# Real-ESRGAN (Real-ESRGAN) — API pricing and providers

> Fast image upscale. Model id `xinntao/real-esrgan`. Image model by Real-ESRGAN.

- Page: https://infro.io/models/xinntao/real-esrgan
- Vendor: Real-ESRGAN (https://infro.io/models/xinntao)
- Modality: Image
- Endpoint through INFRO: `POST /v1/images/generations` at https://api.infro.io/v1
- List rate: $0.0020 per image
- Rates checked: 2026-10-05

Rates are Real-ESRGAN's published list price: what the customer's own provider account bills, not an INFRO charge. INFRO is a BYOK control plane; it charges a software subscription and adds 0% to model spend.

## Providers that serve it

| Provider | Model id sent |
| --- | --- |
| Replicate | `nightmareai/real-esrgan` |

## Questions

### How much does the Real-ESRGAN API cost?

Real-ESRGAN's published list rate for Real-ESRGAN is $0.0020 per image (checked 2026-10-05). The provider account you connect bills you at the rate on that account, so a negotiated rate replaces the list rate. INFRO adds 0% to model spend.

### Which providers serve Real-ESRGAN?

In INFRO's provider registry, Real-ESRGAN can be served by Replicate. You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.

### What is the Real-ESRGAN model ID?

Request it from INFRO as "xinntao/real-esrgan". INFRO sends each provider its own id: Replicate "nightmareai/real-esrgan".

### How do I call Real-ESRGAN through an OpenAI-compatible API?

Point an OpenAI SDK, or any HTTP client, at https://api.infro.io/v1 with an INFRO gateway key and send model "xinntao/real-esrgan" to POST /v1/images/generations. INFRO runs the request on a provider account you connected and returns the provider's response with an estimated cost.

### Does INFRO mark up Real-ESRGAN usage?

No. Real-ESRGAN or the provider you connect bills model usage to your own account. INFRO charges a software subscription for routing, failover, observability, budgets and policy, and takes 0% of model spend.