Does nanobot work with Standard Compute?

Yes. nanobot 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 nanobot?

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

Use Standard Compute with nanobot

HKUDS's lightweight, self-hosted personal agent in Python, with a WebUI, memory, MCP, scheduled tasks and chat-app channels. Paste three settings into nanobot: the base URL, your Standard Compute API key and the model.

nanobot's custom provider does not infer a base URL, so apiBase must include the version path (https://api.stdcmpt.com/v1). Any string value in config.json can be a ${VAR} reference resolved from the environment at startup.

Connect nanobot

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 nanobot expects them (steps below).

Base URL

https://api.stdcmpt.com/v1

API Key

Your Standard Compute key

Model

standardcompute

Where to set them in nanobot

In the WebUI open Settings → Models → New preset and choose Add provider; or edit ~/.nanobot/config.json.
Add a provider named standardcompute with apiKey "${STANDARDCOMPUTE_API_KEY}" and apiBase https://api.stdcmpt.com/v1.
Create a model preset with provider standardcompute and model standardcompute, set agents.defaults.modelPreset to it, and restart nanobot from the environment that sets the key.

nanobot docs ↗

What changes in nanobot

Billing: nanobot 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: nanobot is free and MIT-licensed. An always-on agent sends requests on schedules and channel messages too; on Standard Compute those stop with HTTP 402 at the monthly budget instead of billing overage.