Qwen3.7 Max
Qwen3.7 MaxRankingin thinking mode?
Alternatives?
CheaperGPT-6.1 Solmax+31%-37%$0.72Remove unsupported parameters+5
BetterClaude Haiku 5.5xhigh+5%-89%$0.12Remove sampling parameters+5
OpenMiMo v2.6 Prothinking+22%-88%$0.13Pass back reasoning_content+3CheaperGPT-6 Astralow+22%-29%$0.82Monitoring can return HTTP 403+2CheaperClaude Opus 5.5low+19%-52%$0.55No forced tool use+5GPT-6.1 Solmax+31%-37%$0.72Remove unsupported parameters+5MiMo v2.6 ProthinkingOpen+22%-88%$0.13Pass back reasoning_content+3GPT-6 Astralow+22%-29%$0.82Monitoring can return HTTP 403+2Claude Opus 5.5low+19%-52%$0.55No forced tool use+5
MiniMax M3.1 Flashthinking+18%-81%$0.22Complete model response must be appendedClaude Haiku 5.5xhigh+5%-89%$0.12Remove sampling parameters+5GPT-6.1 Sollow+17%-89%$0.13Remove unsupported parameters+5MiMo v2.6 ProthinkingOpen+22%-88%$0.13Pass back reasoning_content+3MiniMax M3.1 Flashthinking+18%-81%$0.22Complete model response must be appended
DeepSeek V4.1 Flash 1017maxOpen+7%-77%$0.26Pass back reasoning_content · Chat Completions+4MiMo v2.6 ProthinkingOpen+22%-88%$0.13Pass back reasoning_content+3
Kimi K3maxOpen+16%+74%$2.00Sampling parameters are fixed+3
Step 5 PreviewthinkingOpen+15%-11%$1.03web_search not available · Chat Completions+2
Muse Spark OpenxhighOpen+8%-26%$0.84Reasoning off leaves output unchanged · Self-hosted / llama.cpp+1DeepSeek V4.1 Flash 1017maxOpen+7%-77%$0.26Pass back reasoning_content · Chat Completions+4Qwen3.8 Max (0902)thinking+6%+371%$5.41Context: 1M → 984KQwen3.8 2.4T A95BthinkingOpen+5%+88%$2.16Context: 1M → 262K+5Qwen3.8 FlashthinkingOpen-6%-68%$0.37Context: 1M → 262K+6Qwen3.7 Plusthinking-12%-81%$0.22Qwen3.6 Max Previewthinking-24%—$1.30 / $7.80Context: 1M → 262K+1Qwen3.5 397B A17BthinkingOpen-28%-59%$0.47Context: 1M → 262KQwen3 Max Thinkingthinking-31%—$1.20 / $6Context: 1M → 256KQwen3.6 Plusthinking-31%—$0.50 / $3All Alibaba (Qwen) models →History
7 versionsBenchmarks
all categoriesFAQ
How much does Qwen3.7 Max cost?›
$1.48 per 1M input tokens and $4.43 per 1M output tokens; cached input $0.29 per 1M; cheapest via Novita at $1.25 / $3.75. A typical benchmark task costs about $1.15 at default effort.
Is Qwen3.7 Max free to use?›
There is no free API; the cheapest paid price is $1.25 per 1M input tokens.
How good is Qwen3.7 Max, and what is it best at?›
#43 of 334 in Chat & Knowledge, #52 of 132 in Coding, #56 of 133 in Agents & Tool Use, #39 of 44 in Writing & Language, #64 of 133 in Vision & Documents. Strongest at: Tool calling, Reasoning, Science, Long context, Knowledge, Instructions.
Is Qwen3.7 Max better than Qwen3.6 Max Preview?›
On Humanity's Last Exam, Qwen3.7 Max scores 40.5 vs 30.8 — higher.
How can I use Qwen3.7 Max?›
Through the API of Alibaba, DeepInfra, Novita.
What is the context window of Qwen3.7 Max?›
1M tokens, with up to 131K output tokens.
When was Qwen3.7 Max released? Is there a newer version?›
Released 2026-05-21. It has been superseded by Qwen3.8 Max.
Is Qwen3.7 Max open source?›
No, Qwen3.7 Max is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can Qwen3.7 Max read images?›
No, it accepts text only.
What is Qwen3.7 Max?›
Qwen3.7 Max is a closed language model from Alibaba (Qwen), released May 2026, the successor to Qwen3.6 Max Preview.
What are the best alternatives to Qwen3.7 Max?›
GPT-6.1 Sol (cheaper), Claude Haiku 5.5 (better), MiMo v2.6 Pro (open weights).