Qwen3 235B-A22B Instruct 2507 vs Voxtral Mini 3B 2507: API price and specs

Voxtral Mini 3B 2507 is 44% cheaper than Qwen3 235B-A22B Instruct 2507 on input price.

Voxtral Mini 3B 2507 is 60% cheaper than Qwen3 235B-A22B Instruct 2507 on output price.

Voxtral Mini 3B 2507 is 47% cheaper than Qwen3 235B-A22B Instruct 2507 on a 1M-in / 200k-out workload.

Qwen3 235B-A22B Instruct 2507 has a 700% larger context than Voxtral Mini 3B 2507.

Field	Qwen3 235B-A22B Instruct 2507	Voxtral Mini 3B 2507
Lowest input, per 1M	$0.071 +77.5%	$0.04
Median input, per 1M	$0.20 +400%	$0.04
Lowest output, per 1M	$0.10 +150%	$0.04
Median output, per 1M	$0.80 +1900%	$0.04
Lowest unit price	—	$0.001 / minute
Cost of 1M in + 200k out	$0.091 +89.6%	$0.048
Context	262K	33K +87.5%
Max output	262K	4K +98.4%
Providers	19	3 +84.2%
Regions	EU, GLOBAL, US	EU, US
Accepts	image, text	audio, audio/mpeg, audio/wav, 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

amazon-bedrock, deepinfra, edenai

Frequently asked questions

Which is cheaper, Qwen3 235B-A22B Instruct 2507 or Voxtral Mini 3B 2507?

Voxtral Mini 3B 2507 is 44% cheaper than Qwen3 235B-A22B Instruct 2507 on input price. Voxtral Mini 3B 2507 is 60% cheaper than Qwen3 235B-A22B Instruct 2507 on output price. Voxtral Mini 3B 2507 is 47% cheaper than Qwen3 235B-A22B Instruct 2507 on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3 235B-A22B Instruct 2507 or Voxtral Mini 3B 2507?

Qwen3 235B-A22B Instruct 2507: 262K tokens; Voxtral Mini 3B 2507: 33K tokens.

Where can I use both Qwen3 235B-A22B Instruct 2507 and Voxtral Mini 3B 2507?

amazon-bedrock, deepinfra, edenai