FLUX 3 Video API
FLUX 3 Video by Black Forest Labs supports text-to-video, image-to-video with 1–10 ordered keyframes, video continuation, and draft enhancement. Generate synchronized audio with 5–20 second HD or FHD output, configurable safety tolerance, and per-second billing.
Service Highlights
- Official Discounts
- Pay-as-you-go
- Fast & Low Latency
Create a video from a prompt
Choose an integer from 5 to 20 seconds.
Generate synchronized native audio with the video.
Generate a lower-cost, low-quality HD draft first, then convert it to the final video with a second request.
Stored on the APIMart CDN
FLUX 3 Video API Pricing
Transparent pricing with no hidden fees. Pay only for what you use.
| Variant | Tier | GoldCurrent price | Platinum | Diamond | Official | Your savings |
|---|---|---|---|---|---|---|
flux-3-video | DRAFT | 0.48Credits(~$0.048)/sec | 0.456Credits(~$0.0456)/sec | 0.432Credits(~$0.0432)/sec | 0.6Credits(~$0.06)/sec | 20% |
| V2V-DRAFT | 0.96Credits(~$0.096)/sec | 0.912Credits(~$0.0912)/sec | 0.864Credits(~$0.0864)/sec | 1.2Credits(~$0.12)/sec | 20% | |
| HD | 1.36Credits(~$0.136)/sec | 1.292Credits(~$0.1292)/sec | 1.224Credits(~$0.1224)/sec | 1.7Credits(~$0.17)/sec | 20% | |
| FHD | 2.32Credits(~$0.232)/sec | 2.204Credits(~$0.2204)/sec | 2.088Credits(~$0.2088)/sec | 2.9Credits(~$0.29)/sec | 20% | |
| V2V-HD | 3.28Credits(~$0.328)/sec | 3.116Credits(~$0.3116)/sec | 2.952Credits(~$0.2952)/sec | 4.1Credits(~$0.41)/sec | 20% | |
| V2V-FHD | 4.24Credits(~$0.424)/sec | 4.028Credits(~$0.4028)/sec | 3.816Credits(~$0.3816)/sec | 5.3Credits(~$0.53)/sec | 20% |
* Actual costs are subject to final output.
FLUX 3 Video API for 20-Second Video with Native Audio
Generate from a prompt, animate 1–10 ordered keyframes, continue a source video, or enhance a completed draft. Choose 5–20 seconds, HD or FHD output, and synchronized native audio.
50K+
Active Users
99.9%
Uptime
2x
Faster
—
Cost Savings
FLUX 3 Video API Example: Text to Video and Image to Video
Call flux-3-video with one POST request. Generation is asynchronous: submit a task, then poll the task endpoint for the video URL.
- 1
Authenticate FLUX 3 Video API requests
Save your APIMart key in the APIMART_API_KEY environment variable and send it as Authorization: Bearer <key> on every request.
- 2
Submit a FLUX 3 Video task
POST /v1/videos/generations with model flux-3-video, your prompt, duration and resolution. Add image_urls for keyframes or video_url to continue a clip. The example.com URLs are placeholders: replace them with your own publicly accessible images or Base64 data. The task ID is in data[0].task_id.
- 3
Get the FLUX 3 Video result
Poll GET /v1/tasks/{task_id} until status is completed, then read the video URL from data.result.videos[0].url[0] and the final charge from cost. APIMart keeps results for 72 hours, so download the videos you want to keep.
See the FLUX 3 Video API reference for every parameter, mode rule and response field.
