Inference API Privacy Policy

1. About this policy

This policy covers the Negbeta inference API at inference.negbeta.com (the “API”), which serves AI language models to OpenRouter and, through OpenRouter, to OpenRouter’s users. It is operated by Negbeta Limited (“Negbeta”, “we”, “us”), a company registered in England and Wales (company number 14318349), registered office 71-75 Shelton Street, Covent Garden, London WC2H 9JQ, United Kingdom.

The privacy policy for our corporate website is separate. Exactly which request data we keep, field by field, is listed in our API data policy.

For the content of requests we act on behalf of OpenRouter, which decides what is sent to us. For the operational metadata described below, Negbeta Limited is the data controller.

2. The short version

• We do not train on your data. Prompts, images and completions are never used to train or fine-tune any model, by us or anyone else.
• We do not store prompts or completions. Prompts, images and model output are held in memory only while your request is processed, and are never written to our logs or database.
• We keep per-request metadata for 180 days. Token counts, timings, sampling parameters and similar operational data, then it is deleted automatically.
• Inference runs in the United Kingdom, on servers rented from Nebius.

3. How requests reach us

We do not offer accounts to the public. Requests reach the API from OpenRouter, authenticated with an API key that we issue to OpenRouter, over an encrypted connection through Cloudflare. We do not receive your name, email address or OpenRouter account details. The network address we see is normally OpenRouter’s, not yours.

4. What we process and why

Request content

Your messages, system prompts, images, tool definitions and tool results, and the model’s output (including reasoning text and tool calls), are processed only to produce the response to your request. While the request runs they exist in the memory of our servers. To make repeated prompts faster, the server keeps a cache of recently processed prompt beginnings, in the model’s internal form, in GPU memory. That cache is never written to disk, is overwritten as new requests arrive, and is cleared whenever the server restarts. If a request links to an image by URL, our server downloads the image to process the request and does not keep it.

Operational metadata

For every request we record operational metadata: identifiers, timings, token counts, sampling parameters, message and tool-call counts, a short sanitised error message when something fails, and one-way hashes in place of the API key and network address. The full list is in the API data policy. We use it to:

• reconcile usage and billing with OpenRouter;
• run the service: capacity planning, routing, monitoring and fixing faults;
• measure and improve quality, for example the share of tool calls that are valid;
• investigate abuse of, or attacks on, the service.

Our lawful basis for this metadata is our legitimate interest in operating, securing and billing the service. We do not use it for advertising or profiling, and we do not sell it.

5. Where data is processed

Inference and the metadata database run on servers we rent from Nebius in its United Kingdom data centres (Nebius region uk-south2). Requests travel to those servers through Cloudflare’s network, which may carry them through Cloudflare locations outside the United Kingdom on the way. How OpenRouter handles your data before it reaches us is covered by OpenRouter’s own privacy policy.

6. Service providers

We use two service providers that handle request data on our behalf:

• Nebius: the cloud servers and GPUs that run the models and store the metadata, in the United Kingdom.
• Cloudflare, Inc.: the encrypted tunnel and network edge in front of the API. Cloudflare terminates the encrypted connection, so request content passes through its network in transit; it does not store it for us.

We share no other data with third parties, except where the law requires it (for example a court order).

7. How long we keep it

• Request content: not kept after the response is complete (the in-memory cache described above aside).
• Per-request metadata: 180 days in our database, then deleted automatically. Temporary local copies made when the database is unavailable are described in the API data policy.
• Server performance metrics (GPU load, queue lengths and similar, with no request content): 90 days.

8. Security

The API is reachable only through the encrypted Cloudflare tunnel and requires an API key. The metadata database is not exposed to the internet and is reachable only from our own servers. Access is limited to Negbeta staff who run the service.

9. Your rights

Under the UK GDPR and the Data Protection Act 2018 you have rights to access, correct, delete, restrict or object to the processing of your personal data, and to complain to the Information Commissioner’s Office (ico.org.uk). We store no names, email addresses or raw network addresses, so we usually cannot tell which metadata relates to you. If you contact us with a request ID returned by the API, we will find and handle the matching record. Requests about your OpenRouter account should go to OpenRouter.

10. Children

The API is a developer service and is not directed at children.

11. Changes

If we change how we handle request data, we will update this page and the “Effective” date before the change takes effect.

12. Contact

Email [email protected], or write to Negbeta Limited, 71-75 Shelton Street, Covent Garden, London WC2H 9JQ, United Kingdom.