# Gemma 4 E2B API Pricing

As of October 10, 2026, Gemma 4 E2B costs $0.04 per 1M input tokens and $0.08 per 1M output tokens on Amazon Bedrock Mantle. It has a 128,000-token context window and returns up to 128,000 tokens per response.

- Page: https://models.litellm.ai/models/gemma-4-e2b
- Lab: Google
- LiteLLM model name: `bedrock_mantle/google.gemma-4-e2b`
- Context window: 128,000 tokens
- Max output: 128,000 tokens
- Added to LiteLLM: June 2026
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Amazon Bedrock Mantle | `bedrock_mantle/google.gemma-4-e2b` | $0.04 | $0.08 | – | – | – | 128K |
| Amazon Bedrock Mantle (us-gov-west-1) | `bedrock_mantle/us-gov-west-1/google.gemma-4-e2b` | $0.048 | $0.096 | – | – | – | 128K |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- Amazon Bedrock Mantle: $0.12

100 long-document requests with 100,000 input and 2,000 output tokens each:

- Amazon Bedrock Mantle: $0.416

## Features

Supported: Function calling, Image input, Reasoning.
Not supported: Parallel tool calls.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="bedrock_mantle/google.gemma-4-e2b",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Gemma 4 E2B cost?

Gemma 4 E2B costs $0.04 per 1M input tokens and $0.08 per 1M output tokens on Amazon Bedrock Mantle.

### What is the context window of Gemma 4 E2B?

Gemma 4 E2B has a 128,000-token context window and returns up to 128,000 tokens per response.

### Which providers offer Gemma 4 E2B?

Gemma 4 E2B is available from Amazon Bedrock Mantle through LiteLLM, using the model name bedrock_mantle/google.gemma-4-e2b.

### How do I call Gemma 4 E2B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="bedrock_mantle/google.gemma-4-e2b", 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 4 E2B support?

Gemma 4 E2B supports function calling, image input and reasoning. It does not support parallel tool calls.

### When did LiteLLM add Gemma 4 E2B?

Gemma 4 E2B was added to LiteLLM's model price file in June 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json