Terms of Service

Last Updated: March 05, 2026

Welcome to LLM Router. These Terms of Service (“Terms”) are a legally binding contract between you and SOOFY LLC (“LLM Router,” “we,” “us,” or “our”) regarding your use of our website, API, dashboard, and intelligent routing services (collectively, the “Service”). PLEASE READ THE FOLLOWING TERMS CAREFULLY. BY CREATING AN ACCOUNT, ACCESSING THE API, OR USING THE SERVICE, YOU AGREE TO BE BOUND BY THESE TERMS.

1. Service Overview

LLM Router provides an intelligent middleware gateway that optimizes, routes, and processes requests between your applications and third-party Artificial Intelligence providers (e.g., OpenAI, Anthropic, Perplexity) (“AI Providers”).

Nature of Service:

You acknowledge that LLM Router acts as a processor and router. We do not generate the AI content ourselves; we facilitate the connection to third-party AI Models based on your configuration, complexity scoring, and routing rules.

2. Eligibility

You must be at least 13 years of age to use the Service. If you are using the Service on behalf of an entity, organization, or company, you represent and warrant that you have the authority to bind that organization to these Terms.

3. Accounts and Security

To use the Service, you must register for an account. You are responsible for maintaining the confidentiality of your API keys and account credentials. You accept responsibility for all activities (and costs incurred) that occur under your API keys. If you believe an API key has been compromised, you must revoke it immediately via the LLM Router dashboard.

4. Payment and Billing

4.1. Billing Models

LLM Router may introduce subscription-based access (SaaS fees) and/or usage-based fees (charged based on tokens processed) once mini-apps are launched inside the platform. These fees will cover the running costs of your applications. You agree to pay all applicable fees. We do not charge any service fees when you top up your API balance. However, third-party payment processor fees (such as Stripe transaction fees) are your responsibility and will be applied at the time of top-up.

4.2. Refunds

Refunds for API balance top-ups are available only if requested within 24 hours of the transaction. Contact support with your transaction details. No refunds after 24 hours or for consumed usage.

5. User Content and Data Processing

5.1. Your Data

You retain ownership of all inputs (“Prompts”) you send to the Service and all outputs (“Completions”) received.

5.2. Data Routing and Third Parties

By using the Service, you authorize LLM Router to transmit your Prompts to third-party AI Providers (such as OpenAI, Anthropic, Google, etc.) based on the routing logic you configure. You acknowledge that your use of these third-party models is subject to their respective Terms of Service and Privacy Policies. LLM Router is not responsible for how third-party providers handle your data once it leaves our infrastructure.

5.3. PII Redaction Feature

LLM Router offers a PII (Personally Identifiable Information) Redaction feature. While we utilize advanced algorithms to detect and mask sensitive data, no automated system is 100% error-proof. You agree that LLM Router is not liable for any failure to redact sensitive information or for any data leaks resulting from such failure. You are responsible for ensuring your data compliance (e.g., HIPAA, GDPR) regardless of the redaction tools used.

5.4. Zero Data Retention

If you enable 'Zero Data Retention' settings, LLM Router will process your request in ephemeral memory and will not log the body of your Prompts or Completions to our database. However, metadata (token counts, latency, routing decision logs) may still be stored for billing and analytics purposes.

5.5 Zero Data Retention & No Training Guarantee

LLM Router operates on a strictly ephemeral architecture. You acknowledge and agree that:

  • No Storage: We do not log, archive, or store the body of your API Requests (Prompts) or API Responses (Completions) in our databases. All processing occurs in-memory and is discarded immediately after the request is fulfilled.
  • No Training: LLM Router does not use your Customer Data to train, retrain, or improve our internal AI models.

    • 6. Prohibited Conduct

    You agree not to:
    Use the Service to violate the Terms of Service of any upstream AI Provider (e.g., generating illegal content via OpenAI). Reverse engineer the routing algorithms, complexity scoring, or latency optimization logic of LLM Router. Attempt to bypass billing limits, or API key restrictions. Use the Service for any illegal purpose or in violation of any local, state, or international law.

    7. Intellectual Property

    The Service, including the routing algorithms, dashboard interface, complexity analysis logic, and documentation, is the proprietary property of LLM Router. You grant us a license to use your feedback to improve the Service.

    8. Disclaimers

    8.1. 'As Is' Service

    THE SERVICE IS PROVIDED “AS IS” WITHOUT WARRANTIES OF ANY KIND. WE DO NOT WARRANT THAT THE SERVICE WILL BE UNINTERRUPTED OR ERROR-FREE.

    8.2. Third-Party Availability

    LLM Router is not responsible for downtime, outages, o imposed by upstream AI Providers (e.g., if OpenAI is down). While our 'Provider Fallback' feature attempts to mitigate this, we cannot guarantee availability if underlying providers fail.

    8.3. Internal Routing & Analysis Logic

    To function as an intelligent gateway, LLM Router employs an internal, lightweight AI model to analyze incoming requests before they are sent to upstream providers. This internal analysis step determines intent, complexity, and tool requirements.

    You acknowledge and agree that for this internal analysis phase, we exclusively select high-performance, cost-efficient models that meet the following strict criteria:

  • Ultra-Low Latency: The routing model must process input tokens in real-time to ensure minimal overhead added to your total request duration.
  • Zero Data Retention (ZDR): The internal model provider is contractually bound to ephemeral processing and does not store or train on your prompt data.
  • High Throughput & Cost Efficiency: We utilize optimized models (typically priced under $1.00 per million tokens) to maintain system stability and affordability without sacrificing classification accuracy.

    • While this internal analysis is automated, it is probabilistic. You accept that routing decisions are based on the AI's best interpretation of your prompt's complexity and intent at the time of the request.

    9. Limitation of Liability

    IN NO EVENT WILL LLM ROUTER (OR ITS AFFILIATES) BE LIABLE FOR ANY INDIRECT, INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES (INCLUDING LOSS OF PROFITS, DATA, OR BUSINESS INTERRUPTION) ARISING OUT OF YOUR USE OF THE SERVICE. OUR TOTAL LIABILITY SHALL NOT EXCEED THE AMOUNT YOU PAID TO LLM ROUTER IN THE TWELVE (12) MONTHS PRIOR TO THE EVENT GIVING RISE TO THE CLAIM.

    10. Indemnification

    You agree to defend and indemnify LLM Router from any claims, damages, or expenses arising from: (a) your use of the Service; (b) your violation of these Terms; or (c) any content you submit that violates the rights of a third party or applicable law.

    11. Changes to Terms

    We may modify these Terms at any time. If we make material changes, we will notify you via email or the Service dashboard. Your continued use of the Service after such changes constitutes acceptance of the new Terms.

    12. Contact Information

    The Service is offered by SOOFY LLC. Contact: support@llmrouter.app Address: 30 N GOULD ST STE R SHERIDAN, WY 82801