DataEyesAI
Official SiteConsoleDocs HomeGetting StartedDeveloper ToolsAI Models API
Terms & Policies
Official SiteConsoleDocs HomeGetting StartedDeveloper ToolsAI Models API
Terms & Policies
  1. Video Model
  • API Overview
  • Chat Completions
  • Responses
  • Messages (Claude)
  • Gemini (generateContent)
  • Embeddings
  • Image Models
    • Images
    • Gemini Image Generation
    • Grok Imagine Image
  • Midjourney format
    • Midjourney API Reference
    • Task query interface
    • Upload image
    • Get seed (Seed)
    • Submit Imagine task
    • Query tasks based on ID list
    • FaceSwap
    • Execute Action operation
    • /mj/submit/blend
    • Submit Describe task
    • Submit Modal
    • Refresh link
    • Edit image
    • Query task status by task ID
    • Get the seed of the task image
  • Video Model
    • FLUX Video Generation (flux-3-video)
    • Grok Video Generation
      • 00-Overview
      • 01-Text-to-Video
      • 02-Image-to-Video
      • 03-Reference-to-Video
      • 04-Video-Editing
      • 05-Video-Extension
    • Seedance Video Generation
      • 00-Overview
      • 01-Create-Video-Generation-Task
      • 02-Query-Video-Generation-Task
      • 03-Query-Video-Generation-Task-List
      • 04-Cancel-or-Delete-Task
      • Seedance Private Asset Library API Documentation
    • MiniMax-H3 Video Generation
      • 00-Overview
      • 01-Create-Video-Generation
      • 02-Create-Video-Regeneration
      • 03-Create-H3-Context-IR
      • 04-Query-Task
      • 05-List-Tasks
      • 06-Cancel-or-Delete-Task
    • Hailuo Video Generation
      • 00-Overview
      • 01-Text-to-Video-T2V
      • 02-Image-to-Video-I2V
      • 03-First-Last-Frame-FL2V
      • 04-Subject-Reference-S2V
      • 05-Query-Task-Status
      • 06-Video-Download
      • 99-Appendix-Camera-Movement-and-Webhooks
    • Jimeng Video Generation
      • 00-Overview
      • 01-3.0-Pro-Video-Generation
      • 02-720P-Text-to-Video
      • 03-720P-Image-to-Video-First-Frame
      • 04-720P-Image-to-Video-Start-End-Frame
      • 05-720P-Image-to-Video-Camera
      • 06-1080P-Text-to-Video
      • 07-1080P-Image-to-Video-First-Frame
      • 08-1080P-Image-to-Video-Start-End-Frame
      • 09-Error-Codes
    • Kling AI Video Generation
      • 00-Overview
      • 01-Text-to-Video
      • 02-Image-to-Video
      • 03-Omni-Video
      • 04-Multi-Image-to-Video
      • 05-Motion-Control
      • 06-Multi-Elements
      • 07-Video-Extension
      • 08-Lip-Sync
      • 09-Avatar
      • 10-Text-to-Audio
      • 11-Video-to-Audio
      • 12-TTS
      • 13-Custom-Voices
      • 14-Image-Recognition
      • 15-Element-Management
      • 16-Video-Effects
      • 17-Kling-4.0-Video-Generation
    • Vidu Video Generation
      • 00-Overview
      • 01-Text-to-Video
      • 02-Image-to-Video
      • 03-Reference-to-Video
      • 04-Start-End-Frame
      • 05-Multi-Frame
      • 06-Scene-Template
      • 07-Template-Story
      • 08-Query-Tasks
    • HappyHorse
      • HappyHorse Text-to-Video
      • HappyHorse Image-to-Video (First Frame)
      • HappyHorse Reference-to-Video
      • HappyHorse Video Editing
    • Wan Video Generation
      • 00-Overview.md
      • 01-Text-to-Video
      • 02-Image-to-Video
      • 03-Reference-to-Video
      • 04-Video-Editing
      • 05-First-Last-Frame-to-Video
      • 06-Motion-Transfer-and-Character-Swap
      • 07-Digital-Human-Video
      • 08-VACE-Video-Editing
      • 09-Query-Task
  • Audio API
    • Audio API
    • Gemini TTS API
    • Google DeepMind Lyria API
    • Elevenlabs Speech to Text API Reference
  1. Video Model

