FLUX 2 [pro] by Black Forest Labs — zero-config generation with automatic prompt upsampling. $0.03/MP, up to 4K resolution.
Multiple FLUX 2 variants for different quality, speed, and control trade-offs — all on the same Runflow API.
Production-grade — zero-config, automatic prompt upsampling, $0.03/MP
Adjustable inference steps and guidance scale for fine control, $0.05/MP
Maximum quality variant — highest fidelity in the FLUX 2 family
Speed-optimised — lowest latency for real-time and preview workflows
Every model on Runflow is scored per vertical — not generic leaderboard numbers. Scores come from domain-expert evaluation on real production prompts.
| Use Case | Assessment | Notes |
|---|---|---|
| Portrait | Strong | High photorealism with automatic prompt refinement |
| Fashion | Strong | Style transfer and editorial quality generation |
| Product | Strong | Clean, accurate rendering with minimal configuration |
| Creative | Strong | Supports JSON prompts, HEX colour codes, and @ image references |
| Quality | Output Size | Megapixels | Price |
|---|---|---|---|
| 1024 × 1024 | 1 MP | $0.030 | |
| 1920 × 1080 | ~2 MP | $0.045 | |
| 2048 × 2048 | ~4 MP | $0.075 | |
| 4096 × 4096 | ~16 MP | $0.255 |
Rounded up to nearest megapixel. Cold starts (5–10s) not billed.
Full parameter reference for the flux-2-pro model endpoint.
| Parameter | Type | Description |
|---|---|---|
| prompt | string | Text description of the image to generate. |
| image_size | object | string | Output size. Presets: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9. Or custom {width, height} up to 4096×4096. Default: landscape_4_3. |
| output_format | string | Output format. Options: "jpeg", "png". Default: "jpeg". |
| safety_tolerance | string | Content moderation strictness. 1 = most strict, 5 = most permissive. Default: 2. |
| enable_safety_checker | boolean | Enable NSFW content filtering. Default: true. |
| seed | integer | Random seed for reproducible outputs. |
| sync_mode | boolean | Return media as data URI without storing in request history. Default: false. |
Flux AI models are available on many platforms. Here's what makes the Runflow image generation API different.
No guidance_scale or inference steps to tune — FLUX 2 [pro] automatically optimises every generation for best quality.
The model refines your prompt internally for better interpretation — shorter prompts produce better results than with most other models.
$0.03 for the first megapixel, $0.015 per additional MP. A 1024×1024 image costs $0.03; a 1920×1080 image costs $0.045.
Supports JSON-structured prompts for granular scene control, HEX colour codes, and @ symbol image referencing for multi-image workflows.
Every output is scored by Runflow's Sentinel system before delivery, catching low-quality or off-prompt results automatically.
Real production use cases teams run on FLUX 2 [pro] today.
Generate polished ad creatives featuring your product across angles, settings, and styles — ready to push to paid social campaigns without a photo shoot.
Rapidly ideate static key art, movie banners, and poster concepts — giving creative directors a visual starting point before committing to production.
Power the pro-tier of a design SaaS with a high-quality backbone model that handles scaled traffic reliably — no per-user GPU provisioning.
Turn a quick phone snap of a dish into multiple upsampled, appetite-worthy versions ready for menus, delivery apps, and social ads.
Same API, different strengths. Switch models with one parameter change.
Black Forest Labs
FLUX.1 [dev] is a 12B-parameter text-to-image model by Black Forest Labs. Open-w…
ByteDance
Seedream 4.5 by ByteDance — unified generation and editing in one model. Strong…
ByteDance
Seedream 4 by ByteDance — unified generation and editing model with photorealism…
Nano Banana 2 by Google — fast image generation across 4 resolution tiers (0.5K–…
OpenAI
GPT-Image 1.5 by OpenAI — high-fidelity images with strong prompt adherence. Thr…
Nano Banana Pro by Google — premium image generation with sharp detail and natur…
Get API access in minutes. No GPU setup, no infrastructure to manage. Pair with Sentinel to control the quality of every AI-generated image you ship.