Skip to content
Dashboard

FLUX.2 [max]

FLUX.2 [max] is Black Forest Labs's quality ceiling in the FLUX.2 family. It delivers 4 MP resolution, high visual fidelity, and multi-reference input for up to 10 images in professional commercial image generation workflows.

Image Gen
index.ts
import { experimental_generateImage as generateImage } from 'ai';
const result = await generateImage({
model: 'bfl/flux-2-max',
prompt: 'A red balloon on a wooden table.'
});

Playground

Try out FLUX.2 [max] by Black Forest Labs. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

bfl logo
Prompt
Describe what you want the model to generate.
Need inspiration?
Reference images(optional)
Images to generate
bfl logo

Your generated image will appear here

Providers

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider
Context
Latency
Throughput
Input
Output
Cache
Web Search
Per Query
Capabilities
ZDR
No Training
Release Date
Black Forest Labs
67K
——
12/16/2025

More models by Black Forest Labs

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Per Query
Capabilities
Providers
ZDR
No Training
Release Date
——
bfl logo
01/15/2026
——
bfl logo
01/15/2026
——
bfl logo
11/25/2025
512
——
bfl logo
05/29/2025
512
——
bfl logo
prodia logo
05/29/2025
——
bfl logo
10/01/2024

About FLUX.2 [max]

FLUX.2 [max] occupies the highest quality position in the FLUX.2 lineup. Black Forest Labs designed FLUX.2 for real-world creative workflows: maintaining character and style consistency across multiple reference images, following structured prompts, rendering complex typography, adhering to brand guidelines, and handling lighting, layout, and logos with precision. Max pushes all of those capabilities to their ceiling.

The FLUX.2 architecture pairs a Mistral-3 24B vision-language model (VLM) with a rectified flow transformer. The VLM contributes real-world knowledge, physical plausibility, and spatial reasoning to both Pro and Max. Max applies additional quality investment, producing images with greater detail fidelity in fine textures, complex materials, and edge rendering. That difference matters for print production, large-format display, and professional media workflows where artifacts visible at 100% zoom are unacceptable.

At 4 megapixels, FLUX.2 [max] outputs suit print layouts, high-resolution editorial use, and downstream editing in design tools where resolution headroom matters. The multi-reference capability supports up to 10 input images simultaneously. This enables brand-controlled workflows where product shots, logos, and character consistency must all hold in one generation.

For typography-intensive outputs (infographics, advertising materials, UI mockups), FLUX.2 [max] produces reliably legible fine text thanks to improved prompt adherence and detail fidelity at this tier.

What To Consider When Choosing a Provider

  • Configuration: 4 MP resolution generation carries a higher per-image cost than standard tiers. Confirm N/A before you build high-volume pipelines around FLUX.2 [max].
  • Zero Data Retention: AI Gateway does not currently support Zero Data Retention for this model. See the documentation for models that support ZDR.
  • Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

When to Use FLUX.2 [max]

Best For

  • Print and large-format display: 4 MP resolution output where downscaled generation would lose critical detail
  • Professional brand assets: Logos, product shots, and editorial imagery where quality artifacts are not acceptable
  • Typography-heavy commercial work: Advertising materials, infographics, and UI mockups where text legibility at full resolution is essential
  • High-stakes multi-reference generation: Up to 10 brand references must be satisfied simultaneously with no quality compromise

Consider Alternatives When

  • Speed and per-image cost: FLUX.2 Pro costs less per image at a lower fidelity tier when maximum fidelity is not required
  • Real-time generation: FLUX.2 Klein is built for sub-second generation
  • Runtime parameter control: FLUX.2 Flex exposes step count and guidance scale directly
  • Context-aware editing: FLUX.1 Kontext Pro or Kontext Max is specialized for editing an existing image

Conclusion

FLUX.2 [max] sets the quality ceiling for the FLUX.2 family with 4 MP resolution, maximum detail fidelity, reliable complex typography, and multi-reference input. For print, editorial, and brand-critical image generation where the difference between Pro and Max is visible, Max is the right choice.