FLUX Video Generation (flux-3-video)

FLUX 3 video model from Black Forest Labs: text-to-video, image-to-video (keyframes), and video continuation, with synchronized dialogue, sound effects, and ambience. The API uses the official BFL format and runs asynchronously: submit a task, poll for the result, then download the video.
POST https://studio.dataeyes.ai/flux/v1/flux-3-video
GET  https://studio.dataeyes.ai/flux/v1/get_result?id={id}
Authenticate with your model API key. Both Authorization: Bearer sk-xxx and the BFL-style x-key: sk-xxx header work.

Quick example#

cURL
Python
On success, the task ID and polling URL are returned immediately:
{
  "id": "d969c847-daef-4ba8-857c-ecda7c4977f1",
  "polling_url": "https://studio.dataeyes.ai/flux/v1/get_result?id=d969c847-daef-4ba8-857c-ecda7c4977f1"
}

Get the result#

In progress:
{ "id": "d969c847-daef-4ba8-857c-ecda7c4977f1", "status": "Generating" }
Finished:
{
  "id": "d969c847-daef-4ba8-857c-ecda7c4977f1",
  "status": "Ready",
  "result": {
    "sample": "https://storage.fonedis.cc/…/content.mp4?Expires=…"
  }
}
Failed:
{
  "id": "340a951d-1a67-4eed-9dbc-a88b4588eeed",
  "status": "Error",
  "details": "background worker died while task was queued (heartbeat lost)"
}
statusMeaning
PendingQueued
GeneratingGenerating
ReadyDone; the video URL is in result.sample
ErrorFailed; the reason is in details
In our tests, a 5-second hd video took about 2–3 minutes from submission to completion. Poll about every 10 seconds. 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.

Modes#

Set the mode with mode. Each mode requires different fields:
modeUseRequired fieldsduration range
t2vText-to-videoprompt5–20 seconds
i2vImage-to-video (keyframes)prompt, keyframes5–20 seconds
v2vVideo continuationprompt, start_video5–15 seconds
Image-to-video (i2v)
Video continuation (v2v)
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.

Request parameters#

ParameterTypeRequiredDescription
modestringYest2v, i2v, or v2v
promptstringYesDescribe the shot, action, lighting, and sound; put any spoken lines in quotes
durationintegerYesLength in whole seconds: 5–20 for t2v and i2v, 5–15 for v2v
resolutionstringNohd (default), fhd, qhd, uhd; 720p, 1080p, 2k, 4k are also accepted. See Resolution below
aspect_ratiostringNoauto (default, chosen from the prompt and references), 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21
generate_audiobooleanNoGenerate synchronized sound, default true; false produces a silent video
keyframesarrayRequired for i2vArray of [seconds, image URL] pairs, 1 to 10
start_videostringRequired for v2vPublic mp4 URL of the clip to continue
safety_toleranceintegerNoModeration tolerance, 0 (strictest) to 4
NOTE
BFL draft mode is not supported: sending draft or mode: "draft_enhance" returns 400.

Resolution#

In our tests, hd with 16:9 produced 1280×704, 5.04 seconds, with an audio track. Each class maps to a billing tier:
resolutionEquivalentBilling tier
hd720p720p
fhd1080p1080p
qhd2k2k
uhd4k4k

Billing#

Billed per second of output × the unit price of the resolution tier; video continuation (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.

FAQ#

duration must be an explicit integer
keyframes must contain 1 to 10 [seconds, image] pairs
Calling /v1/videos fails
The video link no longer opens
Previous
Get the seed of the task image
Next
00-Overview