# Gemini 2.5 Flash Image API Pricing

As of October 10, 2026, Gemini 2.5 Flash Image costs $0.039 per image on Google AI Studio, plus $0.30 per 1M input tokens. It has a 65,536-token context window and returns up to 32,768 tokens per response.

- Page: https://models.litellm.ai/models/gemini-2.5-flash-image
- Lab: Google
- LiteLLM model name: `gemini/gemini-2.5-flash-image`
- Context window: 65,536 tokens
- Max output: 32,768 tokens
- Added to LiteLLM: October 2025
- Deprecation date: March 15, 2027
- 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 | `gemini/gemini-2.5-flash-image` | $0.30 | $2.50 | $0.03 | $0.039 | – | 64K |
| Google Vertex AI | `vertex_ai/gemini-2.5-flash-image` | $0.30 | $2.50 | – | $0.039 | – | 32K |

## Cost examples

Generating 1,000 images:

- Google AI Studio: $39.00
- Google Vertex AI: $39.00

## Features

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

## Use it with LiteLLM

```python
from litellm import image_generation

response = image_generation(
    model="gemini/gemini-2.5-flash-image",
    prompt="A cute baby sea otter",
)
```

## FAQ

### How much does Gemini 2.5 Flash Image cost?

Gemini 2.5 Flash Image costs $0.039 per image on Google AI Studio, plus $0.30 per 1M input tokens.

### What is the context window of Gemini 2.5 Flash Image?

Gemini 2.5 Flash Image has a 65,536-token context window and returns up to 32,768 tokens per response.

### Which providers offer Gemini 2.5 Flash Image?

Gemini 2.5 Flash Image is available from 2 providers through LiteLLM: Google AI Studio and Google Vertex AI.

### How do I call Gemini 2.5 Flash Image with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="gemini/gemini-2.5-flash-image", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/images/generations from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does Gemini 2.5 Flash Image support?

Gemini 2.5 Flash Image supports parallel tool calls, image input, PDF input and prompt caching. It does not support function calling, structured output, audio input, audio output, reasoning and web search.

### When did LiteLLM add Gemini 2.5 Flash Image?

Gemini 2.5 Flash Image was added to LiteLLM's model price file in October 2025.

### Is Gemini 2.5 Flash Image being deprecated?

Google AI Studio lists a deprecation date of March 15, 2027 for gemini/gemini-2.5-flash-image.

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