Gemini 2.5 Flash overview

Provider

The company that provides the model

Google

Context window

The number of tokens you can send in a prompt

1,048,576 tokens

Maximum output

The maximum number of tokens a model can generate in one request

65,536 tokens

Input token cost

The cost of prompt tokens sent to the model

$0.15 / 1M input tokens (free while in experimental stage)

Output token cost

The cost of output tokens generated by the model

$0.60 / 1M output tokens (free while in experimental stage)

Knowledge cut-off date

When the model's knowledge ends

January 1, 2025
Unknown

Release date

When the model was launched

April 17, 2025

Gemini 2.5 Flash functionality

Function (tool calling) support

Capability for the model to use external tools

Yes

Vision support

Ability to process and analyze visual inputs, like images

Yes

Multilingual

Support for multiple languages

Yes

Fine-tuning

Whether the model supports fine-tuning on custom datasets

No

Common questions about Gemini 2.5 Flash

What is Gemini 2.5 Flash?

Gemini 2.5 Flash is Google’s first hybrid reasoning model, combining the speed and cost-efficiency of the 2.0 Flash model with adjustable thinking budgets. This allows developers to balance quality, cost, and latency in their applications.

How much does Gemini 2.5 Flash cost?

Gemini 2.5 Flash has a cost structure of $0.15 per million input tokens and $0.60 per million output tokens, though it is free during the experimental stage.

What is the input token cost for Gemini 2.5 Flash?

The input token cost for Gemini 2.5 Flash is $0.15 per million input tokens.

What is the output token cost for Gemini 2.5 Flash?

The output token cost for Gemini 2.5 Flash is $0.60 per million output tokens.

What is the context window for Gemini 2.5 Flash?

Gemini 2.5 Flash supports a context window of up to 1,048,576 tokens, which allows it to handle large and complex inputs effectively.

What is the maximum output length for Gemini 2.5 Flash?

Gemini 2.5 Flash can generate up to 65,536 tokens in a single output.

When was Gemini 2.5 Flash released?

Gemini 2.5 Flash was released on April 17, 2025.

How recent is the training data for Gemini 2.5 Flash?

The knowledge cut-off date for Gemini 2.5 Flash is January 1, 2025.

Does Gemini 2.5 Flash support tool calling or functions?

Yes, Gemini 2.5 Flash supports tool calling, allowing it to use external tools as part of its operations.

Does Gemini 2.5 Flash support vision capabilities?

Yes, Gemini 2.5 Flash supports vision capabilities, allowing it to process and analyze visual inputs like images.

Is Gemini 2.5 Flash a multilingual model?

Yes, Gemini 2.5 Flash supports multiple languages, making it suitable for global applications.

Does Gemini 2.5 Flash support fine-tuning?

No, Gemini 2.5 Flash does not support fine-tuning.

Where can I find the official documentation for Gemini 2.5 Flash?

You can find the official documentation for Gemini 2.5 Flash here:
Gemini 2.5 Flash Documentation

Let me know if you need any adjustments!

Join thousands of AI builders

Collaborate with thousands of AI builders to discover, manage, and improve prompts—free to get started.