Qwen3 235B-A22B Instruct 2507 vs voxtral-small-2507: API price and specs

Qwen3 235B-A22B Instruct 2507 is 29% cheaper than voxtral-small-2507 on input price.

Qwen3 235B-A22B Instruct 2507 is 73% cheaper than voxtral-small-2507 on output price.

Qwen3 235B-A22B Instruct 2507 is 48% cheaper than voxtral-small-2507 on a 1M-in / 200k-out workload.

Qwen3 235B-A22B Instruct 2507 has a 700% larger context than voxtral-small-2507.

Field	Qwen3 235B-A22B Instruct 2507	voxtral-small-2507
Lowest input, per 1M	$0.071	$0.10 +40.8%
Median input, per 1M	$0.20 +81.8%	$0.11
Lowest output, per 1M	$0.10	$0.37 +268.9%
Median output, per 1M	$0.80 +100%	$0.40
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.091	$0.17 +91%
Context	262K	33K +87.5%
Max output	262K	32K +87.8%
Providers	19	2 +89.5%
Regions	EU, GLOBAL, US	EU, GLOBAL
Accepts	image, text	audio, text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	requesty	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

cortecs, edenai

Frequently asked questions

Which is cheaper, Qwen3 235B-A22B Instruct 2507 or voxtral-small-2507?

Qwen3 235B-A22B Instruct 2507 is 29% cheaper than voxtral-small-2507 on input price. Qwen3 235B-A22B Instruct 2507 is 73% cheaper than voxtral-small-2507 on output price. Qwen3 235B-A22B Instruct 2507 is 48% cheaper than voxtral-small-2507 on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3 235B-A22B Instruct 2507 or voxtral-small-2507?

Qwen3 235B-A22B Instruct 2507: 262K tokens; voxtral-small-2507: 33K tokens.

Where can I use both Qwen3 235B-A22B Instruct 2507 and voxtral-small-2507?

cortecs, edenai