Does FLUX-2-klein-4b support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for FLUX-2-klein-4b is available on request via Opper Enterprise — contact hello@opper.ai.

Where is FLUX-2-klein-4b hosted?

FLUX-2-klein-4b runs on US hosting routes through the Opper gateway.

Is FLUX-2-klein-4b trained on prompts and outputs?

No. Every hosting route for FLUX-2-klein-4b is configured so customer prompts and outputs are not used to train models by default.

FLUX-2-klein-4b

by Black Forest Labs

FLUX-2-klein-4b is a 4 billion parameter distilled rectified flow transformer released in January 2026, built for fast image generation and editing on consumer hardware. It uses the Qwen3 4B text encoder and achieves sub-second generation on modern hardware, fitting in roughly 13GB of VRAM and running on consumer GPUs such as the RTX 3090 and RTX 4070, with quantized FP8 and NVFP4 builds reducing memory use further. Released under the Apache 2.0 license, FLUX-2-klein-4b permits personal, scientific, and commercial use, making it the most accessible variant in the FLUX-2 family. It natively supports text-to-image generation, single-reference editing, and multi-reference composition without swapping models, and a separate undistilled 4B Base model is available for fine-tuning and LoRA training, suiting rapid iteration and interactive workflows.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Pricing

$0.014 / generation

Billing

Per generation

US residency available
Zero data retention via Enterprise
No training by default

Pricing

Usage-based pricing, billed per generation, not by token.

Variant	Price
Standard	$0.014 / generation

Available routes

FLUX-2-klein-4b 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	$0.014 / generation

Training posture across routes: No training on prompts by default.

Data handling per route

Each route hosting FLUX-2-klein-4b has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

DeepInfra — United States🇺🇸

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; unknown.

Zero data retention: Available via Opper Enterprise contract.
Training: No training on customer data.
Logging: Limited debug logs
Third-party access: None disclosed
GDPR DPA: No DPA
Transfer mechanism: unknown

Get started

Call FLUX-2-klein-4b 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.

Set it up with your agent

Copy this and paste it into your coding agent — Claude Code, Cursor, Codex, and more — and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "deepinfra/black-forest-labs/FLUX-2-klein-4b",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);