Trae

Trae is ByteDance's AI-native IDE, with built-in Chat, Builder, and Agent modes. Trae doesn't ship a generic "OpenAI-compatible" provider, but its OpenAI and Anthropic providers both accept a Custom Request URL, so either one can be pointed at Tempools.

Update Trae to the latest version first. Older builds of the Add Model dialog don't expose the Custom Request URL field or the Other Models option for manually entering model names, so the steps below won't line up. Open the Trae menu in the top-left and pick Check for Updates to upgrade.

Prerequisites

Trae IDE desktop app installed, on the latest version (IDE mode or SOLO mode)
A Tempools API key from the console

Configuration

Open model settings

Click the Settings icon in the top-right of the Trae window (in SOLO mode, the same icon lives in the top-right of the chat panel). In the left navigation, pick Models, then click + Add Model — the Add Model dialog opens.

Pick a provider and set the custom URL

Either of the two paths below works — pick one:

Provider: OpenAI
Model: click Other Models and enter the exact card title from the Models page or the Console → Models catalog
API Key: paste your Tempools key (starts with sk-tb-)
Custom Request URL: https://api.tempools.com/v1/chat/completions

Trae expects the full request path here, not a base URL. This path can reach every model family behind Tempools (Claude, Gemini, and more); for the model field, use the exact title shown on the model card.

Provider: Anthropic
Model: click Other Models and enter the exact title of a Claude-family model card
API Key: paste your Tempools key
Custom Request URL: https://api.tempools.com/messages

This path only reaches Claude-family models. For mixed-provider routing, use OpenAI.

Click Add Model. Trae validates by calling the provider immediately — a bad key, URL, or model name surfaces in the dialog's error log.

Select it in a conversation

In Chat / Builder / Agent, open the model dropdown at the top — the Tempools model you just added is now listed. When building a custom agent, the Use custom models section under the agent config references the same list.

Verify

Open Chat and ask something small, e.g. "Summarize this project in three sentences." A coherent reply means you're set.

Settings → Models lets you Enable / Disable or delete custom models at any time. A disabled model stays in the list but is hidden from the chat model picker — handy for toggling without re-entering credentials.

Trae's inline autocomplete (Tab-key) is powered by a separate engine called Tab-Cue, which cannot be pointed at a custom provider — the Tempools setup only applies to Chat / Builder / Agent. If you want routing for completions too, use a third-party completion extension or another IDE.

Stuck? See the FAQ.