FLUX-2-dev is a 32 billion parameter rectified flow transformer released in November 2025 as the open-weight flagship of the FLUX-2 family. It supports both text-to-image generation and multi-reference image editing, accepting up to 10 reference images at once and producing output at up to 4 megapixels, with strong handling of fine detail such as hands, faces, fabrics, and small objects alongside reliable text rendering. Designed for high-quality work where latency is less critical, FLUX-2-dev is strong at character consistency across assets, accurate object positioning, and dependable style adherence. It is available under the FLUX Non-Commercial License and accepts exact hex color codes directly in prompts for precise color reproduction, supporting flexible output resolutions and aspect ratios for product visualization, brand asset creation, and design system generation.
Usage-based pricing, billed per megapixel, not by token.
| Variant | Price |
|---|---|
| Standard | $0.01 / megapixel |
FLUX-2-dev runs on 1 route through the qynio gateway. Compare residency, zero retention, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Price |
|---|---|---|---|---|
| US | Zero data retention | No | $0.01 / megapixel |
FLUX-2-dev runs on a single route through the qynio gateway today, so its availability is that provider's availability.
Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. .
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider qynio monitors.
Each route hosting FLUX-2-dev has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; unknown; deposit available.
Call FLUX-2-dev through the qynio gateway with one API key. Let your coding agent set it up, or call it directly — qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.QYN_API_KEY,baseURL: "https://api.qyn.io/v3/compat",});const completion = await client.chat.completions.create({model: "deepinfra/black-forest-labs/FLUX-2-dev",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, crypto rails, pricing, and benchmarks.
