Image

Flux 2 Pro API

The Flux workhorse: quality, speed, and price in balance.

Generate high-quality AI images with Black Forest Labs' Flux 2 Pro through one unified API. A single REST endpoint, async jobs, and webhooks, with no separate provider account to manage.

Get API key Read the docs

4MP
Max output: ~15s
Avg. generation: 5
Aspect ratios: 3 credits
From

Flux 2 Pro photoreal NOMAD electric crossover on a coastal highway at golden hour, rust accent stripe, wet asphalt

Playground

Try Flux 2 Pro right here.

model: flux-2-pro

Prompt

Aspect ratio Resolution

Image strength

Media inputs

Reference image

Advanced settings

Output format Output quality Prompt upsampling Let the model rewrite your prompt for better quality. Seed

Estimated cost 3–9 credits · $0.03–$0.09 Generate in Studio

Output Example

Flux 2 Pro editorial product photo of a matte black NOMAD ceramic travel mug on sunlit marble — Editorial studio product photo of a matte black NOMAD ceramic travel mug on sunlit marble, morning light through linen curtains, sharp reflections, no extra props.

Capabilities

What's new in Flux 2 Pro.

Frontier photorealism

It produces realistic lighting and physics that reduce the typical "AI look," making it strong for commercial-grade imagery.

Multi-reference consistency

It can take up to 10 reference images at once and hold a consistent character, product, or style across every output.

A large context window

A 32k-token context lets it follow long, detailed, multi-part prompts without losing the thread.

Accurate text rendering

It renders clean, legible typography even at small sizes, which makes it dependable for posters, infographics, and UI.

Unified generation and editing

The same model both creates images from text and edits existing ones at up to 4MP while preserving detail.

Production-ready speed and pricing

It generates in under 10 seconds with automatic prompt enhancement, from 3 credits ($0.03) per image at 0.5MP, scaling up to 9 credits ($0.09) at 4MP.

Showcase

See what Flux 2 Pro can create.

Real outputs generated with Flux 2 Pro on Apiframe, each with the prompt behind it.

Try Flux 2 Pro

A brand-consistent set of the same NOMAD fox mascot in three poses: waving, sitting at a wooden desk, holding a travel mug. Flat graphic, rust and navy, white background.

Flux 2 Pro NOMAD event poster reading THE ROAD IS THE POINT, Sept 12, Coast Highway, over a coastal dusk — Event poster reading NOMAD across the top in bold condensed sans, subline THE ROAD IS THE POINT, date SEPT 12 and venue COAST HIGHWAY, rust and navy on a photographic coastal dusk.

Flux 2 Pro restage of the same NOMAD crossover on a rain-wet city street at night with neon reflections — Restage the same NOMAD electric crossover at night on a rain-wet city street, wet reflections, neon shop signs, the car unchanged, cinematic.

Flux 2 Pro lifestyle still of a NOMAD electric crossover charging at a cedar cabin at dusk — The same compact NOMAD electric crossover parked at a cedar cabin at dusk, charging cable plugged in, warm window light, coastal pines, wet gravel.

Pricing

Simple per-generation pricing.

3–9 credits per generation ≈ $0.03–$0.09

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 API pricing Flux 2 Pro credit cost and rates

Specs

At a glance.

Provider Black Forest Labs

Model ID flux-2-pro

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

Resolutions 0.5MP, 1MP, 2MP, 4MP

Image input Supported

Avg. time ~14s

Comparison

Flux 2 Pro vs Flux 2 Max vs Nano Banana 2

Flux 2 Pro against its Max tier and the Google flagship. All flat-priced, all on the same key.

Feature	Flux 2 Pro	Flux 2 Max	Nano Banana 2
Max resolution	4MP	4MP	4K
Avg. generation	~15s	~20s	~12s
Image input	Image prompt + strength dial	Image prompt + strength dial	Multi-image editing
Price per image	3–9 credits (≈$0.03–$0.09)	7–20 credits (≈$0.07–$0.20)	8–19 credits (≈$0.08–$0.19)
Best for	High-volume production at a balanced price	The final render where fidelity wins	Editing, search grounding, world knowledge

Specs reflect what each model supports on Apiframe today, from the live catalog.

Quickstart

How to call the Flux 2 Pro 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-pro 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-pro",
    "fluxParams": {
      "resolution": "2MP",
      "image_prompt": "https://example.com/input.jpg",
      "image_prompt_strength": 0.5,
      "output_format": "jpg"
    }
  }),
});
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-pro",
        "fluxParams": {
            "resolution": "2MP",
            "image_prompt": "https://example.com/input.jpg",
            "image_prompt_strength": 0.5,
            "output_format": "jpg"
        }
    },
)
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-pro",
        "fluxParams": {
            "resolution": "2MP",
            "image_prompt": "https://example.com/input.jpg",
            "image_prompt_strength": 0.5,
            "output_format": "jpg"
        }
    }'

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 Pro 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-pro" · "flux-2-pro"
fluxParams.resolution	string	Resolution Default:"2MP" · "0.5MP", "1MP", "2MP", "4MP"
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.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.seed	number	Reuse a number to reproduce the same result. step 1

Flux versions

Every Flux image model on Apiframe. Switch with one parameter.

Use cases

What teams build with Flux 2 Pro.

Marketing visuals at volume

Strong prompt adherence and consistent editing behavior at 3–9 credits per image make Flux 2 Pro the default tier for campaign asset pipelines.

Product imagery

Guide generations with an image prompt and a strength dial to keep a product recognizable while changing scene, lighting, or season.

Editing that stays consistent

Flux 2 holds character and brand identity through edits, retexture, recolor, or restage without the subject drifting off-model.

Draft here, finish on Max

Iterate on Pro, then re-run the winning prompt on Flux 2 Max for the highest-fidelity final, same request shape, one model id apart.

Reviews

9,800+ developers. One API.

Real Apiframe reviews from Trustpilot and G2.

Speeds up our ad creative iteration

The API integrates directly into my existing pipeline, so I can generate and iterate on image variations for Meta ads without jumping between tools. We can go from concept to a testable ad in the same day instead of spreading it across a week.

Ethan M. July 2026 G2

Fast, reliable, easy to integrate

Image generation requests are processed quickly, and the results are consistently high quality. Customer support has also been responsive whenever I had questions. It has saved me a lot of development time.

Nana Arianto July 2026 Trustpilot

Seamless integrations, effortless setup

Generating ad creatives for Facebook and Google ads is more streamlined now since we use APIFRAME to manage the workflow, which used to require a lot of time with official APIs. The initial setup was very easy, just a matter of using curl.

Bean A. July 2026 G2

Flux 2 Pro questions

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

Is Flux 2 Pro free?

No. On Apiframe it is a paid production model priced from 3 credits ($0.03) per image at 0.5MP up to 9 credits ($0.09) at 4MP, scaling with image size. The open-weight Dev variant is the free, local option.

How is it different from the other Flux 2 models?

Pro is the everyday production workhorse. Flex offers more control and typography quality at a higher price, Dev is the open-weight model for local use, and Klein is the fastest, lightest variant.

How many reference images can it use?

Up to 10 at once, for consistent characters, products, and styles.

Can it edit images, not just generate them?

Yes. It handles both text-to-image generation and image editing at up to 4MP in a single model.

Can you run it locally?

Not Pro itself, but the open-weight Dev and Klein variants are built for local and on-device use.

Where can you access it?

Through Apiframe, as well as the BFL API and major hosting partners.