STABLE DIFFUSION API
Generate images with one API call.
Send a prompt, get an image back. SDXL, Stable Diffusion 3.5 and FLUX.1 through one OpenAI-compatible images endpoint, with control over size, steps and seed.
Hand this to your agent
Add a Runcrate model to this project: run curl -fsSL"https://runcrate.ai/agents.md?intent=build"and follow it.
Your agent asks for an API key. Create a key
Quick start
Hand it to your agent. Or read the request it sends.
Your agent writes and runs it. The same key works for every model and every GPU.
Available models
Models you can call today. Billed prices, as charged.
| Model | Maker | Price | Detail |
|---|---|---|---|
| stabilityai/stable-diffusion-3-5-large | Stability AI | $0.0813 per image | SD 3.5 Large, strong prompt following |
| black-forest-labs/FLUX.1-dev | Black Forest Labs | $0.0313 per image | 12B params, photorealistic |
| black-forest-labs/FLUX.1-schnell | Black Forest Labs | $0.00375 per image | 4-step generation, fast |
Why Runcrate
Built for production. One key, one balance.
Multiple architectures
SDXL for its fine-tune ecosystem, FLUX for photorealism. Pick the right model for your quality and speed requirements.
Configurable output
Control resolution, aspect ratio, inference steps, and guidance scale to fine-tune the output for your specific needs.
No GPU setup
Skip the PyTorch, diffusers, and CUDA setup. One API call generates an image. Scale from one image to thousands without infrastructure changes.
Fast generation
FLUX.1 Schnell generates images in 4 steps for fast results. SDXL and FLUX.1 Dev offer higher quality with more steps.
FAQ