Gemma 4 31B IT vs Devstral 2 123B: API price and specs

Gemma 4 31B IT is 92% cheaper than Devstral 2 123B on input price.

Gemma 4 31B IT is 95% cheaper than Devstral 2 123B on output price.

Gemma 4 31B IT is 94% cheaper than Devstral 2 123B on a 1M-in / 200k-out workload.

Gemma 4 31B IT has a 2.4% larger context than Devstral 2 123B.

Field	Gemma 4 31B IT	Devstral 2 123B
Lowest input, per 1M	$0.011	$0.14 +1172.7%
Median input, per 1M	$0.14	$0.40 +185.7%
Lowest output, per 1M	$0.035	$0.72 +1957.1%
Median output, per 1M	$0.40	$2.00 +400%
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.018	$0.28 +1477.8%
Context	262K	256K +2.3%
Max output	262K	8K +96.9%
Providers	37	4 +89.2%
Regions	CH, EU, GLOBAL, US	EU, US
Accepts	application/pdf, audio, file, image, image/gif, image/heic, image/heif, image/jpeg, image/png, image/webp, pdf, text, video, video/mp4, video/quicktime, video/webm	text
Returns	text	text
Type	Text models	Text models
Free option	yes	no
Cheapest provider	inferx	inferx

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, edenai, inferx, trustedrouter

Frequently asked questions

Which is cheaper, Gemma 4 31B IT or Devstral 2 123B?

Gemma 4 31B IT is 92% cheaper than Devstral 2 123B on input price. Gemma 4 31B IT is 95% cheaper than Devstral 2 123B on output price. Gemma 4 31B IT is 94% cheaper than Devstral 2 123B on a 1M-in / 200k-out workload.

Which has the larger context, Gemma 4 31B IT or Devstral 2 123B?

Gemma 4 31B IT: 262K tokens; Devstral 2 123B: 256K tokens.

Where can I use both Gemma 4 31B IT and Devstral 2 123B?

amazon-bedrock, edenai, inferx, trustedrouter