FLUX 3 Video API
Black Forest Labs' multimodal video model with native synchronized audio. Text-to-video, keyframes (1-10 images) and continuation of an existing clip, 5-20 seconds at 720p/1080p, with a low-cost draft mode.
- Text to video
- Image to video
Starting at
$0.06
per second of output
Playground
Input
Scene description: subject, action, camera movement, dialogue and sound
Keyframes for image-to-video, in playback order. One image is the start frame, two are start + end, three or more are spread evenly across the clip
Source video (mp4) to continue. Continuation is billed at a higher per-second rate and cannot be combined with imageUrls
Runs are charged to your balance.
Output
Output will appear here.
Pricing
| Option | Price per second |
|---|---|
| Draft: yes · Mode: generate · Resolution: 720p | $0.06 |
| Draft: yes · Mode: extend · Resolution: 720p | $0.12 |
| Draft: no · Mode: generate · Resolution: 720p | $0.17 |
| Draft: no · Mode: generate · Resolution: 1080p | $0.29 |
| Draft: no · Mode: extend · Resolution: 720p | $0.41 |
| Draft: no · Mode: extend · Resolution: 1080p | $0.53 |
Quick start
Full API reference →1curl -X POST https://api.api-stock.com/api/v1/generation/create \2 -H "Authorization: Bearer $API_STOCK_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "flux-3-video",6 "input": {7 "prompt": "A cinematic shot of a city at dusk",8 "resolution": "720p",9 "duration": 5,10 "aspectRatio": "auto",11 "draft": false,12 "safetyTolerance": 213 }14 }'
Parameters
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Scene description: subject, action, camera movement, dialogue and sound |
resolution | string | No | 720p | Video resolution (affects pricing). Draft mode supports 720p onlyOne of: 720p, 1080p |
duration | number | No | 5 | Video duration in seconds (5-20). Billed per second |
aspectRatio | string | No | auto | Video aspect ratio. `auto` lets the model choose from the prompt and input framesOne of: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16 |
imageUrls | string[] | No | — | Keyframes for image-to-video, in playback order. One image is the start frame, two are start + end, three or more are spread evenly across the clip |
videoUrl | string | No | — | Source video (mp4) to continue. Continuation is billed at a higher per-second rate and cannot be combined with imageUrls |
draft | boolean | No | false | Draft mode: a fast, low-quality 720p preview at about a third of the price |
safetyTolerance | number | No | 2 | Moderation tolerance from 0 (strictest) to 4 (most permissive) |
Frequently asked questions
How much does FLUX 3 Video cost?
FLUX 3 Video starts at $0.06 per second of output through the API Stock API. You pay per use from a single prepaid balance — there is no subscription — and the final price scales with parameters such as resolution or duration.
How do I get an API key for FLUX 3 Video?
Sign up for API Stock, top up your balance by any amount and create an API key in the dashboard — it takes a couple of minutes and needs no contract. The same key works with every model in the catalog, so there is no separate key to obtain for FLUX 3 Video.
How do I call the FLUX 3 Video API?
Send a POST request to https://api.api-stock.com/api/v1/generation/create with your API key and the model id "flux-3-video". The call returns a task id you poll, or a webhook callback when the result is ready. A ready-to-run example is in the quick start above.
What input parameters does FLUX 3 Video accept?
FLUX 3 Video accepts 8 input parameters, including the required field(s) prompt. Their types, defaults and allowed values are listed in the parameters table above.
What happens if a FLUX 3 Video request fails?
API Stock automatically retries the request on a reserve provider. If every provider fails, the charge is refunded to your balance.
Can I use FLUX 3 Video with the same API key as other models?
Yes. Every model on API Stock — video, image, music and chat — shares one API key and one prepaid balance, so you can switch to FLUX 3 Video without new credentials.
Other Video models
- Seedance 2.0 MiniByteDance$0.016/ second
- Grok Imagine 1.5 VideoxAI$0.016/ second
- MiniMax H3MiniMax$0.016/ second
- PixVerse V6PixVerse$0.024/ generation
- Wan 3.0 VideoAlibaba$0.05/ second
- Seedance 2.0 FastByteDance$0.06/ second
- Seedance 1.5 ProByteDance$0.068/ generation
- Kling 3.0 Motion ControlKling$0.07/ second
- Kling 3.0Kling$0.09/ second
Guides
- Text to videoWhich text-to-video model fits the shot you have in mind, prompts that actually work, and the full API run from create to finished file.9 min read
- Image to videoTurning a still into a shot — which model to animate it with, first and last frame control, motion transfer, and the prompts that keep the subject intact.8 min read
- Going to productionKey handling, webhooks over polling, idempotency, terminal states, retry policy by error code, balance monitoring, rate limits and media storage.10 min read