Terms of Service

By accessing or using the ServeLLM platform — including our website, dashboard, APIs, SDKs, and any related services (collectively, the "Service") — you agree to be bound by these Terms of Service ("Terms"). If you do not agree to these Terms, you may not use the Service.

These Terms apply to all users, whether you access the Service as an individual developer or on behalf of an organization.

ServeLLM provides an OpenAI-compatible API for inference against open-source large language models such as Qwen, Llama, Mistral, DeepSeek, and Gemma. We operate region-localized infrastructure intended to keep model traffic close to your users and to allow billing in your local currency.

The specific models, regions, throughput limits, and pricing available to you may change over time. We do not guarantee the availability of any particular model or region.

To use the Service, you must create an account and generate one or more API keys. You are responsible for safeguarding your credentials, keeping your contact information current, and for all activity that occurs under your account or keys.

You must notify us immediately of any unauthorized use of your account or any other suspected breach of security. ServeLLM is not liable for losses arising from your failure to keep credentials confidential.

You agree not to use the Service to: (a) generate or distribute content that is unlawful, harmful, defamatory, or that infringes third-party rights; (b) attempt to bypass rate limits, quotas, or security controls; (c) reverse-engineer the Service or the underlying model weights; or (d) use outputs to train competing inference services without our written consent.

You are responsible for ensuring that your use of the Service complies with all applicable laws and with the license terms of any open-source model you invoke through the API.

You retain ownership of the prompts, inputs, and other content you submit to the Service ("Customer Content"). Subject to your compliance with these Terms, you also own the outputs generated by the models in response to your Customer Content, to the extent permitted by the underlying model license.

ServeLLM does not claim ownership of Customer Content or outputs. We may process Customer Content solely to operate, secure, and improve the Service, as further described in our Privacy Policy.

Usage of the Service is billed on a per-token or per-request basis, depending on the model and plan you select. Where supported, charges are denominated in your local currency. Pricing is published in the dashboard and may be revised with reasonable notice.

You authorize ServeLLM and our payment processors to charge your selected payment method for all fees incurred. Fees are non-refundable except where required by applicable law.

We strive to keep the Service available and performant, but we do not guarantee uninterrupted operation. Scheduled maintenance, model rollouts, regional infrastructure events, and upstream provider issues may affect availability.

Specific availability commitments, if any, are set out in a separate service-level agreement applicable to your plan.

Your use of the Service is also subject to our Privacy Policy, which describes how we collect, use, and protect information. Where you operate in a specific region, we will use commercially reasonable efforts to keep inference traffic within that region.

You are responsible for ensuring that any personal data you submit through the API complies with the laws applicable to you and to your end users.

We may suspend or terminate your access to the Service if you breach these Terms, if your usage poses a security or stability risk, or if required by law. Where practical, we will notify you and provide an opportunity to cure.

You may terminate your account at any time from the dashboard. Outstanding fees remain payable upon termination.

The Service is provided on an "as is" and "as available" basis without warranties of any kind, whether express, implied, or statutory. Model outputs may be inaccurate, incomplete, or unsuitable for a given purpose. You are responsible for evaluating outputs before relying on them.

To the maximum extent permitted by law, ServeLLM and its affiliates will not be liable for any indirect, incidental, special, consequential, or punitive damages, or for any loss of profits, revenue, data, or goodwill, arising out of or related to your use of the Service.

Our aggregate liability for any claim arising out of these Terms will not exceed the amounts you paid to us for the Service in the twelve months preceding the event giving rise to the claim.

We may update these Terms from time to time. When we make material changes, we will update the "Last updated" date above and, where appropriate, provide additional notice through the dashboard or by email. Your continued use of the Service after the changes take effect constitutes acceptance of the revised Terms.

Questions about these Terms can be sent to legal@servellm.com. For account or billing issues, please use the support channels available in your dashboard.