FLUX-2-klein-9b is a 9 billion parameter rectified flow transformer released in January 2026 as a middle ground between the lightweight 4B variant and the flagship FLUX-2-dev. It pairs a 9B flow model with an 8B Qwen3 text embedder and is step-distilled to 4 inference steps, delivering more nuanced prompt adherence and quality than the 4B variant while still running on consumer and professional GPU hardware. FLUX-2-klein-9b supports text-to-image generation along with single-reference and multi-reference editing, enabling character consistency and product visualization at fast inference speeds. Available under the FLUX Non-Commercial License, it suits developers who want more sophisticated output than the 4B model without the heavier compute of the 32B FLUX-2-dev, with a separate undistilled 9B Base model available for fine-tuning.
Usage-based pricing, billed per generation, not by token.
| Variant | Price |
|---|---|
| Standard | $0.015 / generation |
FLUX-2-klein-9b runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Price |
|---|---|---|---|---|
| DeepInfra | US | Enterprise | No | $0.015 / generation |
Training posture across routes: No training on prompts by default.
Each route hosting FLUX-2-klein-9b has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; unknown.
Call FLUX-2-klein-9b through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into your coding agent — Claude Code, Cursor, Codex, and more — and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "deepinfra/black-forest-labs/FLUX-2-klein-9b",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
