Use the Qwen API via RunAPI with a model skill, unified auth, and pay-as-you-go pricing.
# Base URL
https://runapi.ai
# Endpoints
POST /v1/chat/completions
POST /v1/responses
POST /v1/messages
POST /v1beta/models/{model}:generateContent
POST /v1beta/models/{model}:streamGenerateContent
curl https://runapi.ai/v1/chat/completions \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3.6-35b-a3b",
"messages": [
{
"role": "user",
"content": "Read this screenshot of a failing dashboard, explain what the error message means, and suggest the code change that would fix it."
}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://runapi.ai/v1",
api_key="your-runapi-key"
)
response = client.chat.completions.create(
model="qwen3.6-35b-a3b",
messages=[{"role": "user", "content": "Read this screenshot of a failing dashboard, explain what the error message means, and suggest the code change that would fix it."}]
)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://runapi.ai/v1",
apiKey: "your-runapi-key"
});
const response = await client.chat.completions.create({
model: "qwen3.6-35b-a3b",
messages: [{ role: "user", content: "Read this screenshot of a failing dashboard, explain what the error message means, and suggest the code change that would fix it." }]
});Qwen is Alibaba's family of open-weight language models, released under Apache 2.0. On RunAPI, the Qwen3.5 models (397B-A17B, 122B-A10B, 27B, 35B-A3B) and the Qwen3.6 models (27B, 35B-A3B) are native vision-language models with a 262,144-token context window and hybrid thinking. Qwen3-VL-235B-A22B comes in Thinking and Instruct versions for image understanding with a 131,072-token context window. Qwen3-Coder-Next is a text-only coding model for agents with 3B active parameters. All of them are called through RunAPI's OpenAI-compatible Chat Completions endpoint with one API key.
| Endpoint | Protocol |
|---|---|
POST /v1/chat/completions | OpenAI compatible |
POST /v1/responses | OpenAI Responses |
POST /v1/messages | Anthropic compatible |
POST /v1beta/models/{model}:generateContent | Gemini generateContent |
POST /v1beta/models/{model}:streamGenerateContent | Gemini streamGenerateContent |
| Variant | Billing | Pricing | |
|---|---|---|---|
| qwen3-coder-next | 1K tokens | Retired | View → |
| qwen3-vl-235b-a22b-instruct | 1K tokens | Retired | View → |
| qwen3-vl-235b-a22b-thinking | 1K tokens | Retired | View → |
| qwen3.5-122b-a10b | 1K tokens | Input $0.40 / 1M tokens | Output $3.20 / 1M tokens | View → |
| qwen3.5-27b | 1K tokens | Input $0.30 / 1M tokens | Output $2.40 / 1M tokens | View → |
| qwen3.5-35b-a3b | 1K tokens | Input $0.25 / 1M tokens | Output $2.00 / 1M tokens | View → |
| qwen3.5-397b-a17b | 1K tokens | Input $0.60 / 1M tokens | Output $3.60 / 1M tokens | View → |
| qwen3.6-27b | 1K tokens | Input $0.60 / 1M tokens | Output $3.60 / 1M tokens | View → |
| qwen3.6-35b-a3b | 1K tokens | Input $0.38 / 1M tokens | Output $2.25 / 1M tokens | View → |
| Endpoint | Resolution | Duration | Price | |
|---|---|---|---|---|
| chat_completion | — | — | Input $0.40 / 1M tokens | Output $3.20 / 1M tokens |
Prices shown for qwen3.5-122b-a10b. 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 language models from Alibaba are open-weight Mixture-of-Experts and dense LLMs with 131K to 256K context. Most of them accept image input and offer a thinking mode. Through RunAPI they share one API key and per-token billing, and any OpenAI SDK can call them at https://runapi.ai/v1. These are Qwen's language models, separate from the Qwen Image, Qwen 2, and Qwen 3 image generation models.
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.
Start with qwen3.6-27b or qwen3.6-35b-a3b, the newest Qwen models on RunAPI, for chat, coding, and image input. Use qwen3.5-397b-a17b when you want the largest Qwen3.5 model, and qwen3-coder-next for coding agents that do not need a thinking step.
All Qwen3.5 and Qwen3.6 models and both Qwen3-VL-235B-A22B versions accept images. Send them as image_url parts in a Chat Completions request. qwen3-coder-next is text-only.
The Qwen3.5 and Qwen3.6 models are hybrid and have thinking and non-thinking modes. qwen3-vl-235b-a22b-thinking always thinks, while qwen3-vl-235b-a22b-instruct and qwen3-coder-next answer without a thinking step.
Use the OpenAI-compatible Chat Completions endpoint at https://runapi.ai/v1/chat/completions with your RunAPI API key and a Qwen model ID. Any OpenAI SDK works after you change the base URL.
Yes. Alibaba releases these Qwen models with open weights under the Apache 2.0 license. RunAPI gives you API access, so you do not have to host them on your own GPUs.
The Qwen line holds the language models, which read text and images and return text. Qwen Image, Qwen 2, and Qwen 3 are separate RunAPI lines that generate and edit images.