qwen-3-235b-a22b-instruct-2507 — Free API

What is qwen-3-235b-a22b-instruct-2507?

Qwen3-235B-A22B is Alibaba's massive 235B-parameter MoE model available for free on Cerebras Cloud's ultra-fast WSE inference hardware. With 131K context and OpenAI-compatible API, it delivers strong general-purpose chat performance at speeds far exceeding GPU-based alternatives — Cerebras' wafer-scale engine means responses stream near-instantly even at this parameter scale. The free tier allows 14,400 requests per day at 30 RPM, making it viable for moderate production workloads. No credit card is required; the main trade-off versus running this model on other providers is the 8K output limit and lower RPM compared to Groq's Llama endpoints.

qwen-3-235b-a22b-instruct-2507 API Code Example

Paste your API key and run. See the config generator for Claude Code, Cursor, and more tools.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.cerebras.ai/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="qwen-3-235b-a22b-instruct-2507",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.cerebras.ai/v1",
  apiKey: "YOUR_API_KEY",
});

const completion = await openai.chat.completions.create({
  model: "qwen-3-235b-a22b-instruct-2507",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(completion.choices[0].message.content);

curl https://api.cerebras.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "qwen-3-235b-a22b-instruct-2507",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Other Free Models from Cerebras