# FLUX 3 Max AI models

Canonical page: https://flux3max.com/

Generated from the live model configuration of flux3max.com. Credit prices per option are in pricing.md.

## FLUX 3 Max (default video model)

- Modes: Text to video, Image to video
- Image to video inputs: first frame (required), last frame (optional)
- Aspect ratios: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16
- Resolutions: 720p, 1080p
- Duration: 5 to 20 seconds
- Credits: 35 per second (720p) to 60 per second (1080p), minimum 175 per run

### Our test runs

- Image to video, 720p, 5 s, audio on, first frame + last frame: 175 credits (run on 2026-10-20)
  - Prompt: "A hand enters the frame, unties the red ribbon and lifts the lid, leans it against the side of the box and moves out of frame, revealing a wristwatch on white tissue paper. The camera holds still. The soft window light stays the same. Sound: ribbon sliding, paper rustling, a soft click as the lid comes off."
  - Result: A hand comes in, pulls the ribbon loose and lifts the lid, and the take ends on the open box as it looks in the last frame. Audio was generated but not reviewed.
  - Video: https://cdn.flux3max.com/assets/landing/flux3max/guide/first-last.mp4
- Text to video, 16:9, 720p, 5 s, audio on: 175 credits, result in 15 s (run on 2026-10-20)
  - Prompt: "Night market food stall, handheld medium shot. An older street cook tosses noodles in a flaming wok; the flames flare up and light her face. She looks up at a customer just off camera and says with a grin: "Two minutes. Best noodles on this street." Sizzling wok, crowd chatter, a distant scooter horn. Warm neon signs and drifting steam."
  - Result: A covered stall under red neon and heavy steam. The cook flings a big tangle of noodles up out of the wok, and the take ends on her grin. Audio was generated but not reviewed.
  - Video: https://cdn.flux3max.com/assets/landing/flux3max/compare/pair1-max.mp4
- Text to video, 16:9, 720p, 5 s, audio on: 175 credits, result in 14 s (run on 2026-10-20)
  - Prompt: "Slow 180-degree orbit around a pair of matte black over-ear headphones resting on a concrete pedestal in a minimal studio. Soft key light from the left, a thin rim light traces the ear cups, dust drifts through the beam. The orbit ends front-on as the light warms slightly. A low ambient synth hum."
  - Result: The light shifts from cool grey to warm amber by the end, but the camera covers only part of the 180-degree orbit. Audio was generated but not reviewed.
  - Video: https://cdn.flux3max.com/assets/landing/flux3max/compare/pair2-max.mp4

## FLUX 3

- Modes: Text to video, Image to video, Video to video
- Reference images: up to 10
- Reference videos: up to 1
- Aspect ratios: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16
- Resolutions: 720p, 1080p
- Duration: 5 to 20 seconds
- Credits: Text to video, Image to video: 35 per second (720p) to 60 per second (1080p), minimum 175 per run; Video to video: 6 per second, minimum 12 per run

### Our test runs

- Text to video, 16:9, 720p, 5 s, audio on: 175 credits, result in 77 s (run on 2026-10-20)
  - Prompt: "Night market food stall, handheld medium shot. An older street cook tosses noodles in a flaming wok; the flames flare up and light her face. She looks up at a customer just off camera and says with a grin: "Two minutes. Best noodles on this street." Sizzling wok, crowd chatter, a distant scooter horn. Warm neon signs and drifting steam."
  - Result: An open-air night street with the crowd and scooters on screen. Her toss is gentler, closer to the prompt's wording, and she ends on a grin. Audio was generated but not reviewed.
  - Video: https://cdn.flux3max.com/assets/landing/flux3max/compare/pair1-flux3.mp4
- Text to video, 16:9, 720p, 5 s, audio on: 175 credits, result in 62 s (run on 2026-10-20)
  - Prompt: "Slow 180-degree orbit around a pair of matte black over-ear headphones resting on a concrete pedestal in a minimal studio. Soft key light from the left, a thin rim light traces the ear cups, dust drifts through the beam. The orbit ends front-on as the light warms slightly. A low ambient synth hum."
  - Result: The camera covers the full half circle, from side profile to front-on, but the light stays cool and neutral instead of warming. Audio was generated but not reviewed.
  - Video: https://cdn.flux3max.com/assets/landing/flux3max/compare/pair2-flux3.mp4

## MiniMax H3 Max

- Modes: Text to video, Image to video, Reference to video, Video to video
- Image to video inputs: first frame (required), last frame (optional)
- Reference images: up to 9
- Reference videos: up to 3
- Reference audio: up to 3
- Aspect ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive, auto
- Resolutions: 480P, 768P, 1080P, 2K
- Duration: 5 to 15 seconds
- Outputs per run: 1 to 4
- Credits: Text to video, Image to video, Reference to video: 10 per second (480P) to 35 per second (1080P); Video to video: 20 per second (480P) to 140 per second (2K)

