1. The Services
OpenInfer provides an inference orchestration platform that executes AI workloads across heterogeneous compute infrastructure. The Services include hosted inference APIs and, where separately contracted, self-hosted deployments of the OpenInfer Engine.
Service levels, support commitments, and deployment-specific features are governed by the applicable Order Form or Service Level Agreement.
Beta, preview, evaluation, or early-access features may be modified, suspended, or discontinued at any time and may not be suitable for production workloads unless expressly stated otherwise.
2. Accounts and API Keys
You are responsible for maintaining the confidentiality of your account credentials and API keys and for all activity conducted under your account. You must promptly notify OpenInfer of any unauthorized access or suspected compromise.
3. Acceptable Use
You may not use the Services to:
- violate applicable laws or regulations;
- infringe the intellectual property or other rights of others;
- generate content intended to facilitate violence, exploitation, or illegal activity;
- develop or distribute malware;
- conduct phishing, credential theft, or social engineering;
- bypass safety, security, rate limiting, or usage controls;
- probe or test the Services without prior written authorization;
- extract or attempt to reconstruct model weights or proprietary platform components;
- resell or sublicense the Services except under a written agreement;
- use the Services for unlawful surveillance or prohibited biometric identification; or
- develop or operate weapons or autonomous systems intended to cause physical harm.
You remain responsible for reviewing and validating all model outputs before relying upon them.
4. Customer Content and Data
As between the parties, you retain all rights in prompts, inputs, outputs, and other content you submit or receive through the Services ("Customer Content"). You grant OpenInfer only the limited rights necessary to provide the Services.
OpenInfer does not use Customer Content to train, fine-tune, or improve foundation models.
OpenInfer minimizes retention of Customer Content. Standard inference requests are processed in memory to fulfill each request. Certain platform capabilities require limited storage of customer data, including:
- server-managed session history for APIs requiring conversational state (such as OpenAI Responses-compatible APIs);
- temporary KV-cache fragments and related metadata used solely to improve inference performance and synchronize cache state across compute infrastructure; and
- customer-authorized debugging sessions where payload capture is explicitly enabled for support purposes.
Where technically supported, stored customer data may be encrypted. For self-hosted deployments, customers control the storage infrastructure and retention of such data.
Additional information regarding data handling and retention is available in the Privacy Policy & Data Retention Policy.
5. Third-Party Models
The Services execute third-party and open-weight models selected by the Customer or a routing platform acting on the Customer's behalf. Those models are subject to their own license terms. OpenInfer does not own or warrant third-party model behavior or outputs.
6. Fees and Payment
Usage-based fees are calculated using metered consumption at the rates published or agreed in an applicable Order Form. Unless required by law, fees are non-refundable. OpenInfer may modify future pricing upon thirty (30) days' notice.
7. Intellectual Property
OpenInfer retains all right, title, and interest in the Services, OpenInfer Engine, Weave, software, documentation, and related technology. No rights are granted except as expressly stated in these Terms.
8. Confidentiality
Each party will protect the other's confidential information using reasonable care and use it solely for purposes of performing under these Terms. These obligations survive termination for three (3) years and indefinitely for trade secrets.
9. Warranty Disclaimer
THE SERVICES ARE PROVIDED "AS IS" AND "AS AVAILABLE." TO THE MAXIMUM EXTENT PERMITTED BY LAW, OPENINFER DISCLAIMS ALL WARRANTIES, INCLUDING MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, AND NON-INFRINGEMENT. MODEL OUTPUTS ARE PROBABILISTIC AND MAY BE INACCURATE.
10. Limitation of Liability
TO THE MAXIMUM EXTENT PERMITTED BY LAW, NEITHER PARTY SHALL BE LIABLE FOR INDIRECT, INCIDENTAL, SPECIAL, CONSEQUENTIAL, EXEMPLARY, OR PUNITIVE DAMAGES. EACH PARTY'S TOTAL LIABILITY SHALL NOT EXCEED THE AMOUNTS PAID OR PAYABLE BY CUSTOMER DURING THE TWELVE (12) MONTHS PRECEDING THE CLAIM.
11. Indemnification
Customer will defend and indemnify OpenInfer against third-party claims arising from Customer Content, misuse of the Services, or violations of applicable law or third-party model licenses.
12. Termination
These Terms remain in effect while you use the Services. OpenInfer may suspend access for material violations, non-payment, or security risks. Either party may terminate for material breach not cured within thirty (30) days.
13. Governing Law
These Terms are governed by the laws of the State of California, excluding conflict-of-law principles. Exclusive jurisdiction shall lie in the state and federal courts located in San Mateo County, California.
14. General
These Terms, together with any Order Forms and incorporated policies, constitute the complete agreement between the parties. OpenInfer may update these Terms upon reasonable notice. Continued use of the Services after the effective date constitutes acceptance of the revised Terms.
OpenInfer, Inc. · San Mateo, California