Does OpenCode work with Standard Compute?

Yes. OpenCode 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 OpenCode?

Use https://api.stdcmpt.com/v1 as the OpenAI-compatible base URL in OpenCode, 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 · Terminal coding agent

Use Standard Compute with OpenCode

An open-source terminal coding agent with an OpenAI-compatible provider mode. Paste three settings into OpenCode: the base URL, your Standard Compute API key and the model.

OpenCode lists Standard Compute natively through models.dev, with the base URL https://api.stdcmpt.com/v1.

Connect OpenCode

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 OpenCode expects them (steps below).

Base URL

https://api.stdcmpt.com/v1

API Key

Your Standard Compute key

Model

standardcompute

Where to set them in OpenCode

Run opencode in your project, then /connect.
Choose Standard Compute and paste your Standard Compute API key.
Select Standard Compute in the model picker. If the provider is missing, update OpenCode or follow its custom-provider documentation.

Full in-dashboard guide → · OpenCode docs ↗

What changes in OpenCode

Billing: OpenCode requests draw on one monthly compute budget, with plans from $19 a month. 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.