Generate · Edit

Image (gen / edit)

Beta

Generate images from text and edit them from reference images with Qwen-Image, Qwen-Image-Edit and FLUX 3 Klein, running on Grid GPUs.

Overview

Image (gen / edit)

Runs the `flux3-klein-local` model (FLUX 3 Klein) on Grid GPUs. Send JSON to `POST /v1/images/local/generations` with prompt (required), size (default "1024x1024"), seed (optional), steps (default 16, 1–50), and guidance_scale (accepted for compatibility but ignored: FLUX 3 Klein is step-distilled and uses no CFG); the response is OpenAI-style `{"data":[{"b64_json":...}]}` (n must be 1, response_format is "b64_json" only). For editing, send a reference image (PNG / JPEG / WebP) and a prompt as multipart to `POST /v1/images/local/edits`. Bearer API key auth; billed per image.

Endpoint: /v1/images/local/generations
Example model: flux3-klein-local

API

API example

curl https://api.openalchemy.io/v1/images/local/generations \
  -H "Authorization: Bearer $OPENALCHEMY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux3-klein-local",
    "prompt": "A neon-lit Tokyo alley at dusk, photorealistic.",
    "size": "1024x1024",
    "steps": 16,
    "response_format": "b64_json"
  }' \
  | jq -r '.data[0].b64_json' | base64 -d > image.png

Status

Quota and pricing (per project)

Allotments and rate limits apply to the project that issued the API key. A second domain-scoped policy layer constrains which origins may invoke each modality.

Read the docs for this modality →

START TODAY

Ready to turn inference cost into something closer to alchemy?

Get started free See pricing