Image

Flux 2 Dev API

Black Forest Labs' open-weight member of the Flux 2 family (Nov 2025), a 32-billion-parameter model you can download and run yourself, positioned as the most capable open-weight image generation and editing model available.

Get API key Read the docs

~17s
Avg. generation: 1 credits
From

Flux 2 Dev photorealistic hero banner of a hiking backpack on a mossy rock in morning mist with soft natural light

Playground

Try Flux 2 Dev right here.

model: flux-2-dev

Prompt

Aspect ratio

Image strength

Media inputs

Reference image

Advanced settings

Steps Guidance Output format Output quality Prompt upsampling Let the model rewrite your prompt for better quality. Go fast Seed

Estimated cost 1–3 credits · $0.01–$0.03 Generate in Studio

Output

Your output lands here. Hit generate to run this request in Studio.

Pricing

Simple per-generation pricing.

1–3 credits per generation ≈ $0.01–$0.03

The rate depends on the resolution and options you pick.

You only pay for successful generations. Failed jobs are refunded automatically.
One credit balance across every model on Apiframe, no per-model plans.
Start with free credits. No subscription required.
Volume discounts on larger plans.

See plans and credit packs

Specs

At a glance.

Provider Black Forest Labs

Model ID flux-2-dev

Aspect ratios 1:1, 3:4, 4:3, 9:16, 16:9

Image input Supported

Avg. time ~17s

Quickstart

How to call the Flux 2 Dev API.

Send one POST /v2/images/generate request with your API key. The call returns a jobId you can poll, or pass a webhook_url and the result is pushed to you the moment it's ready.

Swap flux-2-dev for any other model and nothing else changes.

Get API key Read the docs

generate.js

const response = await fetch("https://api.apiframe.ai/v2/images/generate", {
  method: "POST",
  headers: {
    "X-API-Key": "afk_your_api_key_here",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
    "model": "flux-2-dev",
    "fluxParams": {
      "image_prompt": "https://example.com/input.jpg",
      "image_prompt_strength": 0.5,
      "steps": 28,
      "guidance": 3
    }
  }),
});
const { jobId } = await response.json();
console.log(jobId);

import requests

response = requests.post(
    "https://api.apiframe.ai/v2/images/generate",
    headers={
        "X-API-Key": "afk_your_api_key_here",
        "Content-Type": "application/json",
    },
    json={
        "prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
        "model": "flux-2-dev",
        "fluxParams": {
            "image_prompt": "https://example.com/input.jpg",
            "image_prompt_strength": 0.5,
            "steps": 28,
            "guidance": 3
        }
    },
)
print(response.json())  # { "jobId": "...", "status": "QUEUED" }

curl -X POST https://api.apiframe.ai/v2/images/generate \
  -H "X-API-Key: afk_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
        "model": "flux-2-dev",
        "fluxParams": {
            "image_prompt": "https://example.com/input.jpg",
            "image_prompt_strength": 0.5,
            "steps": 28,
            "guidance": 3
        }
    }'

let job;
do {
  await new Promise((r) => setTimeout(r, 2000));
  job = await fetch("https://api.apiframe.ai/v2/jobs/JOB_ID", {
    headers: { "X-API-Key": "afk_your_api_key_here" },
  }).then((r) => r.json());
} while (job.status !== "COMPLETED" && job.status !== "FAILED");
console.log(job.result);

import requests, time

while True:
    job = requests.get(
        "https://api.apiframe.ai/v2/jobs/JOB_ID",
        headers={"X-API-Key": "afk_your_api_key_here"},
    ).json()
    if job["status"] in ("COMPLETED", "FAILED"):
        break
    time.sleep(2)
print(job["result"])

curl https://api.apiframe.ai/v2/jobs/JOB_ID \
  -H "X-API-Key: afk_your_api_key_here"

Input schema

Every field Flux 2 Dev accepts, with types and defaults. The full reference lives in the docs.

Field	Type	Description
prompt required	string	Text description of what to generate.
model required	string	The model identifier for this endpoint. Default:"flux-2-dev" · "flux-2-dev"
fluxParams.image_prompt	string (URL)	Reference image (URL)
fluxParams.image_prompt_strength	number	How closely to follow the reference image (0–1). Default:0.5 · min 0, max 1, step 0.05
fluxParams.steps	number	Steps Default:28 · min 1, max 50, step 1
fluxParams.guidance	number	How strictly to follow the prompt. Default:3 · min 1.5, max 10, step 0.1
fluxParams.output_format	string	Output format Default:"jpg" · "jpg", "png", "webp"
fluxParams.output_quality	number	Output quality Default:90 · min 0, max 100, step 1
fluxParams.prompt_upsampling	boolean	Let the model rewrite your prompt for better quality. Default:false
fluxParams.go_fast	boolean	Go fast Default:false
fluxParams.seed	number	Reuse a number to reproduce the same result. step 1

The Flux flagship

Flux 2 Dev is one of 7 Flux image models on Apiframe. The full editorial page (showcase, comparison, and use cases) lives on the flagship.

Flagship from 7 cr Flux 2 Max

The quality ceiling of the Flux family.

Explore Flux 2 Max All image models

Flux 2 Dev questions

What teams ask before shipping with Flux 2 Dev. Everything else lives in the docs.

Is Flux 2 Dev free?

The open weights are free to download and run, but they are released under a non-commercial license.

Can you use it commercially?

Not under the open-weight license alone. Commercial use requires a separate self-hosted commercial license from Black Forest Labs, or using the paid API.

Can you run it locally, and what hardware do you need?

Yes. Full precision needs heavy VRAM, but quantized versions run on consumer RTX cards in roughly the 14 to 24GB range via ComfyUI and Diffusers.

How is it different from Pro, Flex, and Max?

Dev is the open-weight option built for local use and customization, while Pro, Flex, and Max are hosted, proprietary tiers.

Can you fine-tune it?

Yes. It supports LoRA training on consumer hardware for custom styles and subjects.

Where can you access it?

Through Apiframe, as well as Hugging Face for the open weights and major hosting partners.