Output image
Output billing uses the 1MP, 2MP, 3MP, and 4MP tiers.
| Variant | Tier | Current Price | Official Price | Your Savings |
|---|---|---|---|---|
flux-2-pro | 1MP | |||
| 2MP | ||||
| 3MP | ||||
| 4MP | ||||
flux-2-max | 1MP | |||
| 2MP | ||||
| 3MP | ||||
| 4MP | ||||
flux-2-flex | 1MP | |||
| 2MP | ||||
| 3MP | ||||
| 4MP |
FLUX.2 is a three-model image generation and editing family: Pro balances speed, quality, and cost for production, Max targets the highest output quality, and Flex adds adjustable steps and guidance for fine control and typography.

Image link valid for 72 hours
FLUX.2 billing adds the output MP price to the reference-image MP price.
Output billing uses the 1MP, 2MP, 3MP, and 4MP tiers.
| Variant | Tier | Current Price | Official Price | Your Savings |
|---|---|---|---|---|
flux-2-pro | 1MP | |||
| 2MP | ||||
| 3MP | ||||
| 4MP | ||||
flux-2-max | 1MP | |||
| 2MP | ||||
| 3MP | ||||
| 4MP | ||||
flux-2-flex | 1MP | |||
| 2MP | ||||
| 3MP | ||||
| 4MP |
A single reference image uses its actual pixel tier, up to 4MP. With two or more images, each is billed at 1MP.
| Variant | Tier | Current Price | Official Price | Your Savings |
|---|---|---|---|---|
flux-2-pro | 1MP | |||
| 2MP | ||||
| 3MP | ||||
| 4MP | ||||
flux-2-max | 1MP | |||
| 2MP | ||||
| 3MP | ||||
| 4MP | ||||
flux-2-flex | 1MP | |||
| 2MP | ||||
| 3MP | ||||
| 4MP |
* Final charges follow the actual generation parameters.
Generate or edit images with FLUX.2 Pro, Max, and Flex. Every variant accepts up to 8 public reference images, supports 1MP, 2MP, 3MP, and 4MP tiers, and can use exact dimensions up to 4 MP.
50K+
Active Users
99.9%
Uptime
2x
Faster
70%
Cost Savings
Documented controls shared by Pro, Max, and Flex, with Flex-only tuning clearly identified
Create a key, submit a generation task, and poll for its result.
Create your APIMart account and add sufficient balance before submitting FLUX.2 tasks.
Create an API key in the dashboard and send it as a Bearer token.
POST to /v1/images/generations, then poll /v1/tasks/{task_id} until the task completes. Use the returned cost as the final charge.
“Flux 2 Pro delivers stunning photorealism—especially with multiple references. The Flux 2 lighting and textures feel incredibly lifelike for our product campaigns.”
Creative Director at DesignWorks
“Flux 2's typography rendering is exceptional. Finally, a model that handles text in mockups cleanly without artifacts or blur.”
UI/UX Designer
“The Flux 2 multi-reference feature helped me keep character styles consistent across my entire illustration series. Game-changer!”
Freelance Illustrator
“Editing existing images with Flux 2's natural language is so intuitive. Just describe what you want changed and Flux 2 works remarkably well.”
Marketing Manager
“Flux 2 Flex's quality vs speed control is super helpful when iterating designs. Flux 2 saved us hours in the creative review process.”
Brand Strategist
“The precise color control with hex codes in Flux 2 gives us exactly the brand colors we need. No more post-processing adjustments!”
Art Director at AdVision
FLUX.2 Pro, Max, and Flex each accept up to 8 reference-image URLs. The URLs must be publicly accessible.
Choose Pro for balanced speed, quality, and cost, Max when the highest output quality matters most, and Flex when you need adjustable steps, guidance, or stronger layout control.
No. These controls are exclusive to flux-2-flex: steps accepts 1–50 and guidance accepts 1.5–10. Pro and Max do not expose them.
Use 1MP, 2MP, 3MP, or 4MP with any of 9 ratios, or provide width and height of at least 64 px with a total output limit of 4 MP. Formats are PNG, JPEG, and WebP.
POST /v1/images/generations returns a task ID. Poll GET /v1/tasks/{task_id} until the task is completed or failed; each task returns one image.
The charge depends on the selected output tier or exact dimensions and the number of reference images. Use the completed task's cost field as the source of truth. Failed tasks are automatically refunded in full.
Explore more models in the same category.

Nano banana pro
Nano Banana 2 API is powered by Google's Gemini 3 Pro Image Preview- the most advanced AI image generation model with 4K native output, multi-step planning workflow, and built-in quality analysis. Features 340% faster processing and professional-grade editing capabilities.

Nano banana
Nano Banana (gemini-2.5-flash-image-preview) is Google DeepMind's fast, conversational image generation and editing model. It delivers natural-language text-to-image, precise multi-turn edits, strong character consistency, and multi-image fusion at low latency.

Seedream 5.0 Pro
Seedream 5.0 Pro (seedream-5-0-pro) is quality-first text-to-image model. It produces cinematic 1K and 2K images with best-in-class text rendering, supports up to 10 reference images for style and character consistency, and unifies generation and editing in a single API call.

Midjourney
Midjourney is a leading text-to-image AI model renowned for its painterly aesthetics, strong composition, and cinematic lighting. Generate high-quality images from text prompts or reference images, with fine-grained control over style, aspect ratio, and creative parameters — accessible programmatically through APIMart's unified API, no Discord required.