Gemma 3 4B IT API Pricing
As of October 10, 2026, Gemma 3 4B IT costs $0.04 per 1M input tokens and $0.08 per 1M output tokens from Amazon Bedrock, the lowest of 3 providers. It has a 128,000-token context window and returns up to 8,000 tokens per response.
google.gemma-3-4b-it.- Input
- $0.04 / 1M tokens
- Output
- $0.08 / 1M tokens
- Context window
- 128,000 tokens
- Max output
- 8,000 tokens
- Providers
- 3
- Added to LiteLLM
- July 2025
Gemma 3 4B IT pricing by provider
3 listings across 3 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Amazon Bedrock | google.gemma-3-4b-it | $0.04 | $0.08 | 128K |
| DeepInfra | deepinfra/google/gemma-3-4b-it | $0.05 | $0.10 | 128K |
| Lemonadegguf | lemonade/Gemma-3-4b-it-GGUF | $0 | $0 | 128K |
Other Gemma 3 4B IT prices on Amazon Bedrock
| Flex input | $0.02 per 1M tokens |
| Flex output | $0.04 per 1M tokens |
What Gemma 3 4B IT costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Amazon Bedrock | $0.12 |
| DeepInfra | $0.15 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Amazon Bedrock | $0.416 |
| DeepInfra | $0.52 |
Gemma 3 4B IT features
- Function calling
- Structured output
- Image input
- Audio input
Use Gemma 3 4B IT with LiteLLM
Call Gemma 3 4B IT through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="google.gemma-3-4b-it",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: gemma-3-4b-it
litellm_params:
model: google.gemma-3-4b-it
aws_region_name: os.environ/AWS_REGION_NAMEcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "gemma-3-4b-it",
"messages": [{"role": "user", "content": "Hello!"}]
}'Gemma 3 4B IT FAQ
How much does Gemma 3 4B IT cost?
Gemma 3 4B IT costs $0.04 per 1M input tokens and $0.08 per 1M output tokens from Amazon Bedrock, the lowest of 3 providers.
What is the context window of Gemma 3 4B IT?
Gemma 3 4B IT has a 128,000-token context window and returns up to 8,000 tokens per response.
Which providers offer Gemma 3 4B IT?
Gemma 3 4B IT is available from 3 providers through LiteLLM: Amazon Bedrock, DeepInfra and Lemonade. The lowest price is on Amazon Bedrock.
How do I call Gemma 3 4B IT with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="google.gemma-3-4b-it", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does Gemma 3 4B IT support?
Gemma 3 4B IT supports function calling, structured output and image input. It does not support audio input.
When did LiteLLM add Gemma 3 4B IT?
Gemma 3 4B IT was added to LiteLLM's model price file in July 2025.
Is Gemma 3 4B IT being deprecated?
Amazon Bedrock lists a deprecation date of March 30, 2027 for google.gemma-3-4b-it.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
- docs.aws.amazon.com/bedrock/latest/userguide/model-card-google-gemma-3-4b-it.html
- deepinfra.com/pricing
LiteLLM docs: Amazon Bedrock, DeepInfra, Lemonade.
Provider pages: Amazon Bedrock, DeepInfra, Lemonade.
