qwen

Call the Qwen text API (qwen3-next-80b-a3b-instruct) through RunAPI using the official OpenAI SDK or compatible clients. Use when the user asks for Qwen text chat, streaming completions, Anthropic or Gemini protocol compatibility, or when they want to point an existing OpenAI SDK setup at RunAPI as the base URL.

RunAPI@runapi-ai

Install

openclaw skills install @runapi-ai/runapi-qwen

Qwen Text on RunAPI

Use the official OpenAI SDK or any OpenAI-compatible HTTP client and switch the base URL to https://runapi.ai/v1. This skill covers Qwen text models. For Qwen image generation, install the separate Qwen 2 skill.

Setup

dotenv

OPENAI_API_KEY=YOUR_RUNAPI_TOKEN
OPENAI_BASE_URL=https://runapi.ai/v1

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

Core recipe - Chat Completions

python

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": "Write a concise API migration note."}],
)
print(response.choices[0].message.content)
print(response.usage)

typescript

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: "Write a concise API migration note." }],
});

Streaming

python

stream = client.chat.completions.create(
    model="qwen3-next-80b-a3b-instruct",
    messages=[{"role": "user", "content": "Write a compact implementation plan."}],
    stream=True,
)
for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

Streaming runs through a regional edge proxy so the request does not hold a Rails/Puma thread. Long generations should always stream.

Protocol compatibility

Qwen text models are also available through RunAPI's Anthropic-compatible and Gemini contents client surfaces. RunAPI bridges those request and response shapes to the OpenAI-compatible chat request format, so use these protocol paths only when an existing tool expects those formats:

bash

curl -X POST "https://runapi.ai/v1/messages" \
  -H "x-api-key: YOUR_RUNAPI_TOKEN" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-next-80b-a3b-instruct",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Draft a concise answer."}]
  }'

bash

curl -X POST \
  "https://runapi.ai/v1beta/models/qwen3-next-80b-a3b-instruct:streamGenerateContent" \
  -H "x-goog-api-key: YOUR_RUNAPI_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"contents":[{"role":"user","parts":[{"text":"Hello!"}]}]}'

For new app code, prefer the OpenAI-compatible setup.

List models

bash

curl https://runapi.ai/v1/models \
  -H "Authorization: Bearer YOUR_RUNAPI_TOKEN"

Supported models

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

References

Model overview, pricing, and rate limits: https://runapi.ai/models/qwen.md
Provider comparison: https://runapi.ai/providers/alibaba.md
Catalog: https://runapi.ai/models.md

Agent rules

Keep API keys in OPENAI_API_KEY, RUNAPI_TOKEN, or a secret manager; never inline them in commits or shell history.
Default new integrations to the OpenAI-compatible client at https://runapi.ai/v1.
Use streaming for responses longer than a few hundred tokens.
For Qwen image generation, use the Qwen 2 model skill instead of this text LLM skill.
For pricing, rate-limit, and commercial-usage answers, link to https://runapi.ai/models/qwen.md rather than copying values.