Gemma 3n 4B
Provider: Google AI US
Overview
Gemma 3n 4B is a model from Google AI, positioned as a cost-optimized option within the Gemma family. It targets workloads requiring a balanced price point and a moderate context window for general text processing tasks.
Strengths
- Competitive output pricing at $0.12 per million tokens.
- Offers a practical 32,768 token context window.
- Balanced input token cost compared to similarly priced models.
Best use cases
- Generating short-form text content like summaries or social media updates.
- Implementing cost-efficient chatbots for customer service interactions.
- Performing text classification or sentiment analysis on moderate-length inputs.
- Extracting specific information from documents up to 32,768 tokens in length.
Pricing position
Gemma 3n 4B features a competitive input price of $0.06 per million tokens, comparable to several peers like GLM 4.7 Flash. Its output price of $0.12 per million tokens is lower than most similarly-priced peer models and many larger Google AI siblings, though higher than Google's Gemma 3 4B and Mistral Small 3.
Caveats
The model's maximum output token limit and specific capabilities like vision or advanced reasoning are not provided in the data. Its 32,768-token context window is notably smaller than other Gemma 3 models or Gemini 2.0 Flash Lite, making it less suitable for very long-form tasks. There is no free tier available for this model.
Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.
Key facts
- Max output
- 29K tokens
- Tracked since
- 2026-05-08
- Last updated
- 2026-08-26
Features
Price history
- 2026-08-26 No longer listed
Monthly cost estimate
| Scale | Input (M) | Output (M) | Monthly |
|---|---|---|---|
| 0.1M (hobby) | 0.1 | 0.05 | $0.01 |
| 1M (small app) | 1 | 0.5 | $0.12 |
| 10M (mid scale) | 10 | 5 | $1.20 |
| 100M (large) | 100 | 50 | $12.00 |
※ Cache and batch discounts not factored in. Detailed calculator
Official resources
Other models from Google AI
Similar-priced models
Source: OpenRouter API