AIREITER
FLUX 3 Max AI Video Generator and API
FLUX 3 Max is a post-trained variant of FLUX 3 Video from Black Forest Labs. It is tuned for stronger prompt adherence and better visual quality while keeping generation fast, and it creates video and native audio together.
Three input modes
Generate from text only, from a first frame with an optional last frame, or from up to 10 keyframes placed across the timeline.
5 to 20 seconds
Pick any whole-second length from 5 to 20. The default is 5 seconds.
720p or 1080p
Render at 720p (default) or 1080p at 24 fps.
Native audio
Sound is generated with the picture by default. Turn audio off for a silent clip.
Text, First / Last Frame, and Keyframes
Choose the mode by how much control you need over the shot.
Text
Write a prompt and let the model plan the shot. Aspect ratio auto uses 16:9.
First / Last Frame
Upload a start image and, optionally, an end image. The video opens on the first and lands on the last.
Keyframes
Upload 2–10 images in order. They are spread evenly from the first frame to the last, so the video passes through each one.
Aspect ratio
Auto, 16:9, 9:16, 1:1, 4:3, 3:4, or 21:9. With images, auto follows the first image.
What to Create with FLUX 3 Max
Cinematic shots from a prompt
Describe the scene, camera move, and sound, and get a finished clip with matching audio.
Controlled transitions
Set the opening and closing frames to move between two product shots, two poses, or two locations.
Storyboards to motion
Turn a sequence of storyboard frames into one continuous shot with keyframes.
Vertical, square, and ultrawide
Generate in 9:16, 1:1, 16:9, or 21:9 so the clip fits social feeds, ads, or cinematic edits without cropping.
Supported FLUX 3 Max Controls
The playground and the API expose the same parameters.
Prompt
Describe the scene, motion, and sound. Required in every mode.
Generation type
text (default), frame (first / last frame), or keyframes.
Images
frame: 1 start image plus an optional end image. keyframes: up to 10 images in order. PNG, JPEG, or WEBP, up to 20MB each.
Resolution and length
720p (default) or 1080p. Length is 5–20 whole seconds, default 5.
Prompt reasoning
high (default) expands your prompt more for better results but is slower. low is faster. Same price.
Aspect ratio and audio
auto (default), 16:9, 9:16, 1:1, 4:3, 3:4, or 21:9. Generate Audio is on by default and can be turned off.
How to Generate a FLUX 3 Max Video
Four steps, in the browser or through the API.
Choose a mode
Text for a prompt-only shot, First / Last Frame to pin the start and end, or Keyframes to guide the whole timeline.
Add your images
Skip this for Text. Upload a start image and optional end image, or 2–10 keyframes in order.
Write the prompt
Describe the action, camera movement, lighting, and the sounds you want to hear.
Set specs and generate
Pick resolution, length, aspect ratio, and prompt reasoning. Keep audio on for sound, then generate.
Use FLUX 3 Max through the AIReiter API
Submit one task and query the same external task ID until it reaches a terminal state.
Model ID
Send flux_3_max as the model value in the request body.
Submit a task
POST /api/openapi/submit with the model, a unique out_task_id, and params: type (text, frame, or keyframes), prompt, image_url, resolution, video_length, aspect_ratio, reasoning_level, and generate_audio.
Query the result
POST /api/openapi/query with the same out_task_id until the status is completed or failed. Completed responses include the video URL.
Input rules
type text ignores images. type frame uses image_url[0] as the first frame and image_url[1] as the optional last frame. type keyframes takes up to 10 images in order.
Related AI Video Models on AIReiter
FLUX 3 Video
The base FLUX 3 video model from Black Forest Labs.
Kling v3 Omni
Text, multi-image reference, first/last frames, and reference video up to 15s.
Wan 3.0
Text, first/last frames, mixed references, and document-to-video up to 30 seconds.
AI Video Generator
Switch between every video model on AIReiter from one tool.
FLUX 3 Max FAQ
Answers about modes, length, resolution, audio, and API usage.
/ 01What is FLUX 3 Max?
FLUX 3 Max is a post-trained variant of FLUX 3 Video from Black Forest Labs, tuned for stronger prompt adherence and better visual quality at lower latency. On AIReiter it creates 5–20 second videos at 720p or 1080p with native audio.
/ 02How is FLUX 3 Max different from FLUX 3 Video?
FLUX 3 Max is post-trained on top of FLUX 3 Video to follow prompts more closely and look better, while staying fast. It also supports first / last frame and keyframe modes.
/ 03Does FLUX 3 Max support text-to-video?
Yes. Text mode needs only a prompt. Auto aspect ratio uses 16:9.
/ 04Can I set both the first and last frame?
Yes. In First / Last Frame mode, upload a start image and an optional end image.
/ 05How do keyframes work?
Upload 2–10 images in order. AIReiter spreads them evenly from the first frame to the last frame of the video, and the model moves through each one.
/ 06How long can a FLUX 3 Max video be?
From 5 to 20 seconds in whole seconds. The default is 5 seconds.
/ 07What resolutions does FLUX 3 Max support?
720p and 1080p, at 24 fps. The default is 720p.
/ 08Does FLUX 3 Max generate audio?
Yes. Native audio is generated with the video by default. Turn Generate Audio off for a silent clip at the same price.
/ 09What does prompt reasoning do?
The model rewrites and expands your prompt before generating. High spends more effort for better results but is slower. Low is faster. Both cost the same.
/ 10Which API model ID should I use?
Use flux_3_max with POST /api/openapi/submit, then poll POST /api/openapi/query with the same out_task_id.