ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Alibaba Qwen
Proprietary API Alibaba Qwen · qwen-max-latest · Text+Image+Video+PDF

Qwen4-Max / Qwen3.8-Max Official Specifications, Pricing & Benchmarks

Alibaba Cloud’s largest proprietary flagship on Model Studio with 1M context and 128K output.

📋 Qwen4-Max / Qwen3.8-Max Official API & System Card Specifications

Verified against official Alibaba Qwen developer documentation & pricing

API Model ID: qwen-max-latest

1. Identity & Capabilities

API Spec
API Model ID
qwen-max-latest
Release Date
2026-08-03
Weight License
Proprietary (Undisclosed)
Native Reasoning
✅ Supported
Function Calling & JSON Schema
✅ 原生支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
1,000,000 tokens (1000K)
Max Output Tokens
131,072 tokens
Input Modalities
Text + Image + Video + PDF
Output Modalities
Text
Direct China Access
✅ Direct CN + RMB
Deployment Mode
Cloud API only (Proprietary)

3. Official Pricing & Cache

CNY / 1M
Input / 1M Tokens
¥ 10
Cached Input / 1M
¥ 1 -90%
Output / 1M Tokens
¥ 30
Tiered Pricing Notes
Alibaba Cloud Bailian commercial flagship: 1M context, 128K max output, 50% off Batch API

🏆 Official Benchmark Results

Sourced from official System Card / Model Card & technical reports

Arena Elo ~1508 AA Index 53
📚 Knowledge
C-Eval 94.2 %

C-Eval is a comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context.

📚 Knowledge
MMLU-Pro 88.9 %

A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks.

🧠 Reasoning
GPQA Diamond 90.4 %

PhD-level Google-proof science reasoning questions

🧠 Reasoning
AIME 2026 94 %

All 30 problems from the 2026 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999.

💻 Coding
SWE-bench Verified 78.5 %

A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.

🤖 Agentic
TAU2-Bench 88.2 %

Dual-control conversational tool-use benchmark

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Bailian Commercial Thinking Mode
temperature=0.6 top_p=0.95 max_tokens=65,536

📊 Qwen4-Max / Qwen3.8-Max Full Benchmark Scorecard

11 public benchmarks · ranks among 154 models · synced 2026-11-20

⚔️ Compare head-to-head

Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).

Closest Self-Hostable Open-Weight Alternatives to Qwen4-Max / Qwen3.8-Max

Open-weight models with full HuggingFace weights for private GPU / Mac deployment

Compare with these →

Frequently Asked Questions

Is Qwen4-Max / Qwen3.8-Max open-source or proprietary?

Qwen4-Max / Qwen3.8-Max (qwen-max-latest) is a proprietary commercial model by Alibaba Qwen. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.

What are the context limit and API pricing of Qwen4-Max / Qwen3.8-Max?

Qwen4-Max / Qwen3.8-Max supports 1000K input context and 131,072 max output tokens, priced at ¥10/1M input (¥1/1M cached) and ¥30/1M output.