Gemma 3 4B IT pricing, context window and limits
Gemma 3 4B IT costs $0.04 per million input tokens and $0.08 per million output tokens at Amazon Bedrock list price. It accepts up to 131,072 tokens of context and returns up to 4,096 tokens.
- Model id
bedrock/google.gemma-3-4b-it - Snapshot
What does Gemma 3 4B IT cost?
| Input | $0.04 |
|---|---|
| Output | $0.08 |
| Cached input (read) | — |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can Gemma 3 4B IT read and write?
| Context window | 131,072 |
|---|---|
| Max output | 4,096 |
What can Gemma 3 4B IT do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | No |
| Structured output | No |
| Reasoning | No |
| Input | text, image |
| Output | text |
What does a request to Gemma 3 4B IT cost?
| A typical request: 1,000 tokens in, 500 out | under $0.0001 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.00048 |
| 1,000 typical requests | $0.08 |
| 1 million tokens in and 1 million out | $0.12 |
Among 199 Amazon Bedrock models with a published price, Gemma 3 4B IT is the 4th cheapest by input price. Its context window is the 162nd largest of 199. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Gemma 3 4B IT through DVARA?
Configure the bedrock provider in the DVARA LLM Gateway and send the model id bedrock/google.gemma-3-4b-it. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Amazon Bedrock models are there?
- Gemma 3 27B IT$0.23 in · $0.38 out · 131K context
- Gemma 4 26B A4B IT$0.13 in · $0.4 out · 262K context
- Gemma 3 12B IT$0.09 in · $0.29 out · 131K context
- Gemma 4 31B IT$0.14 in · $0.4 out · 262K context
- Gemma 4 E2B IT$0.04 in · $0.08 out · 131K context
- GLM-5.3 (Global)$1.68 in · $5.28 out · 1M context
- Grok 4.7 (Global)$2 in · $6 out · 500K context
- Claude Haiku 4.5 (India)$1.1 in · $5.5 out · 200K context
- Grok 4.6 (Global)$2 in · $6 out · 500K context
- Claude Opus 5 (India)$5.5 in · $27.5 out · 1M context
- GPT-6.1 Sol (Global)$2 in · $10 out · 1.05M context
- Claude Sonnet 5 (India)$2.2 in · $11 out · 1M context
Which models from other providers are similar to Gemma 3 4B IT?
These are the closest in context window and input price, one per provider.
- Ministral 3B (latest)Mistral AI · $0.04 in · $0.04 out · 131K context
- Command R7BCohere · $0.0375 in · $0.15 out · 128K context
- Llama 3.1 8BGroq · $0.05 in · $0.08 out · 131K context
- Qwen2.5 7B InstructAlibaba Qwen · $0.072 in · $0.144 out · 131K context
- GLM-4.7-FlashXZhipu GLM · $0.07 in · $0.4 out · 200K context