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.

Integrate Flux 2 Dev with a single API call — one key, one unified endpoint, and shared billing across every model on Apiframe.

Get API Key Use in Apiframe Studio View Flux 2 Dev API Docs

model: "flux-2-dev"

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

What's special about Flux 2 Dev

Open weights you can run yourself

The full model is published on Hugging Face with reference code, so you can generate and edit locally instead of relying only on a hosted API.

Runs on consumer GPUs

Full precision needs data-center hardware, but quantized fp8 and 4-bit builds run on high-end consumer cards like an RTX 4090 through ComfyUI and Diffusers.

A smarter text encoder

It pairs with a Mistral-3 language model and a 32k-token context window, which sharpens prompt accuracy and handles long, detailed instructions.

Multi-reference editing in one checkpoint

Generation and image editing with multiple reference images live in a single model, keeping characters, style, and branding consistent.

Built for customization

You can train your own LoRA adapters on consumer VRAM, tailoring the model to a specific style, product, or character.

Up to 4MP output

It generates and edits at resolutions up to 4 megapixels with strong lighting, faces, hands, and text.

Made with Flux 2 Dev

A few outputs generated through the Flux 2 Dev API on Apiframe.

Flux 2 Dev three product renders of the same sneaker in white, black, and red with a consistent angle and lighting — Three product renders of the same sneaker in white, black, and red, consistent angle and lighting.

Flux 2 Dev 3D concept art frame of a futuristic train station interior with warm lighting and detailed reflections — A 3D concept art frame of a futuristic train station interior, warm lighting, detailed reflections.

Flux 2 Dev cozy reading nook with a velvet armchair, a stack of books, and a warm lamp in late afternoon light — A cozy reading nook with a velvet armchair, a stack of books, and a warm lamp, late afternoon light.

Flux 2 Dev ad creative for a cold brew can on crushed ice with condensation droplets and bright studio lighting — An ad creative for a cold brew can on crushed ice, condensation droplets, bright studio lighting.

Flux 2 Dev consistent mascot shown waving, sitting at a desk, and giving a thumbs up in a unified style — Using these reference images of our mascot, show it waving, sitting at a desk, and giving a thumbs up, in a consistent style.

Overview

Endpoint: POST /v2/images/generate
Model ID: flux-2-dev
Params key: fluxParams
Modality: Image
Provider: Black Forest Labs
Avg. completion: ~10s

Capabilities

Aspect ratios1:1, 3:4, 4:3, 9:16, 16:9

Image inputSupported

Avg. time~10s

Quick start

Send a single POST /v2/images/generate request with your API key to generate with Flux 2 Dev. The call returns a jobId you can poll or receive via webhook.

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
        }
    }'

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" }

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);

Response & job lifecycle

Generation is asynchronous. A successful submission returns 202 Accepted with a jobId. Poll GET /v2/jobs/{id} (or supply a webhook_url) until the status is COMPLETED; the result field then holds the output URL(s).

1. Submission response (202)

{
  "jobId": "b2c3d4e5-f6a7-8901-bcde-f23456789012",
  "status": "QUEUED"
}

2. Poll for the result

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

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"])

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);

Input schema

Request parameters accepted by the Flux 2 Dev endpoint. Model-specific options are nested under the params object shown below.

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

Frequently Asked Questions

Common questions about the Flux 2 Dev API.

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.

Still have questions?

Contact Support Join Discord

Start building with the Flux 2 Dev API

Get your API key and integrate Flux 2 Dev in minutes — Pay-as-you-go.

Free credits to start

One API for every model

Webhooks, SDKs & idempotency

No provider account required

Get Started Free Read Documentation

Questions? Join our Discord or contact sales.