Standard Compute

Which API should you use with TRAE?

For TRAE's agent on your own monthly-priced API, the best fit is a flat-rate OpenAI-compatible custom model: in Settings → Models → Add Model → Custom Model, choose OpenAI Chat Completions, enter the base URL https://api.stdcmpt.com/v1 and your Standard Compute key, from $19 a month with a $20 compute budget. TRAE's own plans are Pro at $20 a month with $20 of usage, Pro+ at $60 and Ultra at $200. The catch: Auto mode never uses custom models, and the Free plan is listed as Auto mode only, so plan on picking your custom model by hand.

Guide updated 2026-10-14. Check each provider's current terms below.
Light or occasional use
TRAE Pro's $20 of monthly usage is the simplest bill if your agent work fits inside it. A pay-as-you-go OpenRouter key added as a custom model suits occasional use.
One fixed monthly bill
When agent sessions regularly outrun Pro's $20 of usage, a Standard Compute custom model keeps the model bill at the plan price. Requests stop at the monthly compute budget instead of billing overage.

API and subscription options for TRAE

OptionPriceWhat you get
TRAE plans$0 / $20 / $60 / $200 per moFree is Auto mode only with limited usage. Pro ($20 of usage a month), Pro+ ($60) and Ultra ($200) add every built-in model. Source: trae.ai
Standard Compute (us)From $19/moSmart routing sends each request to the cheapest model that can do it, or pin any model by its exact ID. Standard Compute starts at $19/month with a $20 monthly compute budget. Requests stop when that budget is exhausted until renewal or a plan change; there are no automatic overage charges. Requests are not slowed as the budget is used. It is a fixed bill with a finite allowance.
OpenRouterPay-as-you-goChoose models and providers through one API. Usage-based pricing can suit light or bursty work; estimate long agent sessions and review current fees and limits. Source: openrouter.ai
Anthropic APIPay-as-you-goDirect API access for supported Claude models. Token use, model choice, service limits and spending controls determine the cost and available throughput. Source: claude.com

Prices and allowances can change. TRAE's plan prices were read from trae.ai/pricing, and the custom model fields from TRAE's models and Auto mode docs, on October 14, 2026. TRAE pricing · TRAE: built-in and custom models. Spot an error? Tell us.

Add Standard Compute as a TRAE custom model

TRAE Settings → Models → Add Model → Custom Model
API format          OpenAI Chat Completions
Custom request URL  https://api.stdcmpt.com/v1      (Full URL off)
Model ID            standardcompute                 (or anthropic/claude-sonnet-5.5)
API key             sc_live_…                       (your Standard Compute key)

TRAE checks the key with a live request when you save. With Full URL on, enter https://api.stdcmpt.com/v1/chat/completions instead. Then pick the model in the agent's model selector, not Auto.

TRAE questions

Does TRAE work with an OpenAI-compatible base URL, like OpenRouter or a gateway?
Yes. Since TRAE 3.5.51 (April 2026), a custom model takes your own request URL, in either OpenAI Chat Completions or Anthropic Messages format. With Full URL off you enter the base URL and TRAE appends the path; with it on you enter the complete endpoint. For Standard Compute that is https://api.stdcmpt.com/v1, or https://api.stdcmpt.com/v1/chat/completions as a full URL.
Why is TRAE not using the custom model I added?
Auto mode is the usual reason: TRAE's docs say that with Auto mode on, the system does not use custom models you add. Switch off Auto and select your custom model in the model selector. TRAE's pricing lists the Free plan as Auto mode only and does not say whether Free can select custom models, so check this in your own plan before relying on it.

Try one task before choosing a plan

  1. Check the API format and model configuration supported by your installed TRAE version.
  2. Run a small task on a clean branch and review the result, elapsed time and compute used.
  3. Estimate your actual monthly workload before selecting a larger allowance.
Get your API keyTRAE setup guide →Compare compute budgets →

Record your own results with the workload CSV and report template. These are blank templates, not published benchmark results.

Disclosure: this guide is maintained by Standard Compute, one of the options above. Choose based on task quality, supported features and total cost for your workload. Light usage may cost less on a usage-based API; sustained workloads need enough allowance on any subscription.

All flat-rate plans compared →The cheapest-tokens math →Plan compute for your team →