Does Warp work with Standard Compute?

Yes. Warp supports a custom OpenAI-compatible base URL, so it works with Standard Compute. Set the base URL to https://api.stdcmpt.com/v1, paste your API key, and set the model to "standardcompute".

What base URL do I use for Warp?

Use https://api.stdcmpt.com/v1 as the OpenAI-compatible base URL in Warp, with your Standard Compute API key and the model "standardcompute".

Do I need to change my code or model names?

No code changes. The model "standardcompute" routes each request to a frontier or an efficient model, so you don't pick or update model names; an exact model ID from the Models page pins one model instead.

← All integrations

OpenAI-compatible · Custom base URL · Agentic terminal

Use Standard Compute with Warp

The agentic development environment built around a modern terminal, whose agent can run on your own OpenAI-compatible inference endpoint. Paste three settings into Warp: the base URL, your Standard Compute API key and the model.

Warp's custom endpoints need the OpenAI Chat Completions API (POST /v1/chat/completions), which Standard Compute serves. They are available on Free and eligible paid plans for individuals and organizations with 10 or fewer employees; larger organizations need Business or Enterprise.

Connect Warp

Eligible new accounts can try $0.25 of compute, with no card. See trial terms →

Your connection settings

Copy these values, then put them where Warp expects them (steps below).

Base URL

https://api.stdcmpt.com/v1

API Key

Your Standard Compute key

Model

standardcompute

Where to set them in Warp

Open Warp Settings and search for inference endpoint.
Add an endpoint with the URL https://api.stdcmpt.com/v1 and your Standard Compute API key.
Add standardcompute as a model, or an exact ID such as anthropic/claude-sonnet-5.5 to pin one model, and save.
Pick that model by hand in Warp's model picker for a local agent run. Warp's Auto models always use Warp-provided inference, even with an endpoint configured.

Warp docs ↗

What changes in Warp

Billing: Warp requests draw on one monthly compute budget, with plans from $19 a month. There is no per-token bill. When the budget is used, requests stop until renewal or an upgrade, unless you turn on pay as you go.
Models: The model standardcompute picks a frontier or an efficient model for each request. An exact model ID from the Models page pins one model instead.
Good to know: Endpoint-routed runs draw on your Standard Compute budget instead of your Warp usage balance, though on Business and Enterprise local runs still incur Warp platform charges. Personal endpoint settings stay on your device, with the key in secure storage, and cloud agent runs do not use them.