OpenAI-Compatible API · Custom Base URL

Unlimited compute. Every AI agent.

Standard Compute is an OpenAI-compatible API with unlimited frontier-model compute at one flat price — from $9/mo, no per-token billing, no 429s. It works as a custom model provider in any agent or tool — Codex CLI, OpenCode, Cursor, Claude Code, Aider and more. Point the base URL at us, drop in your key, set the model to standardcompute, and run — no code changes, no per-token billing.

Get your API key →

How it works

Three settings connect Standard Compute to anything OpenAI-compatible.

1
Get your key
Grab a Standard Compute API key from the dashboard — free tier, no card.
2
Swap base URL + key
In your agent, set the base URL to api.stdcmpt.com/v1 and paste your key.
3
Run
Set the model to standardcompute and go. Unlimited compute, flat price.

Step-by-step for your tool

Exact setup — the custom OpenAI-compatible base URL and where it goes — for the tools developers connect most.

Cursor
AI code editor
Cline
VS Code agent
Roo Code
VS Code agent
Aider
Terminal coding agent
Continue
IDE extension
Codex CLI
Terminal coding agent
OpenCode
Terminal coding agent
Kilo Code
VS Code extension
Z
Zed
Code editor
T
Trae
AI IDE
Hermes
Personal agent
OpenClaw
Personal agent
Pi
Terminal coding agent
omp
Terminal coding agent
Using Claude Code? It's built for Anthropic's API and can't take an OpenAI-compatible base URL directly — see what actually works →

Works with your AI agent

Pick your agent for its exact setup. Standard Compute powers coding agents, personal automation agents, and conversational assistants alike.

Claude Code logo

Claude Code

Coding Agent
Setup ↓

Anthropic's terminal coding agent — plans, edits, runs tests, and ships multi-file changes with frontier-model quality.

Point Claude Code at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
Hermes Agent logo

Hermes Agent

Personal Agent
Setup ↓

Nous Research's open-source self-improving agent — persistent memory, a learning loop that creates reusable skills, and access from 20+ messaging platforms.

Point Hermes at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
OpenAI Codex CLI logo

OpenAI Codex CLI

Coding Agent
Setup ↓

OpenAI's open-source terminal coding agent — sandboxed local execution with approval modes, powered by GPT-5-class models.

Point Codex at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
Gemini CLI logo

Gemini CLI

Coding Agent
Setup ↓

Google's open-source terminal AI agent with a 1M-token context window and the most generous free tier of any frontier agent.

Point Gemini CLI at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
OpenClaw logo

OpenClaw

Personal Agent
Setup ↓

The viral open-source autonomous agent that runs on your own machine and acts through your messaging apps — 100+ skills spanning browser, email, files, and APIs.

OpenClaw sets up with a single paste-in prompt — no manual config. Grab it in the OpenClaw guide.
Kilo Code logo

Kilo Code

IDE Extension
Setup ↓

VS Code extension that provides AI-powered coding assistance with multi-file editing and refactoring.

Point Kilo Code at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
Cursor logo

Cursor

IDE / Editor
Setup ↓

AI-first code editor built on VS Code with deep codebase understanding and natural language editing.

Point Cursor at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
GitHub Copilot logo

GitHub Copilot

IDE Extension
Setup ↓

GitHub's AI coding assistant with inline suggestions, chat, and deep GitHub ecosystem integration.

Point Copilot at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
Cline logo

Cline

IDE Extension
Setup ↓

The open-source agent that defined the VS Code agent category — Plan/Act approval modes, MCP support, and full bring-your-own-key freedom.

Point Cline at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
Windsurf logo

Windsurf

IDE / Editor
Setup ↓

AI-powered code editor (formerly Codeium) with Cascade flow for multi-file, multi-step coding tasks.

Point Windsurf at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
Aider logo

Aider

Coding Agent
Setup ↓

Terminal-based AI pair programmer that edits code in your local git repo with any LLM.

Point Aider at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
Continue logo

Continue

IDE Extension
Setup ↓

Open-source AI coding assistant for VS Code and JetBrains with customizable models and context.

Point Continue at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
OpenCode logo

OpenCode

Coding Agent
Setup ↓

Terminal-based AI coding agent with a clean TUI, multi-provider support, and LSP integration.

