Standard Compute

Which API should you use with Cursor?

To put Cursor's chat and agent on one monthly price, paste a Standard Compute key into Cursor's OpenAI API key field and override the base URL to https://api.stdcmpt.com/v1, from $19 a month. It matters most on Cursor's Premium plan and up, where Claude, GPT and other third-party models are charged at API list price on top of the subscription. Any custom key has two limits: Tab completion stays on Cursor's own models, and requests still pass through Cursor's servers.

Guide updated 2026-10-13. Check each provider's current terms below.
Light or occasional use
Stay on Cursor's included usage. If a month of third-party model spend on Cursor's usage page comes to a few dollars, a second subscription will not pay for itself.
One fixed monthly bill
Switch the override on when agent runs on Claude or GPT start adding a visible line to your Cursor bill. The override covers every OpenAI-format model in Cursor, so toggle it off when you want Cursor's included models back.

API and subscription options for Cursor

OptionPriceWhat you get
Cursor's own plans$8 / $30 / $100 / $200 per moPlus ($8) covers Grok models only. On Premium ($30) and above, third-party models such as Claude and GPT run at API list price, billed separately by usage. Tab completion always uses Cursor's built-in models. Source: cursor.com
Standard Compute (us)From $19/moStandard 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. Pin any model by its exact ID, or let smart routing pick per request. It is a fixed bill with a finite allowance.
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
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

Prices and allowances can change. Cursor plan prices were read from cursor.com/pricing on October 13, 2026. Cursor's API key help page states that custom keys only work with chat models, that Tab uses Cursor's built-in models, and that requests route through Cursor's servers. Cursor pricing · Cursor: custom API keys. Spot an error? Tell us.

Connect Cursor in Settings → Models

Cursor Settings → Models
OpenAI API Key            sc_live_…            (your Standard Compute key, toggle on)
Override OpenAI Base URL  https://api.stdcmpt.com/v1
Add custom model          standardcompute      (enable it, pick it in a new chat)

Send one small agent task and confirm it appears in your Standard Compute request log. Custom endpoint support varies by Cursor version.

Try one task before choosing a plan

  1. Check the API format and model configuration supported by your installed Cursor 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 keyCursor 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 →