Using FLUX 3 Image on Vercel AI Gateway

Implementation guide · FLUX 3 · Black Forest Labs

Serverless

Vercel AI Gateway exposes FLUX 3 Image through model ID bfl/flux-3-image. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-07. Next refresh: weekly.

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 — see the documentation for request format.

Code Examples

Install
pip install openai
API key
AI_GATEWAY_API_KEY
Model ID
bfl/flux-3-image

creator/model-name e.g. kwaipilot/kat-coder-pro-v2

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",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Pricing on Vercel AI Gateway

TypeRate
Image input$1.00

Capabilities

Multimodal

About FLUX 3 Image

FLUX 3 Image is Black Forest Labs' image generation and editing product in the FLUX 3 family. One endpoint (POST https://api.bfl.ai/v1/flux-3-image) handles text-to-image and edits: up to 10 reference images, bounding-box layouts in the prompt, pixel-exact local edits, and resolution classes from 768sq through 4K (~16 MP) across 15 aspect ratios. First-party pricing (docs.bfl.ml): $0.041 (768sq), $0.048 (1k), $0.100 (2k), $0.607 (4k) per image. Commercial weights license is offered; open weights not published yet. Also listed on Vercel AI Gateway as bfl/flux-3-image.

Model Specs

Released2026-10-05
ArchitectureDiffusion Transformer

Provider

Vercel AI Gateway

Vercel