Qwen3.7 Max

AlibabaMCP Tool CallReasoning

alibaba/qwen3.7-maxClosed API

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

Benchmark Pricing$2.50 / 1M in$7.50 / 1M out$0.50 cache read

Context: 1,000,000 tokens•Max Output: 131,072 tokens•Released: 2026-05-21

TECHNICAL SPECIFICATIONS

Context Window1,000,0001M tokens

Max Output131,072131.1K tokens

LicenseProprietaryCloud API only

Input Modalities

Text

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Qwen3.7 Max 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 1,000,000 tokens, this model can handle extremely large MCP resource manifests, complete database schemas, and multiple active server tool definitions simultaneously without degradation.

STANDARDIZED BENCHMARKS & EVALS

SWE-Bench Verifiedresolved

80.4

SWE-Bench Proresolve rate

60.6

SWE-Bench Multilingualresolve rate

78.3

Terminal-Benchsuccess rate

69.7

GPQA Diamondaccuracy

92.4

Humanity's Last Examaccuracy

41.4

SciCodeUnit not reported

53.5

MCP Atlassuccess rate

76.4

NL2RepoUnit not reported

47.2

API CALL INVOCATION EXAMPLE

// Example: Calling Qwen3.7 Max 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/qwen3.7-max",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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