Using FLUX 3 Image Klein on Vercel AI Gateway

Quick Start

1. 1
   Create an account at Vercel AI Gateway and generate an API key.
2. 2
   Use the Vercel AI Gateway SDK or REST API to call bfl/flux-3-image-klein — see the documentation for request format.

Code Examples

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AI_GATEWAY_API_KEY"],
    base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
    model="bfl/flux-3-image-klein",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Capabilities

About FLUX 3 Image Klein

FLUX 3 Image Klein is Black Forest Labs' 5.6-billion-parameter open-weights image generation and editing model, released October 15, 2026 as a smaller version of FLUX 3 Image. It supports text-to-image, image editing, up to ten reference images and bounding-box layouts, with output from 768 x 768 up to 4K. The distilled model runs 16 steps (a 50-step Klein Base is published for fine-tuning and LoRA) and fits consumer GPUs down to 8GB VRAM with the INT8 build. The BFL API serves it as flux-3-image-klein from $0.008 to $0.036 per image; weights are on Hugging Face under the FLUX Kommunity License.