Terms of Service

1. Service Overview

FreeInference is an experimental research service that provides access to hosted and routed large language model inference for experimentation and related development work.

The service may route requests across local inference servers and remote model providers. Available models, providers, limits, features, latency, throughput, output quality, and routing behavior may change without notice, and there is no performance guarantee.

2. Eligibility and Accounts

You are responsible for maintaining the confidentiality of your account credentials and API keys. You are responsible for activity submitted through your account or keys.

Do not share API keys publicly, embed them in client-side code, or use another person's account without permission.

3. Acceptable Use

You may not use the service to violate laws, infringe rights, compromise security, abuse infrastructure, or intentionally disrupt availability for other users.

You may not attempt to bypass rate limits, quotas, authentication, authorization, routing controls, or provider restrictions.

4. Quotas and Limits

Quotas, rate limits, model access, and usage limits may change based on usage, demand, infrastructure capacity, abuse prevention, operational needs, and individual or aggregate activity.

High-volume, automated, abusive, or operationally risky usage may be limited, delayed, deprioritized, or blocked without advance notice.

5. Logging and Data Use

All prompts and responses may be logged for research purposes, stored, hashed, redacted, or otherwise processed depending on operator configuration and service needs. Logs and derived data may be used to operate, secure, debug, improve, and analyze the service.

We sanitize all text before analysis where feasible to reduce sensitive or identifying content in analysis workflows. Sanitization is not a guarantee that all sensitive information will be removed from logs, derived data, or third-party provider systems.

Do not submit sensitive personal information, confidential information, regulated data, secrets, credentials, or data you are not authorized to process through the service.

6. Third-Party Providers

Some requests may be forwarded to third-party model providers. Those providers may process submitted prompts, responses, metadata, and related usage information under their own terms and policies.

You are responsible for ensuring that your use of the service and any routed providers is appropriate for your data and intended use case.

7. No Warranty

The service is provided without guarantee and on an as-is and as-available basis. Outputs may be inaccurate, incomplete, unsafe, unavailable, delayed, or unsuitable for your needs.

You must review model outputs before relying on them. Do not rely on the service for legal, medical, financial, safety-critical, or other high-risk decisions. This page is not legal advice.

8. Suspension and Termination

Access may be limited, suspended, or terminated for misuse, security concerns, operational needs, policy violations, or discontinuation of the service.

We may remove or restrict models, providers, accounts, API keys, or features at any time.

9. Changes to These Terms

These terms may be updated from time to time. Continued use of the service after updates means you accept the revised terms.

10. Contact

For questions about FreeInference or these terms, contact us at [email protected].