Image generation

Generate images with FLUX.1 Schnell via POST /v1/images/generations — OpenAI-compatible shape.

Basic request

curl https://api.ecohash.com/v1/images/generations \
  -H "Authorization: Bearer eco_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-1-schnell",
    "prompt": "a watercolor painting of a fox in a misty forest, soft light",
    "size": "1024x1024",
    "n": 1,
    "response_format": "b64_json"
  }'

Response:

{
  "created": 1776391234,
  "data": [{
    "b64_json": "iVBORw0KGgo...",
    "revised_prompt": null
  }]
}

Decode the base64 to get the PNG bytes.

Parameters

Parameter	Type	Default	Notes
model	string	—	Required. Currently "flux-1-schnell"
prompt	string	—	Required. Max ~1000 characters
size	string	"1024x1024"	One of 512x512, 768x768, 1024x1024, 1024x768, 768x1024
n	integer	1	Number of images. Currently only n=1 is supported
response_format	string	"b64_json"	"b64_json" returns inline base64; "url" returns a hosted URL (24h expiry)
seed	integer	random	Non-OpenAI extension — deterministic generation when set

Python example

from openai import OpenAI
import base64

client = OpenAI(api_key="eco_...", base_url="https://api.ecohash.com/v1")

resp = client.images.generate(
    model="flux-1-schnell",
    prompt="a cyberpunk cityscape at sunset, neon reflections",
    size="1024x1024",
    response_format="b64_json",
)

image_bytes = base64.b64decode(resp.data[0].b64_json)
with open("out.png", "wb") as f:
    f.write(image_bytes)

Tips

• FLUX.1 Schnell is a 4-step model. It's fast (~1–2 seconds for 1024×1024) but less controllable than FLUX.1 Dev. Use short, focused prompts; long negative-prompt systems aren't necessary.
• Describe the subject, style, lighting, mood. "a golden retriever wearing a top hat, oil painting, Rembrandt lighting" beats "a dog in a hat."
• Use seed if you need reproducible output for testing.
• Horizontal vs vertical — use 1024x768 for landscapes, 768x1024 for portraits.

Billing

Image generation bills per image at a flat rate. Typical cost per 1024×1024 image is in the single-digit cents range.

Try it in the playground

See Playground for an interactive UI where you can iterate prompts visually before writing code.