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-draft-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 ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }; const job = await (await fetch("https://api.aimlapi.com/v2/video/generations", { method: "POST", headers, body: JSON.stringify({ "model": "blackforestlabs/flux-3-video-draft-t2v", "prompt": "A serene timelapse of clouds over a mountain range" }), })).json(); let res; do { await new Promise((r) => setTimeout(r, 5000)); res = await (await fetch(`https://api.aimlapi.com/v2/video/generations?generation_id=${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-draft-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 | |
Draft mode is hd-only, no fhd option. Same pricing for text-to-video and image-to-video modes.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
FLUX 3 Video Draft This page | Fast, low-cost previews before full-quality render | |||
| Fast, high-volume video generation | ||||
| Video generation |
FLUX 3 Video Draft takes text, image as input and returns video.
FLUX 3 Video Draft became available on August 12, 2026.
FLUX 3 Video Draft is priced at $0.078 / sec (hd only).
FLUX 3 Video Draft is billed per generation — a fixed charge per output rather than by prompt length.
Yes, FLUX 3 Video Draft accepts image input as well as a text prompt.
FLUX 3 Video Draft was built by Black Forest Labs.
Use blackforestlabs/flux-3-video-draft-t2v as the model id on AI/ML API.
Yes. FLUX 3 Video Draft is served through AI/ML API, so the same key and endpoint format used for other models applies.
FLUX 3 Video Draft only renders in HD; there is no Full HD option in draft mode.
Draft mode lets you preview a text-to-video or image-to-video prompt quickly before committing to a full-quality render.