Qwen3.7 Plus · Alibaba (Qwen)

What does Qwen3.7 Plus cost to run in a coding agent?

Qwen3.7 Plus costs about $0.014 per average coding-agent request on our measured traffic, at OpenRouter's listed prices of $0.32 per million input and $1.28 per million output tokens. It scores 25 on the Artificial Analysis Intelligence Index, 35th of the 48 models we track. Source: Artificial Analysis (artificialanalysis.ai)

List prices: OpenRouter listed price, checked 2026-10-13. Request costs: Standard Compute gateway data, 79,301 coding-agent requests from 75 users, Sep 13 to Oct 12, 2026. How we compute this

Run Qwen3.7 Plus in your agent

Or let the router send each step to the cheapest model that can do it, on providers we vet for price, uptime and speed. Plans from $19 a month.

See plans

What Qwen3.7 Plus costs per coding-agent request

Cost at list price	Qwen3.7 Plus
Prompt under 100K tokens50% of requests, 87% of input cached	$0.0064
Prompt of 100K to 272K39% of requests, 88% of input cached	$0.017
Prompt over 272K tokens11% of requests, 86% of input cached	$0.038
Average request	$0.014
100 requests	$1.39
Median session16 requests; a session ends after 10 idle minutes	$0.18
A month of regular usemedian of 20 users active on 5+ days	$22.60

Each logged request priced at the listed rates above for its own token counts, including cache reads and any higher rate for long prompts. Average output: 698 tokens per request.

Qwen3.7 Plus benchmarks, speed and latency

Artificial Analysis	Value	Rank
Intelligence Index10 evaluations, 0 to 100	25	35 of 48
Terminal-Bench 4.0agentic coding in a terminal	1.0%	30 of 39
Output speedmedian	55 tokens/s	38 of 44
Time to first answer tokenincludes thinking time	39 s	21 of 44

Source: Artificial Analysis (artificialanalysis.ai). Measured variant: Qwen3.7 Plus, speed on Alibaba. Fetched October 13, 2026. Rank is among the models on this site, older versions included. Artificial Analysis runs Terminal-Bench 4.0 in its own setup, so its scores differ from the tbench.ai leaderboard.

About Qwen3.7 Plus

Qwen3.7 Plus is the lower-cost hosted Qwen3.7 model, released June 1, 2026 with the same 1M-token context as Max. At OpenRouter's listed price it costs $0.014 per request in our measurements, about a fifth of Max. It scores 25 on the Artificial Analysis Intelligence Index and 1.0% in its Terminal-Bench 4.0 run, and runs at about 55 output tokens per second, so it suits simple, long-context calls more than agentic coding.

Sources: Artificial Analysis

Qwen3.7 Plus FAQ

How much does Qwen3.7 Plus cost per coding-agent request?

$0.014 on average at OpenRouter's listed price, $1.39 per 100 requests, and $0.18 for a median 16-request session. That is 79,301 real coding-agent requests (Sep 13 to Oct 12, 2026) priced at OpenRouter's listed rates; the median request sent 99,534 input tokens, 87% of input was read from cache, and requests returned 698 output tokens on average.

Does Qwen3.7 Plus charge more for long prompts?

No. Qwen3.7 Plus bills the same rate per token up to its 1M-token context window.

How fast is Qwen3.7 Plus?

Artificial Analysis measures Qwen3.7 Plus at 55 output tokens per second, with 39 seconds to the first answer token, thinking time included, on Alibaba's API. Source: Artificial Analysis (artificialanalysis.ai).

Is Qwen3.7 Plus good for AI agents?

Simple, long-context calls on a budget. On our scoring, which is calibrated to public benchmarks, it rates 4.7/10 for agentic ability and 5.7/10 for output quality. 1M context.

What is Qwen3.7 Plus's context window?

Qwen3.7 Plus has a 1M-token context window, large enough to hold sizeable codebases or document sets in a single run. Alibaba (Qwen) is the maker.

Can I self-host Qwen3.7 Plus?

No. Qwen3.7 Plus is a proprietary, hosted-only model from Alibaba (Qwen). You access it through an API, such as OpenRouter, rather than running the weights yourself.

What are the downsides of Qwen3.7 Plus?

The main trade-offs: Weak on long agentic tasks (1.0% in Artificial Analysis's Terminal-Bench 4.0 run); About 55 output tokens/s, per Artificial Analysis; Hosted only, no open weights. It's strongest for simple, long-context calls on a budget.