Connect anything

Connect Anything.

Tokenator is a drop-in replacement for the OpenAI and Anthropic APIs. Point your app, IDE, or SDK at it and instantly spend less, with full governance and analytics — with no code changes.

Base URL
https://api.tokenator.ai
Paste this one URL into any tool — OpenAI-compatible apps and Claude Code alike. That's it.
1
Copy the base URL
Set it in your tool's API base-URL field.
2
Use your tk_ key
Generate it above, then paste it as the API key.
3
Run — unchanged
Same SDK calls, now cheaper and fully metered.
Works with

Your stack, unchanged

If it can set an API base URL, it works. No SDK to adopt, no rewrite.

IDEs & editors
CursorClaude CodeContinueClineRooVS Code
SDKs & frameworks
OpenAI SDKAnthropic SDKPythonNode.jsLangChainLlamaIndex
CLI
Claude CLIaidercurl
How it works

One layer between your app and every model

Your applicationapp · IDE · SDK · CLI
Tokenatorcheaper & accountable
OpenAIClaudeGeminiGroqDeepSeekOpenRouterOllamaLM Studio

Change one URL. Keep your code. Everything else stays the same.

Why Tokenator

Smarter than a proxy

Every call is cheaper, governed, and fully accounted for — automatically.

Never pay twice

Ask the same thing again and the answer comes back instantly — at no cost.

Free on repeats

Similar questions come back instantly, so you’re never billed for the same work twice.

Efficient by default

Requests are kept lean — and your code is always left untouched.

Affordable long chats

Long conversations stay cheap automatically, however far they run.

The right price for the job

You pay premium prices only when the work actually needs them.

Spend controls

Budgets, rate limits, and per-key governance — overspend stops before it happens.

Analytics

Know exactly where every token goes, per key, per project, per model.

Savings breakdown

Every response shows what it cost and exactly what was saved.

Integration guides

Copy-paste setup for your tool

Coding in Cursor or VS Code? Get the biggest savings.

Cut your coding bill without changing how you work:

  1. 1. Bring your own key for your vendor (Anthropic, OpenAI, or Google) under Connect below.
  2. 2. Point your editor at the model you already use.
  3. 3. Turn on Smart savings (Pro) in Models.

Tokenator does the rest — your dashboard shows exactly what you saved, with the same quality you expect.

Cursor

Settings → Models → enable OpenAI API Key, paste your tk_ key, tick Override OpenAI Base URL and set it to the URL below. Add a model name (e.g. gpt-4o).

Base URL:  https://api.tokenator.ai
API Key:   tk_your_key_here
Claude Code — Mac app, VS Code, or terminalAnthropic

Two settings point Claude Code at Tokenator. Easiest everywhere (including the Mac app): add this env block to ~/.claude/settings.json — create the file if it doesn't exist, or merge the env key if it does — then restart Claude Code. Prefer a terminal? export the same two variables and run claude.

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.tokenator.ai",
    "ANTHROPIC_API_KEY": "tk_your_key_here"
  }
}
Continue.dev

Add a model to ~/.continue/config.json with provider openai and an apiBase.

{
  "models": [{
    "title": "Tokenator",
    "provider": "openai",
    "model": "gpt-4o",
    "apiKey": "tk_your_key_here",
    "apiBase": "https://api.tokenator.ai"
  }]
}
Cline / Roo (VS Code)

Extension settings → API Provider OpenAI Compatible → Base URL + API Key + a Model ID.

Base URL:  https://api.tokenator.ai
API Key:   tk_your_key_here
Model ID:  gpt-4o
Python SDK (openai)

Any code using the openai library — change two arguments.

from openai import OpenAI
client = OpenAI(base_url="https://api.tokenator.ai", api_key="tk_your_key_here")
client.chat.completions.create(model="gpt-4o",
    messages=[{"role":"user","content":"hi"}])
Node SDK / LangChain / LlamaIndex

Same idea — set baseURL (JS) / base_url and your key. Everything else is unchanged.

import OpenAI from "openai";
const client = new OpenAI({
  baseURL: "https://api.tokenator.ai",
  apiKey: "tk_your_key_here",
});
aider

Point aider at the OpenAI-compatible endpoint via env vars (or the matching flags).

export OPENAI_API_BASE="https://api.tokenator.ai"
export OPENAI_API_KEY="tk_your_key_here"
aider --model gpt-4o
curl

Sanity-check the endpoint from a terminal.

curl https://api.tokenator.ai/chat/completions \
  -H "Authorization: Bearer tk_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o","messages":[{"role":"user","content":"hi"}]}'
Bring your own key

Your key. Your provider. Zero markup.

Youyour account
Your API keystored encrypted
Tokenatorlowers your bill
Providerbilled by them

You pay your provider directly for tokens. Tokenator never marks up your BYOK usage — keys are encrypted at rest and never logged; we only charge a share of what Tokenator measurably saves you.

Providers

One API for every model

Direct providers, an aggregator, and any OpenAI-compatible or self-hosted endpoint.

O● Live
OpenAI
GPT-4o, o-series
A● Live
Anthropic
Claude
G● Live
Gemini
Google
M● Live
Moonshot
Kimi K2
O● Live
OpenRouter
aggregator
Gbase URL
Groq
OpenAI-compatible
Dbase URL
DeepSeek
OpenAI-compatible
Abase URL
Azure OpenAI
OpenAI-compatible
Obase URL
Ollama
self-hosted
Lbase URL
LM Studio
self-hosted

Using ChatGPT, Claude Desktop, or Gemini?

Consumer desktop apps connect straight to their own backend and can't point at a custom inference endpoint — there's no setting for it. Tokenator covers them a different way, no configuration needed:

Available
Built-in Chat

Streams token-by-token and shows what Tokenator did beside each answer.

Available
Browser extension

A chat side-panel on any page, page-aware — download it and add to Chrome or Edge (Mac or Windows).

Coming soon
Remote MCP

Expose Tokenator to MCP-aware desktop apps as a model source.

Install the extension in ~1 minute (Chrome or Edge · Mac or Windows)
  1. Download the zip above and unzip it — you'll get a tokenator-chat folder.
  2. Open chrome://extensions (or edge://extensions) in your browser.
  3. Turn on Developer mode — the toggle at the top-right.
  4. Click Load unpacked and select the unzipped tokenator-chat folder.
  5. Click the Tokenator icon in the toolbar → the side panel opens → open ⚙ settings and paste your tk_ key.

One-click install from the Chrome Web Store is coming soon — this download works today on any Chromium browser.

Roadmap

Coming soon

Where we're expanding next — nothing hidden.

MCP GatewayComing soon
Remote MCPComing soon
RaycastComing soon
Tokenator DesktopComing soon
WindsurfComing soon
ZedComing soon
JetBrainsComing soon
Gemini CLIComing soon
OpenAI CLIComing soon
Where Tokenator is going

One home for all your AI

One workspaceOne memoryOne dashboardEvery providerEvery toolEvery agent

One URL away.

Point your tools at Tokenator and keep everything else exactly as it is.