Qwen API Skill for RunAPI

Configure OpenAI-compatible clients to use Qwen text models on RunAPI.

Model Reference | Skill Repo | All Models

Call Qwen text models through RunAPI with the official OpenAI SDK or any OpenAI-compatible client. Point clients at https://runapi.ai/v1, send qwen3-next-80b-a3b-instruct, and pay through one RunAPI balance. This skill teaches Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents how to wire Qwen text requests through RunAPI.

The canonical agent file is skills/qwen/SKILL.md.

Install the skill

npx skills add runapi-ai/qwen -g

Or paste this prompt to your AI agent:

Install the qwen skill for me:

1. Clone https://github.com/runapi-ai/qwen
2. Copy the skills/qwen/ directory into your
   user-level skills directory (e.g. ~/.claude/skills/
   for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.

Use Qwen on RunAPI

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_RUNAPI_TOKEN",
    base_url="https://runapi.ai/v1",
)

response = client.chat.completions.create(
    model="qwen3-next-80b-a3b-instruct",
    messages=[{"role": "user", "content": "Hello, Qwen!"}],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_RUNAPI_TOKEN",
  baseURL: "https://runapi.ai/v1",
});

const response = await client.chat.completions.create({
  model: "qwen3-next-80b-a3b-instruct",
  messages: [{ role: "user", content: "Hello, Qwen!" }],
});
console.log(response.choices[0].message.content);

Get a RunAPI API Key at https://runapi.ai/api_keys.

Supported Qwen text models

Model ID	Notes
qwen3-next-80b-a3b-instruct	Qwen text chat and instruction-following workloads

Routing

• Qwen API on RunAPI: https://runapi.ai/models/qwen
• Provider page: https://runapi.ai/providers/alibaba
• Browse the full RunAPI catalog: https://runapi.ai/models
• Skill repository: https://github.com/runapi-ai/qwen

Agent rules

• Keep API keys in OPENAI_API_KEY or your secret manager; never inline them in commits or shell history.
• Stream long responses (stream: true) so the agent can release the terminal/IO loop early.
• This skill is for Qwen text models. Use the Qwen 2 skill for image generation.
• For pricing, rate-limit, and commercial-usage answers, link to https://runapi.ai/models/qwen rather than this README.

License

Licensed under the Apache License, Version 2.0.