InferStack

Terms of Service

Effective 1 November 2026

1. The service

InferStack provides API access to open-weight AI models ("the Service"), primarily through OpenRouter. If you use the Service through OpenRouter, OpenRouter's terms also apply, and billing is handled by OpenRouter.

2. Acceptable use

You may not use the Service to:

You must also follow the licence and usage policy of each model you use. We may suspend access that breaks these terms.

3. Model outputs

Outputs are generated by AI models and may be inaccurate, incomplete or inappropriate. You are responsible for reviewing outputs and for how you use them. Model licences (for example Apache-2.0) are those of the model authors.

4. Availability

We aim for high availability but provide the Service without uptime guarantees. We may change, add or retire models. Where possible, we give notice through OpenRouter's deprecation mechanism.

5. Data

Our handling of request data is described in the Privacy Policy. We do not store prompt or completion content, and we do not train on customer data.

6. Disclaimer and liability

The Service is provided "as is", without warranties of any kind. To the maximum extent permitted by law, our total liability for any claim is limited to the amounts paid for the Service in the three months before the claim.

7. Governing law

These terms are governed by the laws of the Province of New Brunswick and the federal laws of Canada applicable there.

8. Contact

hello@inferstack.ca