gemma-4-31b vs gpt-6.1-terra
- gemma-4-31b
- 1 advantage
- gpt-6.1-terra
- 1 advantage
How to choose
gemma-4-31bOpen weights
gpt-6.1-terraLonger context: 1.1M tokens
gemma-4-31b
By GoogleNew in the last two weeks
gpt-6.1-terra
By OpenAI
Where they differ
gemma-4-31bgpt-6.1-terra
On this site
98%102 callsAvailability, last 3 days—
96%193 testsAvailability, this week's tests—
2.1sAverage response this week—
FreeReference price per million output tokens$7.50
#8Place in this week's rankingUnranked
FreeReference price per million input tokens$1.50
The model itself
256K tokensContext length1.1M tokens
256K tokensLongest reply128K tokens
Jan 2025Knowledge cutoffJun 2026
2 Apr 2026Released26 Oct 2026
YesOpen weightsNo
FreeReference price per million cache-read tokens$0.075
Where they match
- Reads imagesYes
- Calls toolsYes
- Thinks before answeringYes
- Conversations used for trainingNot used for training
Availability over 3 days counts every call made through the site; this week's availability counts every call over the last 7 days, scheduled tests included, and response time comes from the site's own scheduled tests. Models marked as free are counted in calls; paid models are charged by usage, in US dollars.
Compare next
gemma-4-31b against other models
gpt-6.1-terra against other models
- vs muse-spark-open$6.38Reference price per million output tokens
- vs glm-5v-turbo$6.00Reference price per million output tokens
- vs kimi-k2.7-code$6.00Reference price per million output tokens
- vs grok-4.7$9.00Reference price per million output tokens
- vs qwen3.8-max$9.00Reference price per million output tokens
- vs qwen3.8-2.4t-a95b$9.00Reference price per million output tokens
Figures come from real calls made through this site. Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.
