---
title: "TRAE setup"
description: "Configure TRAE for Infistar and check the address, key and model."
lastUpdated: 2026-10-22
---

Install TRAE from its [official site](https://www.trae.ai/). Open model settings and add a custom model where that feature is available in your edition.

Choose OpenAI Chat Completions format. For a field accepting a complete request URL, use `https://infistar.ai/v1/chat/completions`; for a base URL field, use `https://infistar.ai/v1`. Do not append the path twice. Enter your Infistar key and exact model ID, then save and select the model in chat.

Enable multimodal options only if the model supports them. Interface names and custom-provider availability can differ by TRAE edition; follow the settings shown in your installed version.


## Check the connection

Use an exact model ID available to your key, and begin with a short text request. For coding agents, first ask for a reply without reading or changing files or running commands. A successful text reply does not verify every tool or multimodal feature.

For 401, check the key and its status. For 404, check the address and protocol. For model errors, recheck the model ID and selected group. See [HTTP troubleshooting](/en/troubleshooting/http-status-troubleshooting).

[Upstream documentation](https://docs.trae.ai/ide/models).