Qwen3.5 397B-A17B vs Apertus v1.5 70B: API price and specs

Qwen3.5 397B-A17B is 79% cheaper than Apertus v1.5 70B on input price.

Qwen3.5 397B-A17B is 65% cheaper than Apertus v1.5 70B on output price.

Qwen3.5 397B-A17B is 73% cheaper than Apertus v1.5 70B on a 1M-in / 200k-out workload.

Qwen3.5 397B-A17B has a 162.1% larger context than Apertus v1.5 70B.

Field	Qwen3.5 397B-A17B	Apertus v1.5 70B
Lowest input, per 1M	$0.16	$0.78 +376%
Median input, per 1M	$0.55	$0.82 +49.1%
Lowest output, per 1M	$0.99	$2.79 +183.3%
Median output, per 1M	$3.60 +23.3%	$2.92
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.36	$1.34 +270.9%
Context	262K	100K +61.9%
Max output	262K	8K +96.9%
Providers	30	3 +90%
Regions	CH, EU, GLOBAL, US	CH
Accepts	file, 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	audio, image, text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	aihubmix	edenai

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

edenai, huggingface, infomaniak

Frequently asked questions

Which is cheaper, Qwen3.5 397B-A17B or Apertus v1.5 70B?

Qwen3.5 397B-A17B is 79% cheaper than Apertus v1.5 70B on input price. Qwen3.5 397B-A17B is 65% cheaper than Apertus v1.5 70B on output price. Qwen3.5 397B-A17B is 73% cheaper than Apertus v1.5 70B on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3.5 397B-A17B or Apertus v1.5 70B?

Qwen3.5 397B-A17B: 262K tokens; Apertus v1.5 70B: 100K tokens.

Where can I use both Qwen3.5 397B-A17B and Apertus v1.5 70B?

edenai, huggingface, infomaniak