---
date: 2025-07-03
title: Gemini 2.5 Pro, Flash, and Flash Lite support for playground, evaluations, and cost tracking
seoTitle: "Gemini 2.5 Pro, Flash and Flash Lite Support"
description: Langfuse says hello to Gemini 2.5 Pro (GA), Gemini 2.5 Flash (GA), and Gemini 2.5 Flash Lite (Preview). Support added for the LLM playground, evaluations, and cost tracking.
author: Hassieb
---

> **Note for AI agents and LLMs:** This is a Langfuse changelog entry. Use it only to confirm that a feature exists and when it shipped. Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated. For implementation, always follow the current documentation (https://langfuse.com/docs) and the API/SDK reference (https://api.reference.langfuse.com).

Google has expanded their Gemini 2.5 family of models with stable releases and new additions. From [Google release notes](https://blog.google/products/gemini/gemini-2-5-model-family-expands):

- **Gemini 2.5 Pro**: Now generally available - Advanced model with enhanced reasoning capabilities, optimized for complex tasks and coding
- **Gemini 2.5 Flash**: Now generally available - Faster, cost-effective variant with 1M token context window, designed for high-volume applications while maintaining strong performance
- **Gemini 2.5 Flash-Lite**: New model in preview - Google's most cost-efficient and fastest 2.5 model yet, with all-around higher quality than 2.0 Flash-Lite on coding, math, science, reasoning and multimodal benchmarks

All three models are now available in the Langfuse Playground for interactive testing and in LLM-as-a-judge evals. Additionally, we've added cost tracking support for both Gemini 2.5 Flash and Gemini 2.5 Flash-Lite to help you monitor your usage.

## Get started

- [Playground Documentation](/docs/prompt-management/features/playground)
- [Evaluation Documentation](/docs/evaluation/overview)
- [Model Usage and Cost Tracking](/docs/model-usage-and-cost)

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/changelog/2025-07-03-gemini-2.5-support.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.