Standard Compute

Which API should you use with Warp?

For Warp's agent on one monthly price, the best API is a flat-rate OpenAI-compatible endpoint: add Standard Compute as a custom inference endpoint in Warp's settings (URL https://api.stdcmpt.com/v1), from $19 a month with a $20 compute budget, and pick its model in the model picker. Warp's Build plan is $20 a month with $20 of agent usage at API rates, and Max is $200 with $200. Custom endpoints work on Warp's Free plan for individuals and organizations with 10 or fewer employees, but Warp's Auto models never use them, so you choose the model by hand.

Guide updated 2026-10-14. Check each provider's current terms below.
Light or occasional use
For light agent use, Warp Build's $20 of included usage or Free with pay-as-you-go will likely cost the least. Watch the usage meter through a busy week first.
One fixed monthly bill
When agent runs regularly go past Build's $20, a Standard Compute endpoint on Warp Free or Build keeps the model bill at the plan price. Requests stop at the monthly compute budget instead of billing overage.

API and subscription options for Warp

OptionPriceWhat you get
Warp plans$0 / $20 / $200 per moBuild includes $20 of agent usage a month at API rates and Max $200; Business is $50 per user with $20 of usage per seat. Free and paid individual plans can bring their own inference. Source: warp.dev
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. Warp's plan prices and custom endpoint terms were read from warp.dev/pricing and Warp's custom inference endpoint docs on October 14, 2026. Warp pricing · Warp: custom inference endpoint. Spot an error? Tell us.

Add a custom inference endpoint in Warp

Warp Settings → search "inference endpoint"
Endpoint URL   https://api.stdcmpt.com/v1
API key        sc_live_…            (your Standard Compute key)
Models         standardcompute
               anthropic/claude-sonnet-5.5

Save, then pick the model from Warp's model picker for a local agent run. Warp keeps the key in local secure storage on your device.

Warp questions

Can Warp's bring-your-own-key use a gateway like OpenRouter instead of OpenAI or Anthropic directly?
Not through the API key fields: Warp's BYOK keys cover OpenAI, Anthropic and Google only. Gateways go in the separate custom inference endpoint setting, which takes any service implementing the OpenAI Chat Completions API (POST /v1/chat/completions) at a public URL. Standard Compute is one: enter https://api.stdcmpt.com/v1 and your key.
Do I pay Warp anything when the agent runs on my own endpoint?
Warp's custom endpoint docs only name a platform charge for Business and Enterprise: local runs on your own endpoint there incur agent-hour charges. Check Warp's pricing page for your plan. Organizations with more than 10 employees need one of those plans to use custom endpoints. Cloud agents do not use a personal endpoint.

Try one task before choosing a plan

  1. Check the API format and model configuration supported by your installed Warp 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 keyWarp 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 →