> For the complete documentation index, see [llms.txt](https://docs.tolvyn.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tolvyn.io/getting-started/readme.md).

# What is TOLVYN?

TOLVYN is the financial control plane for AI infrastructure. Every AI API call — metered, attributed, governed.

***

## What you get

* **Real-time cost metering.** Every request that goes through TOLVYN is recorded with model, token counts, latency, and exact cost in microdollars. Pricing is live, not estimated.
* **Budget enforcement.** Set hard, soft, or approval budgets per team, service, agent, user, or end-customer. Hard budgets block requests at the proxy before the provider is called.
* **Immutable audit ledger.** Every request appends to a SHA-256 hash-chained ledger with HMAC signatures. Verifiable at any time via `GET /v1/ledger/verify`. Designed for financial evidence, not just monitoring.
* **Drop-in SDKs and proxy.** Replace one import line in Python, Node.js, or Go. Or point any HTTP client at `proxy.tolvyn.io`. OpenAI, Anthropic, Google, and DeepSeek supported.

***

## 60-second quickstart

1. Sign up at [app.tolvyn.io/signup](https://app.tolvyn.io/signup)
2. **Account → Provider Connections** — add your OpenAI / Anthropic / Google / DeepSeek key (stored encrypted server-side)
3. **API Keys → Create** — copy the `tlv_live_...` key (shown once)
4. Use it:

   ```python
   from tolvyn import OpenAI
   client = OpenAI(tolvyn_api_key="tlv_live_...")
   client.chat.completions.create(model="gpt-4o", messages=[...])
   ```
5. Open the dashboard — the request appears within seconds with cost, tokens, and latency.

Full walkthrough: [Quickstart](/getting-started/quickstart.md).

***

## Where to next

| If you want to...                             | Go to                                                                      |
| --------------------------------------------- | -------------------------------------------------------------------------- |
| Get to a working request in 5 minutes         | [Quickstart](/getting-started/quickstart.md)                               |
| Choose between SDK and proxy mode             | [Integration Modes](/getting-started/integration-modes.md)                 |
| See SDK reference for your language           | [Python](/sdks/python.md) · [Node.js](/sdks/nodejs.md) · [Go](/sdks/go.md) |
| Move from Helicone, Portkey, or direct OpenAI | [Migration guides](/migrate-to-tolvyn/index.md)                            |

***

## Need help?

Email <founder@tolvyn.io>.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.tolvyn.io/getting-started/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.