Google: Gemma 3 4B
Analysis Summary
Google's Gemma 3 4B is a compact open-weight model released in March 2025, supporting text and image input. At an intelligence index of 6.3 and coding index of 2.9, it sits at the lower end of the capability spectrum. Its math index of 12.7 and agentic index of 2.9 confirm it is not designed for complex reasoning or autonomous workflows.
For businesses, its primary advantage is cost: at $0.05 input and $0.10 output per million tokens, it is among the cheapest vision-capable models available. The 131K context window is a practical positive. However, instruction-following, long-context reasoning, and coding scores are all low, limiting it to simple classification, tagging, or basic image description tasks.
It is best deployed as a lightweight, cost-sensitive component in larger pipelines rather than as a standalone business model. Teams needing reliable reasoning or structured output should look to larger models in the Gemma 3 family or beyond.
Assessed June 9, 2026
Editorial notes
Gemma 3 4B from Google is a very small open-weight model with vision support and low pricing, suited only to simple, lightweight tasks.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Google: Gemma 3 4B compares
Google: Gemma 3 4B ranks #369 of 377 AI models we track for overall intelligence, #291 of 314 for coding, #283 of 289 for agentic tasks. Its 131K-token context window is larger than 59% of the models we list. At $0.05 per million input tokens it is cheaper than 73% of comparable models.
About Google: Gemma 3 4B
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,..
Capabilities
Architecture Detail
| Instruct Type | gemma |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Google: Gemma 3 4B stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
google/gemma-3-4b-it
|
| Provider | |
| Release Date | March 13, 2025 |
| Context Length | 131,072 tokens |
| Max Completion | 16,384 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.05 | $0.000050 |
| Output | $0.10 | $0.000100 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
External Resources
Frequently asked questions about Google: Gemma 3 4B
How much does Google: Gemma 3 4B cost?
Google: Gemma 3 4B costs $0.05 per million input tokens and $0.10 per million output tokens.
What is the context window of Google: Gemma 3 4B?
Google: Gemma 3 4B has a context window of 131,072 tokens (131K).
Is Google: Gemma 3 4B good for coding?
On our coding benchmark index, Google: Gemma 3 4B ranks #291 of 314 models, placing it in the broader range of the field for code generation and debugging.
What can Google: Gemma 3 4B do?
Google: Gemma 3 4B supports image/vision input.
Who created Google: Gemma 3 4B?
Google: Gemma 3 4B is developed by Google and was released on March 13, 2025.
