Image APIActive

flux-2 API

Generate photorealistic AI images with the Flux 2 API through API in One. High-quality text-to-image and image-to-image generation. Supports Pro and Flex modes with 1K/2K resolution.

Real routes1Real endpoint rows linked to this model.

Endpoint models11Live models sharing this endpoint.

Base cost5 credits$0.05 · 3–8 seconds

Endpoint familyImage API/api/v1/images/generations

Get API Key View Docs

Model IDflux-2

Use this in the request body model field.

Endpoint/api/v1/images/generations

The currently implemented BFF route.

Outputimage

Input types: text, image

AuthBearer API key

Keys are managed by the shared dashboard.

WebhookSupported

Use callback_url on supported async tasks.

Service highlights

Marketplace-style signals backed by the current live route, without copying external SLA, discount, login, or payment claims.

Live production route

This page only shows endpoints implemented under /api/v1. /api/v1/images/generations

Webhook / polling

Use callback_url when supported, or poll the task status route for results.

Shared billing system

Top-up, orders, credit balance, and profile continue through the existing shared console.

Managed provider credentials

Your browser only holds an API in One key; provider calls stay server-side.

Call contract

Use these fields to integrate the current live model route.

Base URL: https://apiin.one
Authorization: Authorization: Bearer <API_KEY>
Model field: flux-2
Result path: /api/v1/tasks/{task_id}
Billing path: /billing/credits

Runtime behavior

This model creates an async task, returns a task_id, then resolves through the real status route.

Client request/api/v1/images/generationstask_id -> result

View usage logs

API Console

Switch between real models on this endpoint, choose a live route, and generate request examples from the current catalog payload.

Live model11 live models

Endpoint1 Routes

ProviderBlack Forest Labshttps://n41.gogloai.com

Current cost5 credits · $0.055–24 credits per image (~$0.05–$0.24)

RuntimeAsync taskAsync jobs return task_id, then use status polling.

Input / outputtext + image -> imageUse callback_url when supported, or poll the task status route for results.

Backend nodenode41Your browser only holds an API in One key; provider calls stay server-side.

Request previewPOST /api/v1/images/generations

curl --request POST \
  --url https://apiin.one/api/v1/images/generations \
  --header 'Authorization: Bearer <API_KEY>'
  --header 'Content-Type: application/json' \
  --data-raw '{
  "model": "flux-2",
  "prompt": "A serene Japanese garden with cherry blossoms, koi pond, and wooden bridge, photorealistic",
  "aspect_ratio": "16:9",
  "type": "pro",
  "resolution": "1K"
}'

Result path/api/v1/tasks/{task_id}

Open docs

Endpoint decision panel

Evaluate cost, provider coverage, and production integration behavior across live models on this implemented endpoint.

Endpoint models11These models share the same BFF route and switch through the model field.

Provider coverage10Real provider sources currently exposed by this endpoint.

Cost range4-25 credits$0.04-$0.25 · Based on the current live catalog base credit cost.

Webhook coverage5/11Models on this endpoint that support callback_url.

Current model position2/11

Sorted by base credits from low to high.

Lowest-cost route in this endpointcogview-4

Zhipu AI / WaveSpeed · 4 credits · $0.04

Production patternAsync task + webhook/polling

Use callback_url when supported, or poll the task status route for results.

Live capabilities

These capabilities come from the current model config and backend route. Unreleased APIs are not listed.

Pro and Flex modes for quality vs speed tradeoff

1K and 2K resolution support

Image

Image-to-image with up to 8 reference images

Webhook support for async workflows

Request format

Clients call same-origin API routes; the server BFF forwards to the matching Worker.

MethodEndpointCreditsPurpose

POST/api/v1/images/generations5 credits

High-quality AI image generation with excellent prompt following and photorealistic output.

