---
title: "Qwen 3 API — Variants, pricing & model skill"
url: "https://runapi.ai/models/qwen-3.md"
canonical: "https://runapi.ai/models/qwen-3.md"
locale: "en"
model: "Qwen 3"
provider: "Alibaba"
modality: "image"
variant_count: 4
price_from_cents: 5
---

# Qwen 3 API

Qwen 3 image generation and editing in standard and Pro tiers.

**Provider:** Alibaba
**Modality:** Image
**Catalog:** 4 variants

The Qwen 3 API delivers a strong quality-to-cost ratio in the image space. Multiple variants let you pick the tier that matches your latency, quality, and budget targets — start on a fast or lite variant for prototyping, then graduate to pro or max for production. Install the Qwen 3 skill to bring docs, typed schemas, pricing notes, and step-by-step setup into your coding workspace. The skill works with Claude Code, Codex, Gemini CLI, Cursor, and VS Code, so your agent has the right context before you write integration code. All variants share a single RunAPI API key, unified billing in USD, and the same async task lifecycle — submit, poll or stream, and receive results via webhook callback.

## Variants

| Version | Variant | Pricing | Billing | URL |
|---|---|---|---|---|
| qwen-3-edit-image | `edit-image` | $0.070 | call | https://runapi.ai/models/qwen-3/edit-image.md |
| qwen-3-pro-edit-image | `pro-edit-image` | $0.140 | call | https://runapi.ai/models/qwen-3/pro-edit-image.md |
| qwen-3-pro-text-to-image | `pro-text-to-image` | $0.120 | call | https://runapi.ai/models/qwen-3/pro-text-to-image.md |
| qwen-3-text-to-image | `text-to-image` | $0.050 | call | https://runapi.ai/models/qwen-3/text-to-image.md |


## Install the skill

```sh
npx skills add runapi-ai/qwen-3 -g
```

The skill gives your coding tool the model docs, schemas, pricing notes, and setup steps needed to add Qwen 3 features to an application.

## Context

The Qwen 3 API exposes a image model from Alibaba, accessible through RunAPI with a single API key and per-call billing. Developers call Qwen 3 the same way they call any other model in the RunAPI catalog — set the model parameter, submit a request, and receive structured JSON. The model skill packages docs, typed schemas, pricing notes, and setup steps so your coding agent has the right context before you write integration code. Billing is unified across all providers, failed generations are never charged, and results are retrievable by task ID.

## FAQ

### Which variant should I start with?

Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.

### Is there a free tier?

New accounts get free first calls on every model. After that, pay per call.

### Do you stream results?

Where streaming is available, RunAPI streams end-to-end.

### How are failures billed?

Failed generations are not charged.

### Are outputs cached?

Generated outputs are stored and retrievable by task ID. Inputs are not cached.

### Can I use commercially?

Yes — commercial use is included for every variant unless a model license explicitly restricts it, which is called out on the variant page.

### What about rate limits?

Per-key rate limits scale with usage tier. See pricing page for current limits.

### Where can I report issues?

Open an issue on the public GitHub repo or email support.