Qwen3 235B-A22B Thinking 2507

AlibabaMCP Tool CallReasoning

alibaba/qwen3-235b-a22b-thinking-2507Open Weights

Updated large open Qwen3 MoE thinking model for reasoning, math, coding, and tool use

Benchmark Pricing$0.30 / 1M in$0.50 / 1M out

Context: 262,144 tokens•Max Output: 81,920 tokens•Released: 2025-07-25

TECHNICAL SPECIFICATIONS

Context Window262,144262.1K tokens

Max Output81,92081.9K tokens

LicenseApache 2.0Self-hostable

Input Modalities

Text

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Qwen3 235B-A22B Thinking 2507 natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 262,144 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Qwen3 235B-A22B Thinking 2507 via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ALIBABA_API_KEY,
});

const response = await client.chat.completions.create({
  model: "alibaba/qwen3-235b-a22b-thinking-2507",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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