curl -X POST https://api.apimart.ai/v1/videos/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "flux-3-video",
"prompt": "An orange cat jumps onto a sunlit wooden table, the camera slowly pushes in, soft morning light, quiet kitchen ambience",
"duration": 5,
"resolution": "hd",
"aspect_ratio": "16:9",
"audio": true
}'import os
import time
import requests
API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}
# 1. Submit the generation task
payload = {
"model": "flux-3-video",
"prompt": "An orange cat jumps onto a sunlit wooden table, the camera slowly pushes in, soft morning light, quiet kitchen ambience",
"duration": 5,
"resolution": "hd",
"aspect_ratio": "16:9",
"audio": True
}
resp = requests.post(f"{API_BASE}/v1/videos/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]
# 2. Poll the task until it finishes
for _ in range(200):
task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
task_resp.raise_for_status()
task = task_resp.json()["data"]
if task["status"] == "completed":
print(task["result"]["videos"][0]["url"][0])
break
if task["status"] == "failed":
raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
time.sleep(10)
else:
raise TimeoutError(f"task {task_id} did not finish in time; continue GET polling with this task ID")curl -X POST https://api.apimart.ai/v1/videos/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "flux-3-video",
"prompt": "A closed flower bud slowly opens into full bloom, smooth time-lapse, soft studio light, gentle ambient music",
"duration": 5,
"resolution": "hd",
"image_urls": [
"https://example.com/start-frame.jpg",
"https://example.com/end-frame.jpg"
]
}'TASK_ID="task_xxx" # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
-H "Authorization: Bearer $APIMART_API_KEY"FLUX 3 Video API Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Required | Default: flux-3-video | Use flux-3-video. |
prompt | string | Required | Default: — | Describe the scene, motion, camera and sound. Do not send it when finalizing a draft with draft_from_task_id. |
duration | integer | Optional | Default: 5 | Integer from 5 to 20 seconds. Non-integer values are treated as 5 seconds. |
resolution | string | Optional | Default: hd | hd (about 1280×704 at 16:9) or fhd (about 1920×1088). Drafts support hd only. |
aspect_ratio | string | Optional | Default: auto | 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16 or auto. |
image_urls | string[] | Optional | Default: — | 1–10 keyframes in playback order: the first is the start frame, the last is the end frame and middle frames are spaced evenly. Public URLs or Base64. |
video_url | string | Optional | Default: — | Source MP4 to continue (public URL or Base64). Takes priority over image_urls and uses video-continuation pricing. |
audio | boolean | Optional | Default: true | Generate synchronized audio. false returns a silent video at the same price. |
draft | boolean | Optional | Default: false | Create a low-cost HD preview at about one third of the price. |
draft_from_task_id | string | Optional | Default: — | ID of your completed draft task. Renders the final video; only resolution can change and the full price applies. |
mode | string | Optional | Default: — | Optional explicit mode: t2v, i2v, v2v or draft_enhance. Otherwise it is inferred from the fields you send. |
safety_tolerance | integer | Optional | Default: 2 | 0 (strictest) to 4. |
nsfw_check | boolean | Optional | Default: false | Review the prompt and input images with omni-moderation-latest before submission. |
Compare FLUX API Models on APIMart
One APIMart API key calls every FLUX model below. Image models are billed per image and FLUX 3 Video per second of video.
| Model | Best for | Output |
|---|---|---|
| FLUX 3 Image API | The FLUX 3 API for images: generation and editing with up to 10 references, search grounding and output up to 4K | 768sq to 4K (about 16 MP) |
| FLUX 3 Image Klein API | Lower-cost FLUX 3 images with seed, 1–16 steps and PNG or JPEG output | 768sq to 4K (about 16 MP) |
| FLUX 3 Video APIThis page | Text to video, 1–10 keyframes, video continuation and drafts, with synced audio | HD or FHD, 5–20 s |
| FLUX.2 API | Choosing between FLUX.2 Pro, Max and Flex on one page | 1–4 MP |
| FLUX.2 Pro API | Balanced quality and cost for production images, up to 8 references | 1–4 MP |
| FLUX.2 Max API | The highest-quality FLUX.2 output, up to 8 references | 1–4 MP |
| FLUX.2 Flex API | Adjustable steps and guidance for typography and layout-heavy designs | 1–4 MP |
| FLUX.1 Kontext API | Choosing between FLUX.1 Kontext Pro and Max on one page | About 1 MP |
| FLUX.1 Kontext Pro API | Context-aware edits at a fixed price per image, up to 4 references | About 1 MP |
| FLUX.1 Kontext Max API | Higher-quality Kontext edits with stronger prompt adherence | About 1 MP |
