Use the Qwen Image API via RunAPI with a model skill, unified auth, and pay-as-you-go pricing.
curl -X POST https://runapi.ai/api/v1/qwen_image/edit_image \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen-image-text-to-image",
"image_url": "https://cdn.runapi.ai/public/samples/image.jpg",
"prompt": "Create a cinematic travel poster for Hangzhou at dusk, with clear bilingual title text reflected across the lake."
}'import { QwenImageClient } from "@runapi.ai/qwen-image";
const client = new QwenImageClient();
const result = await client.editImage.run({
model: "qwen-image-text-to-image",
image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
prompt: "Create a cinematic travel poster for Hangzhou at dusk, with clear bilingual title text reflected across the lake.",
});require "runapi/qwen_image"
client = RunApi::QwenImage::Client.new
result = client.edit_image.run(
model: "qwen-image-text-to-image",
image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
prompt: "Create a cinematic travel poster for Hangzhou at dusk, with clear bilingual title text reflected across the lake."
)npx skills add runapi-ai/qwen-image -g# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
# Codex
codex plugin install runapi-mcp@agents
# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursorQwen Image is Alibaba's visual generation family for creating new images, remixing source images, and applying precise edits from natural-language instructions. It combines strong language-to-visual alignment with reliable text rendering and semantic image editing.
| Endpoint | Resolution | Duration | Price | |
|---|---|---|---|---|
| edit_image | — | — | $0.06 / image |
Prices shown for qwen-image-edit-image. Other variants retain their own endpoint pricing.
Sign up and generate an API key from the dashboard.
Choose the version that best matches your quality and cost requirements.
Submit your prompt and parameters to the model's documented endpoint.
Poll the task or set a webhook, then download the completed output.
Qwen Image is the original Alibaba image model line, distinct from the newer Qwen 2 generation. Through RunAPI, its generation, remix, and edit endpoints use separate model IDs and a consistent task contract.
A single RunAPI API key unlocks the whole model catalog across all providers. No separate accounts to create, no API keys to rotate per integration, and no credential management overhead. Add a new model to your app by changing one parameter.
Per-call pricing in USD, billed monthly into a single invoice. No subscription tiers, no minimum spend, and failed generations are never charged. The pricing page and check_pricing API show exact costs before you commit to a model.
Typed schemas, parameter constraints, and setup notes are packaged in the model skill so your implementation starts from the right contract. The skill loads into Claude Code, Codex, Gemini CLI, Cursor, and VS Code — your agent knows the correct request shape before you write a line of code.
Create an image from a prompt, remix a source image while guiding the new result, or apply text-driven edits to an existing image.
They are separate model generations with different RunAPI model IDs. Choose Qwen Image when you need this original generation, remix, or edit workflow without conflating it with Qwen 2.
Yes. Strong text rendering, including Chinese and English, is a core capability of the Qwen Image family.
Remix reinterprets a source image under a new prompt, while edit applies more precise instructions to change selected content while preserving the rest of the composition.
Yes. The edit model follows natural-language instructions to add, remove, or alter visual elements while retaining relevant scene context.
Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.