Does Amp work with Standard Compute?

Yes. Amp 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 Amp?

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

Use Standard Compute with Amp

The coding agent that spun out of Sourcegraph: an effort dial instead of a model picker, subagents, and threads across CLI, web and desktop. Paste three settings into Amp: the base URL, your Standard Compute API key and the model.

Amp's Model Routing takes any OpenAI- or Anthropic-compatible endpoint as a Custom URL connection, on every tier including the free Hobby plan, and Amp's pricing page lists no Amp token fees on your own keys.

Connect Amp

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 Amp expects them (steps below).

Base URL

https://api.stdcmpt.com/v1

API Key

Your Standard Compute key

Model

standardcompute

Where to set them in Amp

Open Settings → Model Routing in Amp and choose Add → Custom URL. The CLI equivalent is amp config model-providers.
Choose the chat-completions format, enter the base URL https://api.stdcmpt.com/v1 and paste your Standard Compute key. Amp sends it as a Bearer token and appends /chat/completions itself.
Under Model mapping, add the models you want Standard Compute to serve, one per line, with the Models picker. Amp writes Claude IDs with dashes (anthropic/claude-opus-4-6), so add -> and the Standard Compute ID where they differ, for example -> anthropic/claude-opus-5.5.
Press Check Access. Then open Settings → Mode Dial → Tune Modes, pin the roles you want on those models and save. The routing graph in Model Routing shows which connection serves each model.

Amp docs ↗

What changes in Amp

Billing: Amp 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: Only the models in your mapping move to Standard Compute. Unmapped roles, plus web search, image generation, voice and orb minutes, stay on Amp credits. A thread keeps its mode and models from the first message, so pin models before you start. For Amp's main agent, pin exact model IDs rather than standardcompute, which can pick a different model per request.