alibaba/qwen3-maxClosed APIFlagship Qwen3 model for coding agents, complex reasoning, and tool use
Benchmark Pricing$1.20 / 1M in$6.00 / 1M out
Context: 262,144 tokens•Max Output: 65,536 tokens•Knowledge: 2025-04•Released: 2025-09-23
TECHNICAL SPECIFICATIONS
Context Window262,144262.1K tokens
Max Output65,53665.5K tokens
LicenseProprietaryCloud API only
Input Modalities
Text
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema
MODEL CONTEXT PROTOCOL (MCP) READINESS
✓ Qwen3 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 262,144 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.
STANDARDIZED BENCHMARKS & EVALS
Artificial Analysis Coding Indexindex
26.4SciCodepercent correct
38.3Terminal-Bench Hardsuccess rate
20.5API CALL INVOCATION EXAMPLE
// Example: Calling Qwen3 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-max",
messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});
console.log(response.choices[0].message.content);PRICING BY PROVIDER
Alibabaqwen3-max
$1.20 / $6.00
NanoGPTqwen/qwen3-max
$1.20 / $6.00$0.60 cache
302.AIqwen3-max-2025-09-23
$0.86 / $3.43
LLM Gatewaynovita/qwen3-max
$0.84 / $3.38
LLMTRqwen/qwen3-max
$1.20 / $6.00
Cloudflare AI Gatewayalibaba/qwen3-max
$1.20 / $6.00
AIHubMixqwen3-max
$0.45 / $2.70$0.09 cache
Abacusqwen3-max
$1.20 / $6.00
Vercel AI Gatewayalibaba/qwen3-max-thinking
$1.20 / $6.00$0.24 cache
Ofoxbailian/qwen3-max
$0.36 / $1.43$0.07 cache
Merge Gatewayqwen/qwen3-max
$0.36 / $1.43$0.07 cache
Alibaba Coding Planqwen3-max-2026-01-23
$0.00 / $0.00$0.00 cache
ZenMuxqwen/qwen3-max
$1.20 / $6.00
DevPass (LLM Gateway)qwen3-max
$0.84 / $3.38$0.60 cache
Alibaba (China)qwen3-max
$0.36 / $1.43
Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.
MODEL RESOURCES
More Models by Alibaba
Alternative and family models from the same lab
Qwen3 Coder Plus
alibaba/qwen3-coder-plus•Alibaba
Hosted Qwen coder for software agents, repo edits, and long-context code
65.5K out max
In: $1.00 • Out: $5.00
AlibabaQwen Turbo
alibaba/qwen-turbo•Alibaba
Efficient Qwen model for fast chat, extraction, and high-volume workloads
16.4K out max
In: $0.05 • Out: $0.20
AlibabaQwen3.8 Max
alibaba/qwen3.8-max•Alibaba
2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows
131.1K out maxVisionPDFTerminal-Bench: 86.6 avg@10
In: $2.00 • Out: $6.00
Alibaba