as 5 seconds without error and without adaptive length.

Note



For video continuation, the delivered duration may be shorter than requested (e.g. request 5s, get 4s). The request is pre-charged for the requested seconds and the difference is refunded after completion; final amount is query cost. Text/image-to-video do not show this gap.

resolution string

Resolution

  • hd (default; also accepts 720p)
  • fhd (also accepts 1080p)

Measured: hd \~1280×704 at 16:9; fhd \~1920×1088.

Warning



Draft mode (draft:true) only allows hd.

aspect_ratio string

Aspect ratio

Options: 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16, or auto (default; chosen automatically from the prompt and assets)

image_urls string[]

Image-to-video keyframes, 1\~10, public http(s) URL or base64

video_url string

Input video for continuation (mp4, public URL or base64)

video_urls string[]

Same as video_url; uses the first item (compat)

audio boolean

Generate synced audio, default true. false yields silent video (no discount)

draft boolean

Draft mode: \~1/3 price low-quality preview; only with resolution: hd

draft_from_task_id string

Draft → final: ID of your successful draft task

  • Only resolution may change; prompt, duration, images, video cannot
  • Charged at full final price; draft fee is not credited
  • Mutually exclusive with draft:true
safety_tolerance integer

Moderation tolerance 0\~4, default 2 (higher = more permissive)

Note



Do not confuse with FLUX.2 images (0~~5) or Kontext (0~~6).

mode string

Explicit mode (optional); see Generation Modes

Draft Mode

Two-step workflow when iterating is expensive:

Step 1  draft:true            → ~1/3 price low-quality preview
Step 2  draft_from_task_id    → full-price final matching the draft look

Create draft

{
  "model": "flux-3-video",
  "prompt": "An orange cat jumps onto a sunlit wooden table",
  "duration": 5,
  "draft": true
}

Draft to final

{
  "model": "flux-3-video",
  "draft_from_task_id": "task_01K_DRAFT...",
  "resolution": "fhd"
}

Draft-to-final re-renders at full quality using the draft’s saved params (mode / prompt / seed / assets). Continuation drafts finalize at continuation final rates.

Request Examples

Text-to-video (portrait)

{
  "model": "flux-3-video",
  "prompt": "Rainy Tokyo street at night, neon in puddles, a person walks with an umbrella.",
  "duration": 8,
  "resolution": "fhd",
  "aspect_ratio": "9:16"
}

Image-to-video (start + end frame)

{
  "model": "flux-3-video",
  "prompt": "Slow push-in as a flower opens from bud to bloom",
  "image_urls": [
    "https://example.com/bud.jpg",
    "https://example.com/bloom.jpg"
  ],
  "duration": 5
}

Video continuation

{
  "model": "flux-3-video",
  "prompt": "Camera keeps following as the lead turns toward a distant lighthouse",
  "video_url": "https://example.com/clip.mp4",
  "duration": 5
}

Silent video

{
  "model": "flux-3-video",
  "prompt": "...",
  "audio": false
}

Constraints

Limit Value
Duration Integer 5\~20 (auto unsupported; 21 is rejected)
Keyframes 1\~10
Resolution hd / fhd only; draft only hd
Aspect ratio Seven options or auto
safety_tolerance 0\~4

Common submit errors (usually not charged)

Case Notes
Missing prompt Required except draft enhance
Invalid resolution / aspect_ratio / duration Out of range
Keyframes > 10 Cap exceeded
Explicit i2v without images / v2v without video Mode/asset mismatch
draft:true + fhd Draft is hd only
Invalid / non-draft / unfinished draft_from_task_id Finalization preconditions
Changing prompt / duration on finalize Only resolution allowed
Both draft and draft_from_task_id Mutually exclusive

Moderation failures end as failed with full refund.

Capability Coverage

Capability Status
t2v / i2v / v2v ✅ Auto or explicit mode
Draft / draft enhance ✅ draft / draft_from_task_id
Synced audio ✅ On by default; audio:false off (no discount)
Timed keyframes [seconds, image] ❌ Evenly spaced keyframe array only
duration: "auto" ❌ Not supported

Response

code integer

Status code; 200 on success

data array
Response data array
status string

Task status; submitted on create

task_id string

Task ID for polling

Note

Query results

Video generation is async. Poll Get Task Status.

Recommended interval 5\~10 seconds; client timeout 15 minutes (20s fhd is slower). Measured \~60s for t2v + hd + 5s.

On success use result.videos[0].url; assets are mirrored to the platform CDN. cost is the final charge. Failures are fully refunded.

This documentation is built and hosted on Mintlify, a developer documentation platform.