Qwen2.5-Coder-32B-Instruct vs granite-4.2-30b: API price and specs

Qwen2.5-Coder-32B-Instruct is 62% cheaper than granite-4.2-30b on input price.

Qwen2.5-Coder-32B-Instruct is 77% cheaper than granite-4.2-30b on output price.

Qwen2.5-Coder-32B-Instruct is 69% cheaper than granite-4.2-30b on a 1M-in / 200k-out workload.

Field	Qwen2.5-Coder-32B-Instruct	granite-4.2-30b
Lowest input, per 1M	$0.06	$0.16 +166.7%
Median input, per 1M	$0.66 +312.5%	$0.16
Lowest output, per 1M	$0.15	$0.65 +333.3%
Median output, per 1M	$1.00 +53.8%	$0.65
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.09	$0.29 +222.2%
Context	131K	131K
Max output	41K	—
Providers	9	3 +66.7%
Regions	GLOBAL	US
Accepts	text	text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	deepinfra	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, huggingface

Frequently asked questions

Which is cheaper, Qwen2.5-Coder-32B-Instruct or granite-4.2-30b?

Qwen2.5-Coder-32B-Instruct is 62% cheaper than granite-4.2-30b on input price. Qwen2.5-Coder-32B-Instruct is 77% cheaper than granite-4.2-30b on output price. Qwen2.5-Coder-32B-Instruct is 69% cheaper than granite-4.2-30b on a 1M-in / 200k-out workload.

Which has the larger context, Qwen2.5-Coder-32B-Instruct or granite-4.2-30b?

Qwen2.5-Coder-32B-Instruct: 131K tokens; granite-4.2-30b: 131K tokens.

Where can I use both Qwen2.5-Coder-32B-Instruct and granite-4.2-30b?

deepinfra, edenai, huggingface