Gemma 3 1B: API Pricing, Context Window & Benchmarks
Gemma 3 1B is a language model from Google, released in March 2025.
The Gemma 3 1B model is a lightweight, 1-billion-parameter language model by Google, optimized for efficiency on resource-limited devices. At 529MB, it processes text at 2,585 tokens/second with a context window of 128,000 tokens. It
Gemma 3 1B benchmarks
Rankings
Quality Tracker
Gemma 3 1B Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sat Jul 18 2026Gemma 3 1B model size
Gemma 3 1B has 1 billion parameters and was trained on 2 trillion tokens. See how it compares to other models in the same parameter range.
Gemma 3 1B API
Available from the model provider
Gemma 3 1B has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationGemma 3 1B latency
Gemma 3 1B time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Gemma 3 1B examples
Recent arena outputs from Gemma 3 1B, picked from the highest-ranked matchups.
Gemma 3 1B license
Gemma 3 1B is released under the Gemma license, which permits commercial use, has 1.0B parameters.
- License
- Gemma
- Commercial use allowed
- Parameters
- 1.0B
Google Gemma Terms of Use
Gemma 3 1B resources
Official sources for Gemma 3 1B: api documentation, official playground, paper or system card, official launch post.
Gemma 3 1B vs other models
The most-compared alternatives to Gemma 3 1B are Phi-3.5-mini-instruct, Llama 3.2 3B Instruct, Pixtral-12B. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Gemma 3 1B
Models ranked just above and below Gemma 3 1B by LLM Stats score.
FAQ
Common questions about Gemma 3 1B.