Qwen3.7 Max
alibaba/qwen3.7-max- Alibaba
- Family · Qwen3 Max
- Released 19 May 2026
- Text → Text
- Tools · JSON
Not on OSMEXO yet
Spec & list price
Context1M
Max output128K
Input / 1M$1.48
Output / 1M$4.423× input
Scores · standing
Intelligence29.5#68/490
Coding66.0#33/196
Usage
Tokens / day764.5M▼ 11% 7d
Usage rank#209
Requests / day28.5K
Tool calls / req0.19
Per request · 30 days
Avg input13.6Kabout median
Avg output1.1K1.7× median
Cache hit70%about median
Reasoning share68%1.2× median
Tool-call failures5.3%2.8× median
Consumption
Peak 4.6B 29 SepLow 567.9M 1 NovRank today #209
News & trends
19 mentions this week ▼ 27%Qwen3 Max family · videos, posts, articles · 30 days
Trending · 14 days · Qwen3 Max family
- 3 AI Models FREE Until Nov 20! DeepSeek V4.1 Flash, GLM 5.3 Flash & Qwen 3.8 Max5.2K views
- 10 Million FREE Tokens for AI Coding 🤯 | GLM-5.3, DeepSeek V4.1, Qwen 3.8 Max & MiniMax M31.3K views
News · latest from Alibaba
- Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hardgithub.com · 31 Oct
- Qwen3.8-Flash Now Available in the EU on Alibaba Cloudtwitter.com · 31 Oct
- Alibaba's Qwen3.8-Flash-Next model tried to upload a file to Beijing in a testnotebookcheck.net · 27 Oct
- Neuron Explorer for Qwen3.5-4B: See every neuron at work, make targeted editsgithub.com · 26 Oct
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across 2 providers, latest day
Output speed#163/33467 tok/sabout median
First token#1811.17 s1.1× longer than median
#8 cheapest of 15 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Family progress
Intelligence Index
- Family releases45.4
Technical details
- Tokenizer
- Qwen
- Moderation
- none
Request parameters 16
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- max_tokens
+6 more
- stop
- seed
- frequency_penalty
- logprobs
- presence_penalty
- top_logprobs
Interesting facts
- 2nd of 4 Qwen3 Max models by tokens last month.
- Weekdays average 1.9B tokens a day against 1.1B on weekends.
When to use
Best for
- Hardest reasoning and science problems
- Coding agents on large codebases
- Agent workflows with heavy tool use
- Strict instruction following in complex prompts
- Very long document analysis
Think twice for
- Image or video input (text only)
- High-volume simple chat (cheaper options exist)
- Self-hosting (closed weights)
- Latency-sensitive interactive apps
Research papers
Same family
Qwen3 Max- 15.6
- 21.3
- 28.4
- 45.4
Alternatives
other vendors · similar capability- T25.0
- 30.1
- 29.7
- 27.0
Want Qwen3.7 Max on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.