Typort vs LiteLLM

A gateway you host. LiteLLM's AI Gateway is a self hosted server that gives your applications one OpenAI compatible endpoint for more than 100 providers. The open source gateway is MIT licensed.

Keys, budgets and rate limits. Each user, team or project gets a virtual key with its own models, budget and rate limits. After a key crosses its budget, requests fail. A budget can reset after a set time, such as 30 days.

Spend on what it carries. The gateway records the cost of each request in its spend logs, by key, user, team and tag. Per person figures depend on each key being issued to a named user: LiteLLM's docs say to set a user_id when creating keys.

What it does not see. Its spend logs hold the requests that go through the gateway. A person chatting in ChatGPT or Claude on a Business or Team seat is talking to that company directly, so that work never reaches LiteLLM.

Open source: free. LiteLLM lists its open source gateway as "Free forever", MIT licensed, and you run it on your own servers.

Enterprise: no public price; sales quote. LiteLLM's Enterprise tier adds "Enterprise support and custom SLAs" and "JWT auth, SSO, and audit logs". The site says "Request pricing".

	LiteLLM	Typort
What it sees	Requests sent through the gateway with a virtual key	Chats in ChatGPT, Claude, Perplexity and Grok in the browser, on Business and Team seats
Usage per person	Spend logs by key, user and team, when each key is issued to a named user	Tokens, tools and active days per person, with adoption over 13 weeks
Spend	The cost of each request through the gateway	Estimated spend per person at API list price, with an allowance and a near or over warning
Hard budgets	Yes. Requests fail once a key crosses its budget	No. Allowances and warnings only, nothing is blocked
Routing, fallbacks, retries	Yes, load balancing, fallbacks and retries	No. Typort routes nothing
What the work is	Not among the features in LiteLLM's docs	Chats sorted into kinds of work, shown as a pie
Client rules	Not among the features in LiteLLM's docs	Rules per client, with chats marked broke a client rule or close to one
What it needs	A self hosted server, apps pointed at it, a key per user, team or project	The Typort browser extension and a sign in
Who sees what	Role based access, listed with Enterprise	Five switches, shown in plain words to everyone on the team

LiteLLM for your apps. Typort for the seats. Anything your developers build, and any agent that calls a model with an API key, goes through the gateway. That is where routing, hard budgets and per key spend belong. The ChatGPT and Claude seats people type into every day are a different stream, and Typort shows who uses them, what for, roughly what it costs, and what went in.

They run side by side. Typort needs no change to your LiteLLM setup, and LiteLLM needs nothing from Typort.

The team view runs on Typort's servers. It is free for a limited time and will move to Typort Pro later.

Is Typort a replacement for LiteLLM?

No. LiteLLM is a gateway: your apps send their requests through it with a key, and it routes them, records their cost and enforces budgets. Typort routes nothing. It shows how people use the AI tools they type into in the browser. Many teams will want both.

Will LiteLLM show what my staff do in ChatGPT or Claude?

No. LiteLLM logs the requests that go through the gateway. When someone chats in ChatGPT or Claude on a Business or Team seat in their browser, the chat goes straight to that company, not through your gateway. That is the part Typort covers.

Can Typort stop someone at a budget?

No. Typort gives each person an allowance and warns admins at 80% and 100%. It does not block anything. LiteLLM can set a hard budget on a key, user or team, and requests fail once a key crosses it, for traffic that goes through the gateway.

Which AI tools does Typort see?

ChatGPT, Claude, Perplexity and Grok in the browser, through the Typort browser extension. It reads the page, so it works on Business and Team seats and needs no API keys from the AI vendors. Microsoft 365 Copilot comes in the next extension update, and Gemini is being added.

What does LiteLLM cost?

LiteLLM's open source gateway is free and MIT licensed, and you host it yourself. Its Enterprise tier has no public price: LiteLLM says request pricing.

Are the dollar figures exact?

No, they are estimates from the tokens in each chat at the AI vendor's API list price. They are there to compare people and tools, not to replace the invoice.

Can staff see what the company sees?

Yes. The five switches are shown to everyone in plain words on their first screen, and every time an admin or team leader opens someone's chat, it is recorded. Chats in the AI's own temporary or incognito mode are never collected.

What does the team view cost?

The team view runs on Typort's servers. It is free for a limited time and will move to Typort Pro later.