Qwen3.7 Max vs Macaron V1 Venti: API price and specs

Macaron V1 Venti is 34% cheaper than Qwen3.7 Max on input price.

Macaron V1 Venti is 34% cheaper than Qwen3.7 Max on output price.

Macaron V1 Venti is 34% cheaper than Qwen3.7 Max on a 1M-in / 200k-out workload.

Qwen3.7 Max has a 1.5% larger context than Macaron V1 Venti.

Field	Qwen3.7 Max	Macaron V1 Venti
Lowest input, per 1M	$1.25 +51.5%	$0.82
Median input, per 1M	$2.00 +129.8%	$0.87
Lowest output, per 1M	$3.75 +51.5%	$2.48
Median output, per 1M	$6.00 +129.8%	$2.61
Lowest unit price	—	—
Cost of 1M in + 200k out	$2.00 +51.5%	$1.32
Context	1.1M	1M +1.4%
Max output	131K	131K
Providers	23	3 +87%
Regions	GLOBAL, US	—
Accepts	text	text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	novita	novita

Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.

Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.

Providers selling both

novita, trustedrouter, zenmux

Frequently asked questions

Which is cheaper, Qwen3.7 Max or Macaron V1 Venti?

Macaron V1 Venti is 34% cheaper than Qwen3.7 Max on input price. Macaron V1 Venti is 34% cheaper than Qwen3.7 Max on output price. Macaron V1 Venti is 34% cheaper than Qwen3.7 Max on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3.7 Max or Macaron V1 Venti?

Qwen3.7 Max: 1.1M tokens; Macaron V1 Venti: 1M tokens.

Where can I use both Qwen3.7 Max and Macaron V1 Venti?

novita, trustedrouter, zenmux