Aider | Vtrix API Docs

Overview

Aider can connect to OpenAI-compatible APIs. Point Aider’s OpenAI API base URL to Vtrix, set your Vtrix API key, and choose a Vtrix model ID.

Prerequisites

Python 3.9 or higher
Aider
A Vtrix API key, created in Settings

Optional: use Vtrix Doctor

You can also use Vtrix Doctor to check the local Base URL, API key, and model settings before editing files. Supported tools, including OpenClaw and Hermes, can be configured after confirmation.

Configuration Steps

Install Aider

• Using the install script

curl -LsSf https://aider.chat/install.sh | sh

• Or using pipx

python -m pip install pipx
pipx install aider-chat

After installation, run:

aider --version

Configure the Vtrix Base URL

Aider reads OpenAI-compatible settings from its own AIDER_OPENAI_API_* environment variables. This keeps the Vtrix configuration scoped to Aider instead of replacing your global OpenAI variables.

Add the following to ~/.bashrc or ~/.zshrc:

export AIDER_OPENAI_API_KEY="YOUR_VTRIX_API_KEY"
export AIDER_OPENAI_API_BASE="https://cloud.vtrix.ai/llm"

After updating the file, restart your terminal or run:

source ~/.zshrc

Base URL

Use https://cloud.vtrix.ai/llm as the OpenAI-compatible Vtrix base URL. Aider will call the chat completions path under that base URL.

Choose a Vtrix model

Start Aider with a Vtrix model ID. For OpenAI-compatible custom endpoints, prefix the model with openai/:

aider --model openai/gpt-5.5

To use another Vtrix model, change only the model ID after openai/.

Type	Example model	Notes
High performance	`openai/gpt-5.5`	Strong general coding and reasoning
Standard	`openai/gpt-5.4`	Balanced daily development
Qwen	`openai/qwen3.7-max`	Qwen route through the same Vtrix base URL

Tip

View current model IDs on the Models page. Copy the model ID exactly as shown there.

Start a project session

Go to your project directory and start Aider:

cd /path/to/your/project
aider --model openai/gpt-5.5

You can also pass a one-off prompt:

aider --model openai/gpt-5.5 --message "Summarize this project in one sentence"

If Aider responds normally, requests are reaching Vtrix through the configured base URL. You can also check usage or billing in Vtrix Settings.

Troubleshooting

Error: 401 Unauthorized

Cause: The Vtrix API key is missing, incorrect, or not loaded in the current terminal session.

Fix:

echo $AIDER_OPENAI_API_KEY

If the value is empty, check ~/.zshrc or ~/.bashrc, then reopen your terminal.

Error: model not found

Cause: The model ID after openai/ is incorrect or unavailable.

Fix: Open the Models page, copy the model ID, and run Aider again with --model openai/<model-id>.

Requests still go to another provider

Cause: Other Aider or OpenAI environment variables may override the values you expected.

Fix:

env | grep -E 'AIDER_OPENAI|OPENAI_API'

Confirm that AIDER_OPENAI_API_BASE is https://cloud.vtrix.ai/llm and AIDER_OPENAI_API_KEY contains your Vtrix API key.

Request timeout

Cause: The task is large, the network is unstable, or the selected model takes longer to respond.

Fix: Split the request into smaller steps or choose a faster model from the Vtrix model list.