## MiniMax H3 Max Turbo

- Modes: Text to video, Image to video
- Image to video inputs: first frame (required), last frame (optional)
- Aspect ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16
- Resolutions: 480P, 768P, 1080P
- Duration: 5 to 15 seconds
- Outputs per run: 1 to 4
- Credits: 5 per second (480P) to 20 per second (1080P)

## GPT Image 2.5 Flare (default image model)

- Modes: Text to image, Image to image
- Reference images: up to 16
- Aspect ratios: auto, 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9
- Resolutions: 1K, 2K, 4K
- Outputs per run: 1 to 4
- Credits: 3 per image (1K) to 16 per image (4K)

### Our test runs

- Image to image, 1:1, background type auto, 1K, 1 output, 1 reference images: 3 credits, result in 104 s (run on 2026-10-22)
  - Prompt: "Turn this photo into a hand-drawn anime film still, with a soft painted background. Keep her face, curly red hair, yellow sweater and the coffee cup."
  - Result: Anime-style shading; curls, gold earrings and open smile kept, still recognizably her.
  - Image: https://cdn.flux3max.com/assets/landing/ai-image-studio/i2i/grid-flare.webp
- Text to image, 1:1, background type auto, 1K, 1 output: 3 credits, result in 59 s (run on 2026-10-22)
  - Prompt: "A rough pencil sketch on white paper of a small wooden cabin by a lake, pine trees behind it, a little dock in front, loose lines, no color."
  - Result: Detailed pencil sketch of a log cabin with a chimney, pine trees, a dock and distant mountains on a lake.
  - Image: https://cdn.flux3max.com/assets/landing/ai-image-studio/i2i/s2-sketch.webp
- Text to image, 1:1, background type auto, 1K, 1 output: 3 credits, result in 81 s (run on 2026-10-22)
  - Prompt: "A candid photo of a young woman with curly red hair and a mustard yellow sweater, laughing at a small cafe table by a rainy window, holding a cup of coffee, natural light, shot on a 35mm lens."
  - Result: Candid photo of a laughing woman with curly red hair and a mustard sweater holding a coffee cup at a rainy cafe window.
  - Image: https://cdn.flux3max.com/assets/landing/ai-image-studio/i2i/s1-cafe.webp

## Nano Banana 2.1

- Modes: Text to image, Image to image
- Reference images: up to 10
- Aspect ratios: 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, 21:9, auto
- Resolutions: 1K, 2K, 4K
- Outputs per run: 1 to 4
- Credits: 8 per image (1K) to 20 per image (4K)

### Our test runs

- Image to image, 1:1, 1K, 1 output, 1 reference images: 8 credits, result in 48 s (run on 2026-10-22)
  - Prompt: "Turn this photo into a soft watercolor illustration on textured paper. Keep her face, curly red hair, yellow sweater and the cafe window."
  - Result: Soft watercolor illustration of the same woman, cup and rainy window; curls and sweater kept.
  - Image: https://cdn.flux3max.com/assets/landing/ai-image-studio/i2i/tab1-watercolor.webp
- Image to image, 1:1, 1K, 1 output, 1 reference images: 8 credits, result in 48 s (run on 2026-10-22)
  - Prompt: "Turn her into a 3D animated movie character with big expressive eyes and soft lighting. Keep her curly red hair, yellow sweater, the coffee cup and the cafe setting."
  - Result: 3D animated-film style character with big eyes; hair, sweater, cup and cafe kept.
  - Image: https://cdn.flux3max.com/assets/landing/ai-image-studio/i2i/tab2-3d.webp
- Image to image, 1:1, 1K, 1 output, 1 reference images: 8 credits, result in 50 s (run on 2026-10-22)
  - Prompt: "Use this mug in a winter holiday ad: it sits on a snowy windowsill with warm fairy lights, and steam rises from hot cocoa inside it. Keep the mug's shape, color and matte finish."
  - Result: Same sage mug, filled with cocoa and marshmallows, on a snowy windowsill with fairy lights and pine sprigs; new angle and light.
  - Image: https://cdn.flux3max.com/assets/landing/ai-image-studio/i2i/tab4-mug.webp
- Image to image, 1:1, 1K, 1 output, 1 reference images: 8 credits, result in 51 s (run on 2026-10-22)
  - Prompt: "Turn this sketch into a realistic photo at golden hour. Keep the cabin, the dock, the lake and the pine trees where they are in the sketch."
  - Result: Realistic golden-hour photo with the cabin, dock, pines and mountains in the sketch's positions; chimney smoke added.
  - Image: https://cdn.flux3max.com/assets/landing/ai-image-studio/i2i/tab3-sketch.webp

## Tools

- Background Remover (image): 1 credit per run
- Image Extender (image): 2 credits per run
- Image Upscaler (image): 2 credits (2x) or 4 credits (4x) or 8 credits (8x) per run
- Photo Restore (image): 6 credits per run
- Motion Control (video): 20 credits (720p) or 40 credits (1080p) per second of video, minimum 45 credits per run
- Lip-Sync Video (video): 5 credits (720p) or 10 credits (1080p) per second of video, minimum 15 credits per run
- Video Upscaler (video): 2 credits (1080p) or 3 credits (2k) or 6 credits (4k) per second of video