# Gemini Exp API Pricing

As of October 10, 2026, Gemini Exp costs $0.30 per 1M input tokens and $2.50 per 1M output tokens on Google AI Studio, with cache reads at $0.03 per 1M tokens. It has a 1,048,576-token context window and returns up to 65,535 tokens per response.

- Page: https://models.litellm.ai/models/gemini-exp
- Lab: Google
- LiteLLM model name: `gemini-exp-1206`
- Context window: 1,048,576 tokens
- Max output: 65,535 tokens
- Added to LiteLLM: November 2024
- 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 |
|---|---|---|---|---|---|---|---|
| Google AI Studio (snapshot 1206) | `gemini-exp-1206` | $0.30 | $2.50 | $0.03 | – | – | 1M |
| Google AI Studio (snapshot 1114) | `gemini/gemini-exp-1114` | $0 | $0 | – | – | – | 1M |
| Google AI Studio (snapshot 1206) | `gemini/gemini-exp-1206` | $0 | $0 | – | – | – | 2.1M |

## Cost examples

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

- Google AI Studio: $1.85

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

- Google AI Studio: $3.50

## Features

Supported: Function calling, Parallel tool calls, Structured output, Image input, PDF input, Reasoning, Prompt caching, Web search.
Not supported: Audio output.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="gemini-exp-1206",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Gemini Exp cost?

Gemini Exp costs $0.30 per 1M input tokens and $2.50 per 1M output tokens on Google AI Studio, with cache reads at $0.03 per 1M tokens.

### What is the context window of Gemini Exp?

Gemini Exp has a 1,048,576-token context window and returns up to 65,535 tokens per response.

### Which providers offer Gemini Exp?

Gemini Exp is available from Google AI Studio through LiteLLM, using the model name gemini-exp-1206.

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

Use the LiteLLM Python SDK with model="gemini-exp-1206", 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 Exp support?

Gemini Exp supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning, prompt caching and web search. It does not support audio output.

### When did LiteLLM add Gemini Exp?

Gemini Exp was added to LiteLLM's model price file in November 2024.

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