How much does Proteus v0.3 cost?

It is billed by GPU time on an L40S. A typical 25-second generation is about $0.024, roughly 41 runs per dollar. Predict time varies significantly with your settings, so heavier runs cost proportionally more. Current rates are shown in the Hormouz dashboard.

How does v0.3 differ from v0.2?

v0.3 is the anime update. It is retuned for anime key visuals, character art and illustration, and defaults to the DPM++2MSDE sampler rather than KarrasDPM. v0.2 remains the better pick for photographic and general-purpose subjects.

What output size should I use?

The model recommends 1024 or 1280 pixels per side. You can request up to four images in a single run, though more outputs means a longer run and therefore a higher cost.

How is Proteus v0.3 served on Hormouz?

Behind an asynchronous predictions API: submit a prediction, then poll until the images are ready. Point your base URL at Hormouz and use a Hormouz key.

proteus-v0.3: image generation model

Proteus v0.3 is the anime update of the Proteus SDXL family — retuned for anime and illustration, with text-to-image, image-to-image and inpainting up to 1280px. Served asynchronously through Hormouz from inside Iran.

Pricing:: ~$0.000975 / sec (Nvidia L40S GPU)
Type:: image

Image generation

Proteus v0.3 is the anime-focused release of the Proteus line. It keeps the prompt adherence the family is known for and retunes the model for anime key visuals, character art and illustration — the subject matter earlier versions handled least well.

It supports the same three modes as v0.2: text-to-image from a prompt, image-to-image with prompt_strength controlling how far the result departs from your source, and inpainting where a mask marks the region to regenerate.

Recommended output is 1024 or 1280 pixels per side, and up to four images per run. The default sampler is DPM++2MSDE, one of eight available schedulers, and denoising steps run from 1 to 100 — the model's notes suggest 20 for speed and up to 60 for more detail.

Billing is by GPU time on an L40S rather than a flat per-image rate. A typical generation takes about 25 seconds and works out around $0.024, though the model notes that predict time varies significantly with the settings you choose. Hormouz provides stable access from inside Iran, with no foreign credit card or circumvention tooling required.

Quickstart

# Create the prediction, then poll until succeeded
curl -s https://api.hormouz.net/v1/predictions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"version":"datacte/proteus-v0.3","input":{"prompt":"A beautiful sunset"}}'

Specs

Vendor	Datacte
Type	Image
Context window	—
Pricing	~$0.000975 / sec (Nvidia L40S GPU)
API	predictions

Code example

cURL

# Create the prediction, then poll until succeeded
curl -s https://api.hormouz.net/v1/predictions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"version":"datacte/proteus-v0.3","input":{"prompt":"A beautiful sunset"}}'

Python

import requests
BASE = "https://api.hormouz.net/v1"
H = {"Authorization": "Bearer ng-YOUR_API_KEY", "Content-Type": "application/json"}
r = requests.post(f"{BASE}/predictions", headers=H,
    json={"version": "datacte/proteus-v0.3", "input": {"prompt":"A beautiful sunset"}})
print(r.json()["id"])

JavaScript

const BASE = "https://api.hormouz.net/v1";
const res = await fetch(`${BASE}/predictions`, {
  method: "POST",
  headers: { Authorization: "Bearer ng-YOUR_API_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({ version: "datacte/proteus-v0.3", input: {"prompt":"A beautiful sunset"} }),
});
const { id } = await res.json();

Buy the proteus-v0.3 API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches proteus-v0.3 and 600+ other models, and you pay only for what you use.
No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.

Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Proteus v0.3 cost?: It is billed by GPU time on an L40S. A typical 25-second generation is about $0.024, roughly 41 runs per dollar. Predict time varies significantly with your settings, so heavier runs cost proportionally more. Current rates are shown in the Hormouz dashboard.
How does v0.3 differ from v0.2?: v0.3 is the anime update. It is retuned for anime key visuals, character art and illustration, and defaults to the DPM++2MSDE sampler rather than KarrasDPM. v0.2 remains the better pick for photographic and general-purpose subjects.
What output size should I use?: The model recommends 1024 or 1280 pixels per side. You can request up to four images in a single run, though more outputs means a longer run and therefore a higher cost.
How is Proteus v0.3 served on Hormouz?: Behind an asynchronous predictions API: submit a prediction, then poll until the images are ready. Point your base URL at Hormouz and use a Hormouz key.

Updated 2026-10-13