# Qwen-Image 3.0 (Alibaba) — API pricing and providers

> Image generation & typography. Model id `qwen/qwen-image-3`. Image model by Alibaba.

- Page: https://infro.io/models/qwen/qwen-image-3
- Vendor: Alibaba (https://infro.io/models/alibaba)
- Modality: Image
- Endpoint through INFRO: `POST /v1/images/generations` at https://api.infro.io/v1
- List rate: $0.03 per image
- Rates checked: 2026-10-05

Rates are Alibaba'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 |
| --- | --- |
| OpenRouter | `qwen/qwen-image-3` |
| fal.ai | `qwen-image-3` |
| Replicate | `alibaba/qwen-image-3` |

## Questions

### How much does the Qwen-Image 3.0 API cost?

Alibaba's published list rate for Qwen-Image 3.0 is $0.03 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 Qwen-Image 3.0?

In INFRO's provider registry, Qwen-Image 3.0 can be served by OpenRouter, fal.ai and Replicate. You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.

### What is the Qwen-Image 3.0 model ID?

Request it from INFRO as "qwen/qwen-image-3". INFRO sends each provider its own id: OpenRouter "qwen/qwen-image-3", fal.ai "qwen-image-3", Replicate "alibaba/qwen-image-3".

### How do I call Qwen-Image 3.0 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 "qwen/qwen-image-3" 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 Qwen-Image 3.0 usage?

No. Alibaba 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.