Gemma 2 2B
Smallest Gemma 2, runs on a phone or laptop. Strong tiny-model baseline.
Gemma 2 2B is a efficient AI model from Google. It costs $0.0200 per million input tokens and $0.0200 per million output tokens (blended $0.0200/M), with a 8,000-token context window.
RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.
Hand-maintained from Google's published pricing; no check date on record.
- Edge / mobile capable
- Open weights
- 2B params
- On-device assistants
- Edge inference
Benchmarks
More from Google
See all 23 →Frequently asked questions
How much does Gemma 2 2B cost?
Gemma 2 2B costs $0.0200 per million input tokens and $0.0200 per million output tokens, for a blended reference rate of $0.0200 per million tokens.
What is Gemma 2 2B's context window?
Gemma 2 2B supports up to 8,000 tokens of context in a single request.
What is Gemma 2 2B best for?
Gemma 2 2B is well suited to Edge / mobile capable, Open weights and 2B params.
Who makes Gemma 2 2B?
Gemma 2 2B is developed and served by Google. It was released in Jul 2024.
