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.
| 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 |
Same pricing applies to both text-to-video and image-to-video generation.
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.
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.
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.
import requests, time headers = {"Authorization": "Bearer " + AIMLAPI_KEY} job = requests.post( "https://api.aimlapi.com/v2/video/generations", headers=headers, json={ "model": "blackforestlabs/flux-3-video-t2v", "prompt": "A serene timelapse of clouds over a mountain range" }, ).json() gid = job["id"] while True: res = requests.get(f"https://api.aimlapi.com/v2/video/generations?generation_id={gid}", headers=headers).json() if res.get("status") in ("completed", "error"): break time.sleep(5) print(res["video"]["url"])
const headers = { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }; const job = await (await fetch("https://api.aimlapi.com/v2/video/generations", { method: "POST", headers, body: JSON.stringify({ "model": "blackforestlabs/flux-3-video-t2v", "prompt": "A serene timelapse of clouds over a mountain range" }), })).json(); let res; do { await new Promise((r) => setTimeout(r, 5000)); res = await (await fetch(`https://api.aimlapi.com/v2/video/generations?generation_id=${job.id}`, { headers })).json(); } while (!["completed", "error"].includes(res.status)); console.log(res.video.url);
# submit the generation — the response contains the job "id" curl -X POST 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 serene timelapse of clouds over a mountain range"}' # then poll until status is "completed" — video.url holds the result curl "https://api.aimlapi.com/v2/video/generations?generation_id={id}" -H "Authorization: Bearer $AIMLAPI_KEY"
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Output | |
hd: $0.221/sec · fhd: $0.377/sec. Same pricing for text-to-video and image-to-video modes.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
FLUX 3 Video This page | Text/image to video with synchronized audio | |||
| Video generation | ||||
| Video generation | ||||
| Cinematic video + native audio |
FLUX 3 Video takes text, image as input and returns video.
FLUX 3 Video became available on August 12, 2026.
FLUX 3 Video is priced at $0.221–$0.377 / sec (hd/fhd, variable).
FLUX 3 Video is billed per generation — a fixed charge per output rather than by prompt length.
Yes, FLUX 3 Video accepts image input as well as a text prompt.
FLUX 3 Video was built by Black Forest Labs.
Use blackforestlabs/flux-3-video-t2v as the model id on AI/ML API.
Yes. FLUX 3 Video is served through AI/ML API, so the same key and endpoint format used for other models applies.
Yes, FLUX 3 Video produces clips with a synchronized audio track.
FLUX 3 Video can generate clips ranging from 5 to 20 seconds long.
FLUX 3 Video supports HD and Full HD (FHD) output resolutions.
