Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksEarn crypto
  1. Models
  2. Video

FLUX.3 Max

Try Model

Create 5–20-second videos at 720p or 1080p with native audio from a prompt, a start image with an optional end image, or up to 10 ordered keyframes. FLUX.3 Max improves prompt adherence and visual quality with lower latency than FLUX.3 Video. Choose low or high prompt reasoning effort.

Added Oct 20, 2026

Details

Starting Price
From $0.850 per video
Model type
both

Final price depends on the selected settings and is shown before generation.

Settings

Generation controls available for this model.

Output Format

up to 1,080p
Auto
Square
Portrait
Landscape

Default Duration

5

16 duration options

Aspect Ratio

Select

Default

auto

Options (8)

Auto (16:9 for text; first image otherwise), 21:9, 2:1, 16:9 +4 more

Duration

Select

Default

5

Options (16)

5 seconds, 6 seconds, 7 seconds, 8 seconds +12 more

Generate Audio

Toggle

Default

Yes

Generate synchronized audio and dialogue.

Prompt Reasoning Effort

Select

Default

high

Options (2)

Low (faster), High

Effort spent interpreting and expanding the prompt.

Resolution

Select

Default

720p

Options (2)

720p, 1080p

Timed Keyframes (advanced)

Text

Default

N/A

Optional JSON array of image_url and frame_index pairs. Use unique frame indices from 0 through duration × 24, up to 10 images. Leave blank to use uploaded images at evenly spaced moments.

Benchmarks

No public benchmark scores for this model yet.

Examples

Loading examples…

Related video models

Compare FLUX.3 Max with similar models from the same provider or model family.

PixVerse V6 Max

pixverse-v6-max

PixVerse V6 Max creates 1–15 second videos from text or a starting image, with 360p–1080p output, optional native audio, multi-clip generation and seed control. Text-to-video supports eight aspect ratios; image-to-video follows the starting image. Prompts support up to 5,000 characters for text-to-video or 2,048 with an image.

MiniMax H3 Max Relight

minimax/h3-max/relight

Relight an existing video using a lighting-sphere reference image while preserving the source subjects, setting, motion, camera, and audio. Source videos are prepared at 24 fps, must be about 2.33–15 seconds, and output matches the prepared source duration.

MiniMax H3 Max Turbo Extend

minimax/h3-max-turbo/extend-video

Continue an existing video with 1–15 seconds of new footage, with optional audio references. Return the full extended video or only the continuation. Source videos must be 1.625–60 seconds and at most 50 MB.

MiniMax H3 Max Recast

minimax/h3-max/recast

Replace the main people in a video using 1–4 reference photos while preserving motion, camera, cuts, and soundtrack. Use a 5–30 second source with individual shots no longer than 15 seconds. An optional prompt specifies who becomes whom.

MiniMax H3 Max Extend

minimax/h3-max/extend-video

Continue an existing video with a prompt describing what happens next. Add 5–15 seconds of new footage at 480p through 2K, returning the full extended video or just the continuation. Source videos must be MP4 or MOV, 1.625–60 seconds, at most 50 MB, with an aspect ratio between 0.4 and 2.5.

MiniMax H3 Max Lip Sync

minimax/h3-max/lip-sync/image-to-video

Animate a portrait or character image from supplied audio with transcription-guided lip sync. Audio must be at least 5 seconds; longer inputs are clipped to the first 15 seconds. Supports talking and singing clips from 480p through 2K.