InferGauge Terms of Service
Effective date: October 27, 2026
Last updated: October 29, 2026
1. The agreement
These Terms are an agreement between you and Nexus Corporation DBA InferGauge ("InferGauge", "we", "us"), 9772 Athletic Way, Gaithersburg, MD 20878, USA. They apply to the InferGauge website, the InferGauge console, the InferGauge command-line agent, and the InferGauge app for ChatGPT, together "the Service".
By creating an account or using the Service, you agree to these Terms. If you use the Service for an organization, you confirm that you are authorized to accept these Terms on its behalf, and "you" includes that organization. Our Privacy Policy explains how we handle personal information and forms part of these Terms.
2. The Service
InferGauge measures how AI and LLM endpoints perform under load: latency, time to first token, inter-token latency, throughput, error rates, goodput, response quality and cost.
Tests run on your own machine or CI runner, using the InferGauge agent. The agent sends requests to the endpoints you configure, then uploads metrics and findings to your InferGauge console. It removes prompts, model responses, API keys and private endpoint URLs before uploading, as described in the Privacy Policy. InferGauge never runs a test on our infrastructure or inside ChatGPT.
The console and the ChatGPT app help you build test configurations, read and compare results, and generate CI workflows. What you can do depends on your plan (section 6).
3. Your account
You must be at least 16 years old to use the Service. You agree to give accurate account information and keep it up to date.
You are responsible for everything done with your account, including by anyone using your password, an API token, or an MCP access token issued to an app you connected. Keep your credentials secure. If you think one has been exposed, revoke it in the console under Settings and tell us at the contact address in section 18.
One account is for one person. Accounts can't be shared, and you can't create accounts to get around a plan's limits.
4. Acceptable use
InferGauge generates heavy traffic on purpose, so these rules matter. You may only test endpoints that you own, or that you have written permission to load test. You must not:
- Point a test at a system you aren't authorized to test, or use the Service to disrupt, overload or attack any system, network or service.
- Run tests that break the terms, rate limits or acceptable-use policies of the AI provider whose endpoint you are testing. Check those before testing a hosted provider at scale.
- Try to access another customer's account, runs or data, or probe the Service for vulnerabilities without our written permission.
- Get around plan limits, quotas or rate limits, including on the ChatGPT app, or share credentials so several people can use one account.
- Use the Service to build a competing product, or copy, resell or sublicense it, except as the software license in section 9 allows.
- Upload unlawful content, or use the Service in breach of any law or regulation.
We may suspend tests, tokens or accounts that break these rules (section 12).
5. Testing costs
Tests send real requests to the endpoints you configure. Any charges your AI provider makes for those requests, such as per-token fees, are yours, and are billed by the provider, not by us.
Cost figures InferGauge reports, including monthly projections, are estimates calculated from the pricing you enter in your configuration. They are not invoices, and they may differ from what your provider actually charges. Guardrails such as a maximum spend stop a run on our measured estimate, not on your provider's billing, so set your own limits with your provider as well.
6. Plans and billing
The Service is offered on Free, Developer, Team and Enterprise plans. Each plan has limits, such as the number of concurrent users per test, test duration, runs per month and the kinds of endpoint you can test. The Service enforces those limits, and the current limits are shown in the console.
Paid plans are billed in advance, monthly or annually, through our payment processor, Stripe. Subscriptions renew automatically until you cancel. You can cancel at any time, and the cancellation takes effect at the end of the current billing period. We don't refund part of a billing period, except as section 12 provides or where the law requires us to.
If a payment fails or a subscription ends, your account moves to the Free plan. Your run history stays, but the Free plan's limits apply from then on. We will give at least 30 days' notice of any price change, and it applies from your next billing period.
7. Your data
You own the data you put into the Service, including test configurations and the results your agent uploads. You give us permission to store and process that data only to provide, secure and support the Service for you, as the Privacy Policy describes.
