Does NanoClaw work with Standard Compute?

Yes. NanoClaw accepts a custom Anthropic-compatible endpoint, and Standard Compute serves Anthropic's Messages API. Set the base URL to https://api.stdcmpt.com (without /v1), use your API key as the auth token, and set the model to "anthropic/claude-standardcompute".

What base URL do I use for NanoClaw?

Use https://api.stdcmpt.com as the Anthropic base URL in NanoClaw, without /v1: the client adds /v1/messages itself. Use your Standard Compute API key and the model "anthropic/claude-standardcompute".

Do I need to change my code or model names?

No code changes. The model "anthropic/claude-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

Anthropic Messages · Custom base URL · Personal agent

Use Standard Compute with NanoClaw

A small, container-isolated personal agent built on the Claude Agent SDK, reachable from Slack, Telegram, Discord, WhatsApp and more, with any Anthropic-compatible endpoint. Paste three settings into NanoClaw: the base URL, your Standard Compute API key and the model.

NanoClaw's agent containers never hold the real key: they see only ANTHROPIC_BASE_URL and a gateway-managed placeholder token, which the credential gateway replaces on the wire.

Connect NanoClaw

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 NanoClaw expects them (steps below).

Base URL

https://api.stdcmpt.com

API Key

Your Standard Compute key

Model

anthropic/claude-standardcompute

Where to set them in NanoClaw

Before running bash nanoclaw.sh, export NANOCLAW_ANTHROPIC_BASE_URL set to https://api.stdcmpt.com (no /v1) and NANOCLAW_ANTHROPIC_AUTH_TOKEN set to your Standard Compute key.
Run setup: it writes ANTHROPIC_BASE_URL to .env and stores the key in the credential vault for api.stdcmpt.com.
Set the model with ncl groups config update --id <agent-id> --model anthropic/claude-standardcompute (or NANOCLAW_DEFAULT_MODEL for every group) and restart the group.

NanoClaw docs ↗

What changes in NanoClaw

Billing: NanoClaw 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 anthropic/claude-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: NanoClaw is free and MIT-licensed. Its default Claude provider speaks only Anthropic's Messages API, which Standard Compute serves at https://api.stdcmpt.com; NanoClaw's setup also accepts a Claude subscription or an Anthropic API key.