Qwen3-Coder 30B-A3B Instruct vs Voxtral Mini 3B 2507: API price and specs

Voxtral Mini 3B 2507 is 43% cheaper than Qwen3-Coder 30B-A3B Instruct on input price.

Voxtral Mini 3B 2507 is 85% cheaper than Qwen3-Coder 30B-A3B Instruct on output price.

Voxtral Mini 3B 2507 is 61% cheaper than Qwen3-Coder 30B-A3B Instruct on a 1M-in / 200k-out workload.

Qwen3-Coder 30B-A3B Instruct has a 700% larger context than Voxtral Mini 3B 2507.

Field	Qwen3-Coder 30B-A3B Instruct	Voxtral Mini 3B 2507
Lowest input, per 1M	$0.07 +75%	$0.04
Median input, per 1M	$0.15 +275%	$0.04
Lowest output, per 1M	$0.26 +550%	$0.04
Median output, per 1M	$0.60 +1400%	$0.04
Lowest unit price	—	$0.001 / minute
Cost of 1M in + 200k out	$0.12 +154.2%	$0.048
Context	262K	33K +87.5%
Max output	262K	4K +98.4%
Providers	13	3 +76.9%
Regions	EU, GLOBAL, US	EU, US
Accepts	text	audio, audio/mpeg, audio/wav, text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	deepinfra	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-Coder 30B-A3B Instruct or Voxtral Mini 3B 2507?

Voxtral Mini 3B 2507 is 43% cheaper than Qwen3-Coder 30B-A3B Instruct on input price. Voxtral Mini 3B 2507 is 85% cheaper than Qwen3-Coder 30B-A3B Instruct on output price. Voxtral Mini 3B 2507 is 61% cheaper than Qwen3-Coder 30B-A3B Instruct on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3-Coder 30B-A3B Instruct or Voxtral Mini 3B 2507?

Qwen3-Coder 30B-A3B Instruct: 262K tokens; Voxtral Mini 3B 2507: 33K tokens.

Where can I use both Qwen3-Coder 30B-A3B Instruct and Voxtral Mini 3B 2507?

amazon-bedrock, deepinfra, edenai