# Gemini 3 Pro API Pricing

As of October 10, 2026, Gemini 3 Pro costs $2.00 per 1M input tokens and $12.00 per 1M output tokens from Replicate, the lowest of 2 providers. It has a 1,048,576-token context window and returns up to 65,536 tokens per response.

- Page: https://models.litellm.ai/models/gemini-3-pro
- Lab: Google
- LiteLLM model name: `replicate/google/gemini-3-pro`
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Added to LiteLLM: January 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 |
|---|---|---|---|---|---|---|---|
| Replicate | `replicate/google/gemini-3-pro` | $2.00 | $12.00 | – | – | – | – |
| Databricks | `databricks/databricks-gemini-3-pro` | $2.50 | $15.00 | $0.25 | – | – | 1M |

## Cost examples

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

- Replicate: $10.00
- Databricks: $12.50

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

- Replicate: $22.40
- Databricks: $28.00

## Features

Supported: Image input, Audio input, Video input, Prompt caching.
Not supported: Function calling, Parallel tool calls, Structured output.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="replicate/google/gemini-3-pro",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Gemini 3 Pro cost?

Gemini 3 Pro costs $2.00 per 1M input tokens and $12.00 per 1M output tokens from Replicate, the lowest of 2 providers. Above 200K input tokens, input costs $4.00 and output costs $18.00 per 1M tokens.

### What is the context window of Gemini 3 Pro?

Gemini 3 Pro has a 1,048,576-token context window and returns up to 65,536 tokens per response.

### Which providers offer Gemini 3 Pro?

Gemini 3 Pro is available from 2 providers through LiteLLM: Replicate and Databricks. The lowest price is on Replicate.

### How do I call Gemini 3 Pro with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="replicate/google/gemini-3-pro", 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 Gemini 3 Pro support?

Gemini 3 Pro supports image input, audio input, video input and prompt caching. It does not support function calling, parallel tool calls and structured output.

### When did LiteLLM add Gemini 3 Pro?

Gemini 3 Pro was added to LiteLLM's model price file in January 2026.

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