Qwen3 235B-A22B Thinking 2507 vs Qwen3 30B A3B Thinking 2507: API price and specs

Qwen3 30B A3B Thinking 2507 is 1% cheaper than Qwen3 235B-A22B Thinking 2507 on input price.

Qwen3 235B-A22B Thinking 2507 is 45% cheaper than Qwen3 30B A3B Thinking 2507 on output price.

Qwen3 235B-A22B Thinking 2507 is 29% cheaper than Qwen3 30B A3B Thinking 2507 on a 1M-in / 200k-out workload.

Field	Qwen3 235B-A22B Thinking 2507	Qwen3 30B A3B Thinking 2507
Lowest input, per 1M	$0.11 +1.2%	$0.11
Median input, per 1M	$0.26 +112.5%	$0.12
Lowest output, per 1M	$0.60	$1.09 +81.2%
Median output, per 1M	$2.30 +91.7%	$1.20
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.23	$0.33 +41.8%
Context	262K	262K
Max output	262K	33K +87.5%
Providers	13	4 +69.2%
Regions	US	GLOBAL
Accepts	text	text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	io-net	qiniu-ai

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, kilo, qiniu-ai

Frequently asked questions

Which is cheaper, Qwen3 235B-A22B Thinking 2507 or Qwen3 30B A3B Thinking 2507?

Qwen3 30B A3B Thinking 2507 is 1% cheaper than Qwen3 235B-A22B Thinking 2507 on input price. Qwen3 235B-A22B Thinking 2507 is 45% cheaper than Qwen3 30B A3B Thinking 2507 on output price. Qwen3 235B-A22B Thinking 2507 is 29% cheaper than Qwen3 30B A3B Thinking 2507 on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3 235B-A22B Thinking 2507 or Qwen3 30B A3B Thinking 2507?

Qwen3 235B-A22B Thinking 2507: 262K tokens; Qwen3 30B A3B Thinking 2507: 262K tokens.

Where can I use both Qwen3 235B-A22B Thinking 2507 and Qwen3 30B A3B Thinking 2507?

aihubmix, edenai, kilo, qiniu-ai