modelbenchmark.io

Qwen Max

Alibaba · qwen-max

Compare

Flagship Qwen model for complex reasoning, coding, and agentic workflows

Specification

alibaba listing

Context
33K
Max output
8K
Released
2024-04-03
Knowledge cutoff
2024-04
Retires
—
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · alibaba list price

Input
$1.60
Output
$6.40
Cache read
$0.32

Quality

1 benchmark · 1 source

Composite
17th
percentile of 344 scored models
Rank
286 / 344
±0.15 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
—
one configuration only
coding19th1/3 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
Aider polyglot21.8max · aider diffAider2025-01-28

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 14 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
alibabavendor$1.60$6.40——33K8K—
alibaba-cn$0.345$1.377——131K8K—
qiniu-ai$0.3478$1.3913——128K4K—
ofox$0.35$1.38$0.069—32K8K—
ofox · bailian$0.35$1.38$0.069—33K8K—
nano-gpt$1.5997$6.392$0.7998—32K8K—
aimlapi$1.60$6.40$0.32—32K8K—
dashscope · dashscope$1.60$6.40——31K8K—
edenai$1.60$6.40$0.32—33K8K—
llmgateway$1.60$6.40——33K8K—
llmgateway-providers$1.60$6.40——33K8K—
qwen_ai_platform · qwen-ai-platform$1.60$6.40——31K8K—
qwencloud · qwencloud$1.60$6.40——31K8K—
fireworks-ai · accounts$2.00$6.00$0.25—262K131K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-10-13aimlapiCache read$0.416
2026-10-23aimlapiCache read$0.32
2026-10-13aimlapiInput$2.08
2026-10-23aimlapiInput$1.60
2026-10-13aimlapiOutput$8.32
2026-10-23aimlapiOutput$6.40

More from Alibaba

most-hosted first