Qwen3.6 35B-A3B vs Nova Pro 1.0: API price and specs

Qwen3.6 35B-A3B is 98% cheaper than Nova Pro 1.0 on input price.

Qwen3.6 35B-A3B is 97% cheaper than Nova Pro 1.0 on output price.

Qwen3.6 35B-A3B is 98% cheaper than Nova Pro 1.0 on a 1M-in / 200k-out workload.

Nova Pro 1.0 has a 21% larger context than Qwen3.6 35B-A3B.

Field	Qwen3.6 35B-A3B	Nova Pro 1.0
Lowest input, per 1M	$0.012	$0.80 +6566.7%
Median input, per 1M	$0.17	$0.85 +400.5%
Lowest output, per 1M	$0.09	$3.20 +3455.6%
Median output, per 1M	$1.01	$3.39 +236.2%
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.03	$1.44 +4700%
Context	262K +17.4%	317K
Max output	262K	10K +96.2%
Providers	27	5 +81.5%
Regions	EU, GLOBAL, TW, 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	file, image, text, video
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	inferx	kilo

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

aiml, cortecs, empiriolabs, kilo, openrouter

Frequently asked questions

Which is cheaper, Qwen3.6 35B-A3B or Nova Pro 1.0?

Qwen3.6 35B-A3B is 98% cheaper than Nova Pro 1.0 on input price. Qwen3.6 35B-A3B is 97% cheaper than Nova Pro 1.0 on output price. Qwen3.6 35B-A3B is 98% cheaper than Nova Pro 1.0 on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3.6 35B-A3B or Nova Pro 1.0?

Qwen3.6 35B-A3B: 262K tokens; Nova Pro 1.0: 317K tokens.

Where can I use both Qwen3.6 35B-A3B and Nova Pro 1.0?

aiml, cortecs, empiriolabs, kilo, openrouter