# Gemma 4 12B IT API Pricing

As of October 10, 2026, Gemma 4 12B IT costs $0.30 per 1M input tokens and $2.00 per 1M output tokens on Sail, with cache reads at $0.15 per 1M tokens. It has a 16,384-token context window and returns up to 16,384 tokens per response.

- Page: https://models.litellm.ai/models/gemma-4-12b-it
- Lab: Google
- LiteLLM model name: `sail/google/gemma-4-12B-it`
- Context window: 16,384 tokens
- Max output: 16,384 tokens
- Added to LiteLLM: September 26, 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 |
|---|---|---|---|---|---|---|---|
| Sail | `sail/google/gemma-4-12B-it` | $0.30 | $2.00 | $0.15 | – | – | 16K |

## Cost examples

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

- Sail: $1.60

## Features

Supported: Function calling, Structured output, Reasoning, Prompt caching.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="sail/google/gemma-4-12B-it",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Gemma 4 12B IT cost?

Gemma 4 12B IT costs $0.30 per 1M input tokens and $2.00 per 1M output tokens on Sail, with cache reads at $0.15 per 1M tokens.

### What is the context window of Gemma 4 12B IT?

Gemma 4 12B IT has a 16,384-token context window and returns up to 16,384 tokens per response.

### Which providers offer Gemma 4 12B IT?

Gemma 4 12B IT is available from Sail through LiteLLM, using the model name sail/google/gemma-4-12B-it.

### How do I call Gemma 4 12B IT with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="sail/google/gemma-4-12B-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 4 12B IT support?

Gemma 4 12B IT supports function calling, structured output, reasoning and prompt caching.

### When did LiteLLM add Gemma 4 12B IT?

Gemma 4 12B IT was added to LiteLLM's model price file on September 26, 2026.

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