Point OpenCode at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
Pi logo

Pi

Terminal Coding Agent
Setup ↓

Mario Zechner's radically minimal open-source terminal coding agent — a handful of core tools, a fast TUI, and TypeScript extensions for everything else.

Point Pi at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
Oh My Pi logo

Oh My Pi

Terminal Coding Agent
Setup ↓

A coding-first fork of Pi with an IDE wired into the terminal — hash-anchored edits, LSP navigation, real debugger control, and subagents on a Rust core.

Point omp at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
Roo Code logo

Roo Code

Coding Agent
Setup ↓

The power-user fork of Cline — a VS Code agent with switchable modes (Architect, Code, Debug, custom), deep configurability, and BYO API key.

Point Roo Code at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
Devin logo

Devin

Coding Agent
Setup ↓

Cognition's autonomous software engineer — takes a ticket, plans, codes, tests, and opens a PR in its own cloud environment, managed from Slack or the web.

Point Devin at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
Amp logo

Amp

Coding Agent
Setup ↓

Sourcegraph's agentic coding tool — thread-based, aggressively autonomous, always running frontier models at full reasoning in your editor or CLI.

Point Amp at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
Jules logo

Jules

Coding Agent
Setup ↓

Google's asynchronous coding agent — connect a GitHub repo, hand it tasks, and get tested pull requests back from cloud VMs while you do something else.

Point Jules at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
Google Antigravity logo

Google Antigravity

Coding Agent
Setup ↓

Google's agentic IDE built around Gemini 3 — an agent manager that plans, codes, and verifies its own work in the editor, terminal, and a controlled browser.

Point Antigravity at Standard Compute with three settings:
Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute

Any OpenAI-compatible tool

Building your own agent, or using an SDK? If it speaks the OpenAI format, it works. Use these three settings anywhere.

Base URL
https://api.stdcmpt.com/v1
API Key
Your Standard Compute key
Model
standardcompute
Works with the OpenAI Python & Node SDKs (pass base_url / baseURL), LangChain, and direct curl / fetch calls. SDK examples →

More than a base-URL swap

The connection is the easy part. What you get on the other side is unlimited frontier-model compute at one flat price — built for agents that run all day.

Unlimited compute, flat price
No per-token billing, no usage caps, no surprise invoices. One predictable monthly price however hard your agent runs.
Frontier models, auto-routed
Set the model to standardcompute and the router picks the best frontier model for each request — you never pick or update model names.
Drop-in OpenAI format
Identical request and response shape. Nothing to rewrite — swap the base URL and key, and every OpenAI-compatible agent or SDK just works.
Built for always-on agents
Intelligent batching, routing, and prompt compaction keep agents fast and stable under sustained, around-the-clock load.

Integration FAQ

Does Standard Compute work with my AI agent?

Almost certainly. Standard Compute exposes an OpenAI-compatible API, so any agent or tool with a custom OpenAI-compatible provider setting works — Cursor, Cline, Aider, OpenCode, Codex CLI, Continue, Kilo Code, OpenClaw, Hermes Agent, and more. You only change the base URL and API key. The exceptions are tools locked to a single vendor's API with no custom-provider setting, like Claude Code.

Does Claude Code work with Standard Compute?

Not directly. Claude Code is built for Anthropic's Messages API and has no native OpenAI-compatible base-URL setting. Community router projects can translate between the two formats, or you can get the same flat-rate setup natively in an OpenAI-compatible terminal agent like OpenCode, Codex CLI, or Aider. Our Claude Code compatibility guide covers what actually works.

How do I connect Standard Compute to an agent?

Set the base URL to https://api.stdcmpt.com/v1, paste your Standard Compute API key, and set the model to "standardcompute". Our router picks the best underlying model for each request. No code changes beyond those three settings.

Do I need to change my code?

No. The request and response format is identical to OpenAI's. If your agent or SDK already speaks the OpenAI format, you only swap the base URL and key.

Why route through Standard Compute instead of calling OpenAI directly?

Per-token billing makes always-on agents unpredictable and expensive. Standard Compute gives you unlimited compute at one flat monthly price, automatically routes each request to the best frontier model, and keeps the exact OpenAI request and response format — so you swap the base URL, not your code.

What model should I select?

Always "standardcompute". It is a single model identifier that routes to the best available frontier model for each request, so you never have to pick or update model names.