We don't collect your prompts, model responses, API keys or private endpoint URLs. The agent removes them before uploading anything. If you delete your account, we delete your data within 30 days, apart from limited records the Privacy Policy says we keep.
8. InferGauge in ChatGPT and Claude
The ChatGPT and Claude integrations are optional. When you connect either, you sign in to the InferGauge console, and that assistant receives an access token that works only for InferGauge's tools in it. The token expires after 90 days. You can revoke it at any time in the console, under Settings, MCP tokens.
Through either integration, ChatGPT or Claude can create test configurations and read your account's own results, comparisons and plan details at your request. Section 4 of the Privacy Policy lists exactly what is sent. Once in ChatGPT, that information is also covered by OpenAI's terms and privacy policy; once in Claude, by Anthropic's terms and privacy policy; either way, terms we don't control.
ChatGPT and Claude each write their own replies from what our tools return, so the wording isn't ours. Review any configuration or workflow either one gives you before you run it. Neither integration ever runs a test or accepts credentials, and both are rate-limited per token.
9. Software license
The InferGauge agent and self-hosted console are licensed under the Business Source License 1.1, which converts to the Apache License 2.0 on 1 August 2030. That license, in the LICENSE file distributed with the software, governs your use of the software itself. These Terms govern the hosted Service at infergauge.com and console.infergauge.com.
The InferGauge name, logo and website content belong to us. Nothing in these Terms gives you rights to them beyond using the Service.
10. Results and findings
Scores, SLA verdicts, saturation estimates, regression comparisons and written findings are measurements and analysis of the tests you run. They depend on your configuration, the thresholds you set, your network and the endpoint's behaviour at the time. They are not a guarantee of how a system will perform in production.
Runs that use InferGauge's built-in simulator measure a simulated endpoint. Their results show how the Service works, not the capacity of any real system.
11. Availability and changes
We work to keep the Service available, but we don't promise it will be uninterrupted or error-free, and we may need to take it down for maintenance. We may change or remove features. If we remove a feature that a paid plan relies on, we will give reasonable notice.
12. Suspension and termination
You can stop using the Service and delete your account at any time.
We may suspend or close an account, or revoke its tokens, if it breaks these Terms, if its use puts the Service, other customers or third parties at risk, or if the law requires it. Where it's reasonable to, we will tell you first and give you a chance to fix the problem. If we close a paid account without cause, we will refund the unused part of the billing period.
Sections 5, 7, 9, 13, 14, 15 and 16 continue after your account ends.
13. Disclaimers
Except as these Terms expressly say, the Service is provided "as is" and "as available". To the extent the law allows, we disclaim all implied warranties, including merchantability, fitness for a particular purpose and non-infringement. Some places don't allow these disclaimers, in which case they apply only as far as the law permits.
14. Limitation of liability
To the extent the law allows, neither party is liable for indirect, incidental, special, consequential or punitive damages, or for lost profits, revenue or data. Our total liability for all claims relating to the Service is limited to the greater of the fees you paid us in the 12 months before the claim arose, or US$100.
This section doesn't limit liability that the law doesn't allow to be limited, or your obligations under section 15.
15. Indemnity
You will defend and indemnify us against claims, losses and costs, including reasonable legal fees, arising from tests you run against systems you weren't authorized to test, from your breach of section 4, or from charges your AI provider makes for your tests.
16. Governing law and disputes
These Terms are governed by the laws of the State of Maryland, USA, without regard to its conflict-of-law rules. Disputes will be heard in the state or federal courts located in Maryland, and both parties consent to those courts' jurisdiction. Nothing here takes away consumer protections that the law where you live gives you and that can't be waived.
17. Changes to these Terms
We may update these Terms. If a change is material, we will tell you by email or in the console at least 30 days before it takes effect. If you keep using the Service after a change takes effect, the updated Terms apply. If you don't agree, you can cancel before then.
18. Contact
Nexus Corporation DBA InferGauge
9772 Athletic Way, Gaithersburg, MD 20878, USA