Qwen3 8B vs Qwen3.5 122B-A10B: API price and specs

Qwen3 8B is 47% cheaper than Qwen3.5 122B-A10B on input price.

Qwen3 8B is 93% cheaper than Qwen3.5 122B-A10B on output price.

Qwen3 8B is 75% cheaper than Qwen3.5 122B-A10B on a 1M-in / 200k-out workload.

Qwen3.5 122B-A10B has a 100% larger context than Qwen3 8B.

Field	Qwen3 8B	Qwen3.5 122B-A10B
Lowest input, per 1M	$0.06	$0.11 +87.7%
Median input, per 1M	$0.08	$0.26 +225%
Lowest output, per 1M	$0.06	$0.90 +1401.3%
Median output, per 1M	$0.20	$2.20 +1000%
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.072	$0.29 +306.6%
Context	131K +50%	262K
Max output	131K +50%	262K
Providers	7 +63.2%	19
Regions	EU	CH, EU, GLOBAL, US
Accepts	text	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
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	siliconflow-cn	aihubmix

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

aihubmix, edenai, huggingface, kilo, siliconflow, siliconflow-cn, trustedrouter

Frequently asked questions

Which is cheaper, Qwen3 8B or Qwen3.5 122B-A10B?

Qwen3 8B is 47% cheaper than Qwen3.5 122B-A10B on input price. Qwen3 8B is 93% cheaper than Qwen3.5 122B-A10B on output price. Qwen3 8B is 75% cheaper than Qwen3.5 122B-A10B on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3 8B or Qwen3.5 122B-A10B?

Qwen3 8B: 131K tokens; Qwen3.5 122B-A10B: 262K tokens.

Where can I use both Qwen3 8B and Qwen3.5 122B-A10B?

aihubmix, edenai, huggingface, kilo, siliconflow, siliconflow-cn, trustedrouter