We recommend using [Gemini 4 Hydrogen](https://cursor.com/docs/models/gemini-4-hydrogen.md). It's Google's successor to Gemini 3.8 Flash.

Gemini 3.8 Flash is Google's previous speed-tier model. It pairs strong agentic coding performance with low per-token costs. Use it for high-throughput coding tasks that benefit from reasoning and a large context window.

## Strengths

- $0.75 per million input tokens and $3.75 per million output tokens.
- 90% discount on cached input tokens ($0.075/1M). Useful for repeated context such as large codebases.
- 1M token context window. Fits substantial portions of a repository in a single request.
- Three effort levels: high (the default), medium, and low. Drop to medium or low for faster responses on simpler tasks.

## Tools

Gemini 3.8 Flash has access to all agent tools when used with Cursor including:

Learn more about [how tools work](https://cursor.com/docs/agent/overview.md#tools) and [tool calling fundamentals](https://cursor.com/learn/tool-calling.md).

## Pricing

Gemini 3.8 Flash is a third-party model, so it isn't part of the usage included with Cursor [plans](https://cursor.com/docs/models-and-pricing.md#third-party-models). On The X Subscription it's billed at the rates below from your prepaid credit. On legacy Cursor plans it draws from the **Other Models** pool. All prices are per million tokens.


---

## Sitemap

[Overview of all docs pages](/llms.txt)
