> ## Documentation Index
> Fetch the complete documentation index at: https://nemonist.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Migrating from OpenRouter

> Change the base URL and the key; keep your requests.

nemonist's API is OpenRouter-compatible: the same endpoints, request bodies, model IDs and responses. To move a client or app:

1. Change the base URL from `https://openrouter.ai/api/v1` to `https://nemonist.com/api/v1`.
2. Use a nemonist key (`sk-nm-...`) instead of your OpenRouter key.

Your models, tools, streaming and routing options (`provider`, `models` fallbacks) work as before.

## Turn memory off for an app

Memory is for coding agents. An app that calls the API (a SaaS backend, a classifier, a function-calling bot) should use a key with memory turned off. Requests under that key are sent as your code wrote them, with no memory and no added tokens, even when they carry `tools`, so prompt tokens and cost match OpenRouter's.

* **New key:** on the **API keys** page, choose **New key** and check **No memory, for an app that calls the API**.
* **Existing key:** open the key, and under **Memory** choose **Turn off**. Turn it back on the same way.
* **From code:** send `"memory_off": true` to `POST /keys` or `PATCH /keys/{hash}` with a [management key](https://nemonist.com/docs/concepts/api-keys.md#management-keys).

With memory on, a request that carries `tools` is treated as a coding agent's and is asked to link a project, which adds tokens to its prompt.

## Keep paying OpenRouter directly

To keep billing to your OpenRouter account, add your OpenRouter key on the workspace's **Your key** page. Requests are then billed to that account. See [Bring your own key](https://nemonist.com/docs/concepts/byok.md).

## What is different

* **Memory.** Requests from coding agents get their project's memory and learn from every turn; a request with `tools` counts as a coding agent's. Other requests, and every request under a key with [memory off](#turn-memory-off-for-an-app), are answered as OpenRouter would answer them. See [Memory](https://nemonist.com/docs/concepts/memory.md).
* **Error bodies.** Status codes are OpenRouter's, and the body keeps `error.code` and `error.message`. nemonist does not return OpenRouter's top-level `user_id` or its `error.metadata` details (`provider_name`, `raw`, `provider_error_code`, `is_byok`, `routing_funnel`, `failed_routing_step`, `ineligibility_reasons`, `limit_source`, `remedy_hint`). When it knows the kind of error, `error.metadata` holds only `error_type`. The message says what went wrong in words. See [Errors](https://nemonist.com/docs/concepts/errors.md).
* **Allowed models.** A request for a model the key's allowed models exclude gets `403` ("This key may not use the model ..."), where OpenRouter answers `404`. A [guardrail](https://nemonist.com/docs/concepts/guardrails.md) refusal is also `403`, with `error.metadata` naming the guardrail.
* **Latency and compression.** Each request passes through nemonist, which adds about 0.15 to 0.3 seconds, before the first token too. Occasionally a provider takes 2 to 6 seconds longer to answer a short request. This happens through OpenRouter directly at the same rate (about 1 to 4 in 100 calls in our tests, up to 5.6 seconds), and nemonist does not add it. If a call sits on a path with a tight timeout, such as a classifier on a user's request, set the timeout to 10 seconds, or cut it off at 6 seconds and retry once. Replies are not compressed (no `content-encoding: gzip`).
* **Cursor.** Cursor uses its own endpoint, `https://nemonist.com/api/v1/cursor`. See [Cursor](https://nemonist.com/docs/clients/cursor.md).
* **Memory endpoints.** [`GET /memory-file`](https://nemonist.com/docs/api-reference/overview#memory) and [`DELETE /memory`](https://nemonist.com/docs/api-reference/overview#memory) read and erase memory.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.