Qwen3.5 122B-A10B vs L3 70B Euryale V2.1: API price and specs

Qwen3.5 122B-A10B is 84% cheaper than L3 70B Euryale V2.1 on input price.

L3 70B Euryale V2.1 is 11% cheaper than Qwen3.5 122B-A10B on output price.

Qwen3.5 122B-A10B is 66% cheaper than L3 70B Euryale V2.1 on a 1M-in / 200k-out workload.

Qwen3.5 122B-A10B has a 3100% larger context than L3 70B Euryale V2.1.

Field	Qwen3.5 122B-A10B	L3 70B Euryale V2.1
Lowest input, per 1M	$0.11	$0.70 +521.7%
Median input, per 1M	$0.26	$1.48 +469.2%
Lowest output, per 1M	$0.90 +12.6%	$0.80
Median output, per 1M	$2.20 +48.6%	$1.48
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.29	$0.86 +193.8%
Context	262K	8K +96.9%
Max output	262K	—
Providers	19	4 +78.9%
Regions	CH, EU, 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	deepinfra

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

deepinfra, jiekou, novita, trustedrouter

Frequently asked questions

Which is cheaper, Qwen3.5 122B-A10B or L3 70B Euryale V2.1?

Qwen3.5 122B-A10B is 84% cheaper than L3 70B Euryale V2.1 on input price. L3 70B Euryale V2.1 is 11% cheaper than Qwen3.5 122B-A10B on output price. Qwen3.5 122B-A10B is 66% cheaper than L3 70B Euryale V2.1 on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3.5 122B-A10B or L3 70B Euryale V2.1?

Qwen3.5 122B-A10B: 262K tokens; L3 70B Euryale V2.1: 8K tokens.

Where can I use both Qwen3.5 122B-A10B and L3 70B Euryale V2.1?

deepinfra, jiekou, novita, trustedrouter