ecohash-ai/image-generation

Image Generation

Generate images from text with Z-Image-Turbo or Qwen-Image. Each request reports the latency you actually experienced, the output resolution, and the exact cost of that image.

Both models are served by EcoHash on our own NVIDIA RTX PRO 6000 Blackwell (96 GB) fleet — not resold from a third party — through one OpenAI-compatible endpoint at https://api.ecohash.com/v1.

The two models

Z-Image-Turbo is a 6B model tuned for throughput, with bilingual text rendering. At $0.01 per image it is cheap enough to put inside a product loop rather than behind a button someone clicks once.

Qwen-Image is the stronger of the two on typography and fine detail, at $0.03 per image.

Both render text inside the image in English and Chinese — try the bilingual poster prompts in the examples.

Reproducing it

import base64
from openai import OpenAI

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

result = client.images.generate(
    model="z-image-turbo",       # or "qwen-image"
    prompt="Your prompt",
    size="1024x1024",
    response_format="b64_json",
)
image_bytes = base64.b64decode(result.data[0].b64_json)

Notes

• —Use your own API key. The demo runs on EcoHash's key with 5 free runs per visitor per day. Paste your own key into the panel at the top to lift that limit — it is held for your browser session only, never stored and never logged. New accounts get $1 of free credit, which is thousands of requests on these models.
• —Billing is 1,000 tokens per image, so cost is flat per image regardless of prompt length; see the price list.
• —Generated images are not retained by this Space.

Links

Model catalog · Pricing · Documentation · GPU instances from $1.89/GPU-hour · Get an API key — $1 free credit