Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/Emanuele-web04/dpcode/llms.txt

Use this file to discover all available pages before exploring further.

The Gemini provider connects DP Code to Google’s Gemini CLI coding agent. The provider kind is gemini. DP Code launches the gemini binary and communicates with it using the Agent Communication Protocol (ACP). Events are streamed to your browser through the DP Code WebSocket connection.

​
Prerequisites

1

Install Gemini CLI

Install the Gemini CLI from Google. Check the official Gemini CLI repository for the latest installation instructions.
npm i -g @google/gemini-cli
Verify the installation:
gemini --version
2

Authenticate

Run gemini to complete the Google account login flow or set up your API key.
gemini
3

Confirm the binary is on your PATH

DP Code looks for gemini on PATH by default. Set binaryPath if you installed it to a non-standard location.

​
Settings

Configure the Gemini provider under providers.gemini in your DP Code server settings.
​
providers.gemini.binaryPath
string
default:"gemini"
Path to the gemini executable. Accepts a bare binary name resolved from PATH or an absolute path.
​
providers.gemini.customModels
string[]
default:"[]"
List of additional model slugs to make available in the model picker. Each entry must be a non-empty string with a maximum of 256 characters.
​
providers.gemini.enabled
boolean
default:"true"
Set to false to disable the Gemini provider. Existing sessions continue until you reload.

​
Model selection

The following models are available by default. DP Code selects auto-gemini-3 when no model is specified.
Model slugDisplay name
auto-gemini-3Auto Gemini 3
auto-gemini-2.5Auto Gemini 2.5
gemini-3.1-pro-previewGemini 3.1 Pro Preview
gemini-3-flash-previewGemini 3 Flash Preview
gemini-3.1-flash-lite-previewGemini 3.1 Flash Lite Preview
gemini-2.5-proGemini 2.5 Pro
gemini-2.5-flashGemini 2.5 Flash
gemini-2.5-flash-liteGemini 2.5 Flash Lite

​
Model aliases

AliasResolves to
autoauto-gemini-3
auto-gemini-3auto-gemini-3
auto-gemini-2.5auto-gemini-2.5
gemini-3-pro-previewgemini-3.1-pro-preview
gemini-2.5-progemini-2.5-pro
gemini-2.5-flashgemini-2.5-flash
gemini-2.5-flash-litegemini-2.5-flash-lite

​
Thinking level (Gemini 3 models)

Gemini 3 series models accept a thinkingLevel option with two values:
ValueLabelDefault
HIGHHighYes
LOWLow—
Set the thinking level in the model options panel when starting or continuing a thread.

​
Thinking budget (Gemini 2.5 models)

Gemini 2.5 models use a token-based thinking budget instead of a level. The available values are:
ValueLabelDefault
-1DynamicYes
512512 Tokens—
-1 (Dynamic) lets the model decide how many tokens to spend on reasoning. 512 caps the thinking budget at 512 tokens.
Use the auto-gemini-3 or auto-gemini-2.5 slugs to let DP Code and the Gemini CLI pick the best available version automatically.

Gemini CLI repository

Source code and releases for the Gemini CLI.

Google AI Studio

Manage API keys and explore Gemini model capabilities.

Build docs developers (and LLMs) love

Get started for freeTalk to us