Qwen3.5 35B-A3B vs Baichuan M2 32B: API price and specs

Qwen3.5 35B-A3B is 19% cheaper than Baichuan M2 32B on input price.

Baichuan M2 32B is 84% cheaper than Qwen3.5 35B-A3B on output price.

Baichuan M2 32B is 43% cheaper than Qwen3.5 35B-A3B on a 1M-in / 200k-out workload.

Qwen3.5 35B-A3B has a 100% larger context than Baichuan M2 32B.

Field	Qwen3.5 35B-A3B	Baichuan M2 32B
Lowest input, per 1M	$0.0564	$0.07 +24.1%
Median input, per 1M	$0.14 +100%	$0.07
Lowest output, per 1M	$0.45 +544.6%	$0.07
Median output, per 1M	$1.00 +1328.6%	$0.07
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.15 +74.6%	$0.084
Context	262K	131K +50%
Max output	262K	131K +50%
Providers	19	3 +84.2%
Regions	GLOBAL, US	—
Accepts	audio, image, image/bmp, image/heic, image/jpeg, image/png, image/tiff, image/webp, text, video, video/mp4, video/quicktime, video/x-flv, video/x-matroska, video/x-ms-wmv, video/x-msvideo	text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	aihubmix	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, requesty, trustedrouter

Frequently asked questions

Which is cheaper, Qwen3.5 35B-A3B or Baichuan M2 32B?

Qwen3.5 35B-A3B is 19% cheaper than Baichuan M2 32B on input price. Baichuan M2 32B is 84% cheaper than Qwen3.5 35B-A3B on output price. Baichuan M2 32B is 43% cheaper than Qwen3.5 35B-A3B on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3.5 35B-A3B or Baichuan M2 32B?

Qwen3.5 35B-A3B: 262K tokens; Baichuan M2 32B: 131K tokens.

Where can I use both Qwen3.5 35B-A3B and Baichuan M2 32B?

novita, requesty, trustedrouter