BroadRouter

Qwen3.7 Max vs Qwen3.7 Plus API pricing

Updated

Qwen3.7 Max: USD 1.25 input, USD 3.75 output per 1M tokens (Novita AI). Qwen3.7 Plus: USD 0.32 input, USD 1.28 output per 1M tokens (Together AI). At 3 input tokens per output token, Qwen3.7 Max costs 3.3× as much as Qwen3.7 Plus (USD 1.875 vs USD 0.56 per 1M).

Qwen3.7 Max and Qwen3.7 Plus are neighbouring tiers of one Qwen generation (Max and Plus, by name), so this page shows what the step up costs. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-15), with no claim about quality, speed or accuracy.

How do Qwen3.7 Max and Qwen3.7 Plus differ on price?

Qwen3.7 Max and Qwen3.7 Plus prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

Qwen3.7 Max and Qwen3.7 Plus API prices compared
PriceQwen3.7 MaxQwen3.7 Plus
Model pageQwen3.7 Max
Qwen · 5 providers
Qwen3.7 Plus
Qwen · 2 providers
Cheapest standard price, blended 3:1USD 1.875
USD 1.25 in / USD 3.75 out at Novita AI
Novita AI page checked 2026-11-14
USD 0.56 lower
USD 0.32 in / USD 1.28 out at Together AI
Together AI page checked 2026-11-14
Cheapest inputUSD 1.25
Novita AI source
USD 0.32 lower
Together AI source
Cheapest cached inputUSD 0.25
Novita AI source
USD 0.08 lower promo
Alibaba Cloud source
Cheapest outputUSD 3.75
Novita AI source
USD 1.28 lower
Together AI source
Maker's own APIUSD 2.50 / USD 7.50
Alibaba Cloud source
USD 0.40 / USD 1.60 promo
Alibaba Cloud source
Median standard priceUSD 2.50 / USD 7.50
input / output, 5 prices
USD 0.36 / USD 1.44
input / output, 2 prices
Context window1,000,000 tokens, largest stated; from 256,000 at some providersNo provider states one on its pricing page.
Providers with a standard price52

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What do Qwen3.7 Max and Qwen3.7 Plus cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).

Monthly cost of three workloads on Qwen3.7 Max and Qwen3.7 Plus
WorkloadQwen3.7 MaxQwen3.7 PlusDifference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 126.00
Novita AI
USD 47.52
Alibaba Cloud
USD 78.48
Qwen3.7 Plus lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 284.25
Novita AI
USD 96.00
Together AI
USD 188.25
Qwen3.7 Plus lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 1,058
Novita AI
USD 374.40
Alibaba Cloud
USD 683.10
Qwen3.7 Plus lower

Qwen3.7 Plus is cheaper on all three workloads. The widest gap is on RAG over documents: the dearer model costs 2.96× as much as the cheaper one.

Does the cheaper model change with your input:output ratio?

Qwen3.7 Plus is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Qwen3.7 Max's, so the input:output ratio never changes the answer.

Price per 1M tokens of Qwen3.7 Max and Qwen3.7 Plus at different input:output mixes
Input : output tokensQwen3.7 MaxQwen3.7 Plus
1 : 3 (long answers)USD 3.125
Novita AI
USD 1.04 lower
Together AI
1 : 1USD 2.50
Novita AI
USD 0.80 lower
Together AI
3 : 1 (the site’s blend)USD 1.875
Novita AI
USD 0.56 lower
Together AI
10 : 1 (retrieval, long prompts)USD 1.477
Novita AI
USD 0.4073 lower
Together AI
30 : 1 (agents, big contexts)USD 1.331
Novita AI
USD 0.351 lower
Together AI

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

What do Qwen3.7 Max and Qwen3.7 Plus cost per character in other languages?

Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and Qwen3.7 Max and Qwen3.7 Plus are not among them. Count tokens on your own text with the counters below.

Check it on your own traffic

More comparisons: Qwen3.8 Max vs Qwen3.7 Max · Qwen3.7 Plus vs Qwen3.6 Plus · every Qwen3.7 Max comparison · every Qwen3.7 Plus comparison · all 662 price comparisons

Questions

Is Qwen3.7 Max cheaper than Qwen3.7 Plus?

No. On a blend of 3 input tokens to 1 output token, Qwen3.7 Plus costs USD 0.56 per 1M tokens and Qwen3.7 Max USD 1.875, at each model's cheapest standard price. For input alone, Qwen3.7 Plus is cheaper (USD 0.32 against USD 1.25 per 1M); for output alone, Qwen3.7 Plus is (USD 1.28 against USD 3.75). This compares price only, not quality.

What do Qwen3.7 Max and Qwen3.7 Plus cost per 1M tokens?

Qwen3.7 Max: from USD 1.25 input and USD 3.75 output at Novita AI; Alibaba Cloud's own API charges USD 2.50 / USD 7.50; median of 5 standard prices USD 2.50 / USD 7.50. Qwen3.7 Plus: from USD 0.32 input and USD 1.28 output at Together AI; Alibaba Cloud's own API charges USD 0.40 / USD 1.60; median of 2 standard prices USD 0.36 / USD 1.44. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both Qwen3.7 Max and Qwen3.7 Plus?

2 providers have a standard price for both: Together AI (USD 3.75 and USD 0.56 at 3:1), Alibaba Cloud (USD 3.75 and USD 0.70 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 1.875 and USD 0.56.

Which is cheaper for a coding agent or a chatbot, Qwen3.7 Max or Qwen3.7 Plus?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 1,058 a month on Qwen3.7 Max (Novita AI) against USD 374.40 on Qwen3.7 Plus (Alibaba Cloud), a difference of USD 683.10. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 126.00 a month on Qwen3.7 Max (Novita AI) against USD 47.52 on Qwen3.7 Plus (Alibaba Cloud), a difference of USD 78.48. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.

At what input:output ratio does the cheaper of Qwen3.7 Max and Qwen3.7 Plus change?

Qwen3.7 Plus is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Qwen3.7 Max's, so the input:output ratio never changes the answer.

Do Qwen3.7 Max and Qwen3.7 Plus have cached input pricing?

Qwen3.7 Max from USD 0.25 per 1M cached input tokens (Novita AI; 5 of 5 standard prices list a discount). Qwen3.7 Plus from USD 0.08 per 1M cached input tokens (Alibaba Cloud; 1 of 2 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity