Qwen3 235B-A22B Instruct 2507 vs gpt-oss-120b-ultra: API price and specs

Qwen3 235B-A22B Instruct 2507 is 64% cheaper than gpt-oss-120b-ultra on input price.

Qwen3 235B-A22B Instruct 2507 is 89% cheaper than gpt-oss-120b-ultra on output price.

Qwen3 235B-A22B Instruct 2507 is 77% cheaper than gpt-oss-120b-ultra on a 1M-in / 200k-out workload.

Qwen3 235B-A22B Instruct 2507 has a 100% larger context than gpt-oss-120b-ultra.

Field	Qwen3 235B-A22B Instruct 2507	gpt-oss-120b-ultra
Lowest input, per 1M	$0.071	$0.20 +181.7%
Median input, per 1M	$0.20	$0.20
Lowest output, per 1M	$0.10	$0.95 +850%
Median output, per 1M	$0.80	$0.95 +18.7%
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.091	$0.39 +328.6%
Context	262K	131K +50%
Max output	262K	131K +50%
Providers	19	4 +78.9%
Regions	EU, GLOBAL, US	US
Accepts	image, text	text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	requesty	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, edenai, fastrouter, trustedrouter

Frequently asked questions

Which is cheaper, Qwen3 235B-A22B Instruct 2507 or gpt-oss-120b-ultra?

Qwen3 235B-A22B Instruct 2507 is 64% cheaper than gpt-oss-120b-ultra on input price. Qwen3 235B-A22B Instruct 2507 is 89% cheaper than gpt-oss-120b-ultra on output price. Qwen3 235B-A22B Instruct 2507 is 77% cheaper than gpt-oss-120b-ultra on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3 235B-A22B Instruct 2507 or gpt-oss-120b-ultra?

Qwen3 235B-A22B Instruct 2507: 262K tokens; gpt-oss-120b-ultra: 131K tokens.

Where can I use both Qwen3 235B-A22B Instruct 2507 and gpt-oss-120b-ultra?

deepinfra, edenai, fastrouter, trustedrouter