Alibaba / manual · models.dev

Qwen3.7 Max

Opened from a screened package 0a40a7b0797b.

Harnesses

Same model, different drivers. ChatGPT is not OpenCode. $ / MU is only set when every official task passed. $ / pass still shows on a partial run; it does not rank. Time is output tokens at 80 tok/s, not wall clock.

Stack	Passed	Attempts	Time	$ / MU	$ / pass	$ / hr	Tokens / pass	Burn	$ / Alibaba
Qwenmax	3/3	18	1h 51m	$0.004119	$5.89	$10.53	533,672	1.00×	$5.89

Official jobs

Pass or fail on each sealed job. Attempts include retries. Failed tries stay in the bill.

Durable work queue	JSON Patch (RFC 6902 subset)	Token bucket and sliding window
pass · 16	pass · 1	pass · 1

Tokens by job

Billed tokens on each official job, including retries. Cache reads drop out of this count.

Qwen · max
1,480,656Durable work queue
59,743JSON Patch (RFC 6902 subset)
60,617Token bucket and sliding window

Where the bill goes

Failed attempts stay in the bill. Cache hits are a discount, shown separately.

Qwen · max1,601,016
Cache hit 21,995,822 (discount, not extra work)

Uncached in
Output
Thinking
Cache write

Retry tax

Attempts are harness calls, including failed hidden-verifier retries. Extra tries stay in the bill.

Qwenmax18 attempts · 15 extra / 3 jobs

Cache hits

Hits divided by uncached input plus hits. No cache means the harness did not report a discount.

Qwenmax95%

Endpoints

Provider	SKU	List in	List out	Cache hit	Cache write
Alibaba	`qwen3.7-max`	$2.50	$7.50	$0.50	$3.13

All stacks