BotGem Setup

BotGem is a cross-platform AI desktop client (macOS, Windows, iOS, Android) that supports custom API providers, making it easy to use for everyday AI conversations.

Prerequisites

An kineticRouter account with an API Key (Get one here )
BotGem installed (Download )

Setup Steps

Step 1: Open Settings

Launch BotGem and click Settings in the left sidebar.

This screenshot will be refreshed with kineticRouter branding during the integration documentation pass.

Step 2: Go to Service Provider

In the Settings page, click Service Provider.

This screenshot will be refreshed with kineticRouter branding during the integration documentation pass.

Step 3: Click + and Select a Protocol

Click the + button in the top right and choose a protocol type.

kineticRouter supports the following protocols — OpenAI is recommended:

Protocol	Select	Supported Models
OpenAI Chat (recommended)	OpenAI	`openai/gpt-4.1`, `openai/gpt-4.1-mini`, `openai/gpt-5.4-mini`, etc. (examples only)
Claude	Claude	`anthropic/claude-sonnet-4.6`, `anthropic/claude-opus-4.6`, `anthropic/claude-haiku-4.5`

BotGem does not support the OpenAI Responses protocol (/v1/responses). This protocol uses an input field instead of messages, and BotGem only supports the standard Chat Completions format.

This screenshot will be refreshed with kineticRouter branding during the integration documentation pass.

Step 4: Fill in the Configuration

Fill in the configuration form based on the protocol selected in Step 3.

API Server by protocol:

Protocol	API Server
OpenAI Chat (recommended)	`https://api.kineticrouter.com`
Claude	`https://api.kineticrouter.com/anthropic`

Example using OpenAI Chat:

Field	Value
Name	`kineticrouter` (or any name)
API Server	`https://api.kineticrouter.com`
API Key	Your kineticRouter API Key
Models	Click Refresh to auto-fetch, or type manually, e.g. `gpt-4.1`

This screenshot will be refreshed with kineticRouter branding during the integration documentation pass.

When you enter https://api.kineticrouter.com, BotGem automatically appends /v1/chat/completions. Using OpenAI Chat, you can call any model — just use the provider/model-name format when typing manually, e.g. anthropic/claude-opus-4.5 or deepseek/deepseek-v3.2.

Step 5: Check Connection and Save

Click Check Connection. Once you see “Connected successfully!” at the top, click Save.

This screenshot will be refreshed with kineticRouter branding during the integration documentation pass.

Start Using

After saving, go back to the main screen and click Start Chat. The current model name is shown at the top of the chat window. Type your message to start.

This screenshot will be refreshed with kineticRouter branding during the integration documentation pass.

Troubleshooting

Q: Connection check fails

Make sure the API Server address is correct (see table above)
Make sure your API Key is copied in full from the kineticRouter Console with no extra spaces
Check your network connection

Q: The model I want isn’t in the list

Click Refresh to auto-fetch the model list. Names in the list have no prefix (e.g. gpt-4.1).

To use a model not in the list, type the full model name in the format provider/model-name, for example:

Model	Input name
DeepSeek V3	`deepseek/deepseek-v3.2`
Claude Sonnet	`anthropic/claude-sonnet-4.6`

See all available models at Models .