Text to video
Elo with audio · text-to-video arena
FLUX 3 Video overview
FLUX 3 Video specs
- Model ID
blackforestlabs/flux-3-video-t2v- Developer
- Black Forest Labs
- Input
- Text, Image
- Output
- Video
- Endpoint
POST https://api.aimlapi.com/v2/video/generations
What Is FLUX 3 Video API?
FLUX 3 Video by Black Forest Labs generates 5–20 second video clips either from a text prompt or from an image, animating a single keyframe, or interpolating between a first and a last frame, in hd or fhd, with a synchronized audio track.
Technical Reference
| Developer | Black Forest Labs |
|---|---|
| Model IDs | blackforestlabs/flux-3-video-t2v (text-to-video), blackforestlabs/flux-3-video-i2v (image-to-video) |
| Supported inputs | Text, Image |
| Output | Video with synchronized audio |
| Resolutions | hd, fhd |
| Duration | 5–20 seconds |
What FLUX 3 Video Brings to the Table
Dual generation modes
Generate from a text prompt alone, or from a reference image, animating a single keyframe, or interpolating between a first and a last frame for controlled motion.
Synchronized audio
Every clip is generated with a synchronized audio track, rather than requiring a separate audio generation step.
hd and fhd output
Choose standard hd or higher-fidelity fhd resolution, with fhd priced higher per second.
Where FLUX 3 Video Makes the Most Sense
Short-form video generation
Create clips for social, ads, and product demos from text or image prompts.
Keyframe animation
Animate a single image, or interpolate between a first and last frame for controlled motion.
Use cases
Creating advertisements is a documented use case for FLUX 3 Video, which is described as handling simple prompts and detailed, multi-element scenes for coherent video output.
Product concept videos are also explicitly mentioned as a supported use case, with the model described as turning written descriptions into video for product-focused scenes.
Character sequences are another stated use case, including scenes built around recurring characters or sequential action.
Entirely fictional worlds are likewise called out as a use case, with the model described as generating coherent video from descriptions of imagined settings.
FLUX 3 Video benchmarks by 
Artificial Analysis
Human-preference results for FLUX 3 Video in text to video and silent video, next to models available on AI/ML API. Data retrieved Nov 3, 2026.
Silent video
Elo · silent text-to-video arena
Models on AI/ML API
Arena results for models you can call with the same API key.
Text to video
Blind votes on clips with generated sound, made from a text prompt. FLUX 3 Video ranks #8 of 31.
Silent video
The same text-to-video task, judged as silent video. FLUX 3 Video ranks #10 of 36.
FLUX 3 Video API pricing
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.17 | per second |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
FLUX 3 Video vs other video models: prices
AI/ML API rates for 5 models, per second.
| Model | Per second |
|---|---|
 FLUX 3 Video | $0.17 |
| FLUX 3 Video Draft | $0.06 |
| FLUX 3 Video Draft Video to Video | $0.12 |
 Kling Video O1 Video-to-Video Reference | $0.168 |
| FLUX 3 Video Video to Video | $0.41 |
How to use the FLUX 3 Video API
View docs
Build with your agent
Give your agent the model details, code and documentation.
Paste it into your coding agent to build the integration.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v2/video/generations' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "blackforestlabs/flux-3-video-t2v",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "blackforestlabs/flux-3-video-t2v",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}
response = requests.post("https://api.aimlapi.com/v2/video/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v2/video/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "blackforestlabs/flux-3-video-t2v",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());The request returns a generation id. Poll GET https://api.aimlapi.com/v2/video/generations?generation_id=<id> until the status is completed.
Models similar to FLUX 3 Video
FLUX 3 Video FAQ
What inputs and outputs does FLUX 3 Video support?
FLUX 3 Video takes text, image as input and returns video.
When was FLUX 3 Video released?
FLUX 3 Video became available on August 12, 2026.
How much does FLUX 3 Video cost?
FLUX 3 Video costs $0.17 per second on AI/ML API, billed as you go with no subscription.
How is FLUX 3 Video billed?
FLUX 3 Video costs $0.17 per second on AI/ML API, billed as you go with no subscription.
Can FLUX 3 Video take an existing image as input?
Yes, FLUX 3 Video accepts image input as well as a text prompt.
Who created FLUX 3 Video?
FLUX 3 Video was built by Black Forest Labs.
How do I call FLUX 3 Video on AI/ML API?
Use blackforestlabs/flux-3-video-t2v as the model id on AI/ML API.
Is FLUX 3 Video available through a single API key?
Yes. FLUX 3 Video is served through AI/ML API, so the same key and endpoint format used for other models applies.
Does FLUX 3 Video include sound with its clips?
Yes, FLUX 3 Video produces clips with a synchronized audio track.
What is the maximum length of a video clip from FLUX 3 Video?
FLUX 3 Video can generate clips ranging from 5 to 20 seconds long.