bflNot yet certifiedReleased 12/16/2025

FLUX.2 [max]

FLUX.2 [max] offers image generation and image editing with the highest quality available. It delivers state-of-the-art image generation and advanced image editing with exceptional realism, precision, and consistency. Built for professional use, FLUX.2 [max] produces production-ready outputs for marketing teams, creatives, filmmakers, and creators around the world.

View API reference ↓
Input / output priceFrom$0 / $0per 1M
24h uptime97.55%

Listed for reference. Inference Bureau dispatches only to certified routes, so requests for this model are refused until one is certified. See certified models.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.images.generate({
  model: "bfl/flux-2-max",
  prompt: "A lighthouse at dusk, oil painting",
  size: "1024x1024",
});

// Base64 only: images are returned, never stored.
const png = Buffer.from(res.data[0].b64_json, "base64");

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
bfl67K67K——$0$0Read —Write —1 featuresNoNoGlobalListed

Uptime

24 hours

Request success rate per provider.

bfl97.55%

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.images.generate({
  model: "bfl/flux-2-max",
  prompt: "A lighthouse at dusk, oil painting",
  size: "1024x1024",
});

// Base64 only: images are returned, never stored.
const png = Buffer.from(res.data[0].b64_json, "base64");

FLUX.2 [max] answers POST /v1/images/generations, not chat completions. It is billed per output token: the balance held for a request is the most tokens the size and quality asked for were measured to take.

More models by bfl

ModelContextInputOutputCacheRelease
bfl/flux-3-image-klein0——Read —Write —10/15/2026
bfl/flux-3-image0——Read —Write —10/05/2026
bfl/flux-2-klein-4b0——Read —Write —01/15/2026
bfl/flux-2-klein-9b0——Read —Write —01/15/2026
bfl/flux-2-flex0——Read —Write —11/25/2025
bfl/flux-2-pro67K——Read —Write —11/25/2025
bfl/flux-kontext-max512——Read —Write —05/29/2025
bfl/flux-kontext-pro512——Read —Write —05/29/2025
bfl/flux-pro-1.1-ultra0——Read —Write —11/01/2024
bfl/flux-pro-1.10——Read —Write —10/02/2024