POST https://studio.dataeyes.ai/flux/v1/flux-3-video
GET https://studio.dataeyes.ai/flux/v1/get_result?id={id}Authorization: Bearer sk-xxx and the BFL-style x-key: sk-xxx header work.{
"id": "d969c847-daef-4ba8-857c-ecda7c4977f1",
"polling_url": "https://studio.dataeyes.ai/flux/v1/get_result?id=d969c847-daef-4ba8-857c-ecda7c4977f1"
}{ "id": "d969c847-daef-4ba8-857c-ecda7c4977f1", "status": "Generating" }{
"id": "d969c847-daef-4ba8-857c-ecda7c4977f1",
"status": "Ready",
"result": {
"sample": "https://storage.fonedis.cc/…/content.mp4?Expires=…"
}
}{
"id": "340a951d-1a67-4eed-9dbc-a88b4588eeed",
"status": "Error",
"details": "background worker died while task was queued (heartbeat lost)"
}status | Meaning |
|---|---|
Pending | Queued |
Generating | Generating |
Ready | Done; the video URL is in result.sample |
Error | Failed; the reason is in details |
result.sample is a signed temporary link (it expired after about 2 hours in our tests), so download and store the video as soon as it is ready.mode. Each mode requires different fields:mode | Use | Required fields | duration range |
|---|---|---|---|
t2v | Text-to-video | prompt | 5–20 seconds |
i2v | Image-to-video (keyframes) | prompt, keyframes | 5–20 seconds |
v2v | Video continuation | prompt, start_video | 5–15 seconds |
keyframes is an array of [seconds, image] pairs, 1 to 10 of them; each time must be between 0 and duration. One pair [0, image] uses the image as the opening frame; [0, image1] and [5, image2] pin the first and last frames. Use public image URLs.| Parameter | Type | Required | Description |
|---|---|---|---|
mode | string | Yes | t2v, i2v, or v2v |
prompt | string | Yes | Describe the shot, action, lighting, and sound; put any spoken lines in quotes |
duration | integer | Yes | Length in whole seconds: 5–20 for t2v and i2v, 5–15 for v2v |
resolution | string | No | hd (default), fhd, qhd, uhd; 720p, 1080p, 2k, 4k are also accepted. See Resolution below |
aspect_ratio | string | No | auto (default, chosen from the prompt and references), 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21 |
generate_audio | boolean | No | Generate synchronized sound, default true; false produces a silent video |
keyframes | array | Required for i2v | Array of [seconds, image URL] pairs, 1 to 10 |
start_video | string | Required for v2v | Public mp4 URL of the clip to continue |
safety_tolerance | integer | No | Moderation tolerance, 0 (strictest) to 4 |
draft or mode: "draft_enhance" returns 400.hd with 16:9 produced 1280×704, 5.04 seconds, with an audio track. Each class maps to a billing tier:resolution | Equivalent | Billing tier |
|---|---|---|
hd | 720p | 720p |
fhd | 1080p | 1080p |
qhd | 2k | 2k |
uhd | 4k | 4k |
v2v) uses the "with video input" unit price. See flux-3-video in the Model Hub for prices, and Usage logs for charges. The amount is pre-deducted from the request parameters at submission; requests that fail parameter validation are not charged.