Parameters

promptstring

Text description of the image (3–5000 chars)

Required

aspect_ratiostring

Output aspect ratio (e.g. 1:1, 16:9, 9:16)

Optional · Default 1:1

typestring

Generation mode: "pro" (higher quality) or "flex" (faster/cheaper)

Optional · Default pro

resolutionstring

Output resolution: "1K" or "2K"

Optional · Default 1K

input_urlsarray

Array of image URLs for image-to-image (max 8 images)

Optional

Example request

curl -X POST https://apiin.one/api/v1/images/generations \
  -H "Authorization: Bearer aio_your_api_key" \
  -H "Content-Type: application/json" \
  --data-raw '{
  "model": "flux-2",
  "prompt": "A serene Japanese garden with cherry blossoms, koi pond, and wooden bridge, photorealistic",
  "aspect_ratio": "16:9",
  "type": "pro",
  "resolution": "1K"
}'

Models on the same endpoint

These live models use the same implemented BFF endpoint and can be switched by changing the model field.

🧠cogview-4image · 4 credits/api/v1/images/generations

grok-imagineimage · 5 credits/api/v1/images/generations

kling-image-o1image · 6 credits/api/v1/images/generations✦ideogram-v3image · 8 credits/api/v1/images/generations🌐imagen-4image · 8 credits/api/v1/images/generations🤖gpt-image-1.5-officialimage · 10 credits/api/v1/images/generations

Endpoint model comparison

Compare real models behind this implemented route by cost, provider, runtime mode, input, output, and backend node.

/api/v1/images/generations11 live models

ModelProviderRoute modeInput / outputBase costBackend node

flux-2Current modelBlack Forest LabsAsync tasktext + image -> image5 credits$0.05node41🧠cogview-4Zhipu AI / WaveSpeedAsync tasktext -> image4 credits$0.04node48

grok-imaginexAIAsync tasktext -> image5 credits$0.05node31

kling-image-o1Kuaishou / WaveSpeedAsync tasktext + image -> image6 credits$0.06node49✦ideogram-v3IdeogramAsync tasktext + image -> image8 credits$0.08node63🌐imagen-4GoogleAsync tasktext -> image8 credits$0.08node47🤖gpt-image-1.5-officialOpenAIAsync tasktext + image -> image10 credits$0.10node42🎨recraft-v4RecraftAsync tasktext -> image10 credits$0.10node78✦ideogram-v4IdeogramAsync tasktext -> image12 credits$0.12node63

seedream-4-5ByteDance / KIEAsync tasktext + image -> image12 credits$0.12node30🏔️hunyuan-image-3Tencent / WaveSpeedAsync tasktext + image -> image25 credits$0.25node68

Integration flow

These steps use the current live route and shared account system; login, payment, orders, credits, and profile remain shared.

Create a shared API key

Create a key in the existing dashboard. Top-up, orders, credit balance, and profile stay in the shared console.

Call the real endpoint

Send a request with the endpoint, model id, and parameters shown on this page. /api/v1/images/generations

Poll task status

Async media and tool jobs use /api/v1/tasks/{task_id}; chat models return a direct response.

Task status route

After creating image, video, audio, or tool tasks, poll the real task endpoint for results.

GET/api/v1/tasks/{task_id}Check generation task status and result.

Pricing

5–24 credits per image (~$0.05–$0.24)

Base cost$0.05

Credits5

BillingSuccessful requests

Use cases

These workflows are supported by the current model and backend node.

Generate product mockups and marketing visuals from text descriptions

Create AI-generated artwork and illustrations for content

Build AI image generation features into your application

Produce photorealistic stock images on demand

FAQ

How much does the Flux 2 API cost?

Credits vary by mode and resolution. Pro mode at 1K costs 5 credits, 2K costs 7 credits. Flex mode at 1K costs 14 credits, 2K costs 24 credits. Manage balance through the shared billing console.

What is the difference between Pro and Flex mode?

Pro mode produces higher quality results. Flex mode is faster and cheaper, suitable for rapid iteration. Set the "type" parameter to "pro" or "flex".

Can I use reference images?

Yes. Flux 2 supports image-to-image by providing up to 8 input image URLs via the "input_urls" parameter alongside your text prompt.

What resolutions are supported?

Flux 2 supports 1K and 2K resolution output. Set via the "resolution" parameter.

How do I call Flux 2?

Use POST /api/v1/images/generations with model "flux-2", then poll the returned task ID through /api/v1/tasks/{task_id}.