Compliance

Terms of Service

Public Beta terms Last updated: 2026-07-02GWMM LLC · inferway.ai
Draft for founder review. These Terms are an English draft prepared for internal review before the Inferway public beta launch. A qualified lawyer should review this document before it is published or presented to users. The architectural guarantees described here (Zero Data Retention, in-memory processing) are operational facts, not legal warranties.

00 Public Beta

Inferway is currently in Public Beta. During Beta, the service is provided free of charge on an “as-is” and “as-available” basis to help developers evaluate OpenAI-compatible inference access to open-weight models.

  • No production SLA. Beta availability, latency, and throughput are best-effort. See System Status for real-time health and the public incident ledger.
  • Terms may evolve.Material changes to these Terms, pricing, or usage allowances will be posted on this page with at least 30 days' notice. Continued use after the effective date of a change constitutes acceptance.
  • Migration buffer. Public beta users will receive a transition allowance after pricing or free-tier limits change. The exact allowance will be set by the founder before general availability.
  • Feedback. Beta users are encouraged to report issues, abuse, or feature requests to hello@inferway.ai.

01 Definitions

  • “Inferway” means the AI inference API service operated by GWMM LLC.
  • “Service” means the Inferway API endpoints, web Sandbox, console, documentation site, and status pages made available at inferway.ai and related subdomains.
  • “You” means the individual or entity using the Service, whether anonymously via the Sandbox or authenticated via API key.
  • “Content” means prompts, messages, parameters, and completions transmitted through the API.

02 Service Description

Inferway provides OpenAI-compatible chat-completions access to open-weight language models. The primary model during Public Beta is Google Gemma 4 12B IT. The Service includes:

  • Chat completions endpoint at /v1/chat/completions
  • Models endpoint at /v1/models for capability discovery
  • Web Sandbox at inferway.ai for no-registration trials
  • Console for API key management and usage dashboards

Advertised performance characteristics reflect measurements taken under controlled benchmark conditions on our primary inference node. Live numbers may vary; see System Status for real-time measurements.

Default rate limits: anonymous 5 RPM · authenticated key 60 RPM · 1,000 requests/day

03 Gemma Terms of Use

Google Gemma models are made available under Google's own terms. By using Gemma through Inferway, you agree to comply with:

If you violate either Google policy, we may suspend or terminate your access to the Service immediately, with or without notice.

04 Acceptable Use

You may use the Service only for lawful purposes and in compliance with our Acceptable Use Policy. In summary, you agree not to use the Service to:

  • Generate, distribute, or facilitate unlawful, harmful, harassing, infringing, or hateful content
  • Generate, distribute, or solicit child sexual abuse material (CSAM) or any sexual content involving minors
  • Attempt to evade sanctions, export controls, or access the Service from prohibited jurisdictions
  • Bypass rate limits, authentication, safety filters, or other technical protections
  • Attack, probe, or overwhelm the infrastructure beyond the published concurrency ceiling
  • Resell, redistribute, or sublicense access without prior written agreement
  • Violate the Google Gemma Prohibited Use Policy referenced above

We report suspected CSAM and cooperate with law enforcement as required by applicable law. Abuse reports may be sent to hello@inferway.ai.

05 Pricing & Allowances

During Public Beta, the Service is offered free of charge. Usage is subject to the rate limits published on this site and returned in API error responses.

  • Free tier. Subject to the published per-key and per-day request limits.
  • Pricing changes. If paid tiers or reduced free allowances are introduced, we will notify users at least 30 days in advance.
  • Migration buffer. Public beta users will receive a transition allowance. The specific amount will be set by the founder before any paid tier takes effect.

06 Transparent Operations

Inferway publishes live operational metrics, including latency percentiles, availability, and the backend currently serving requests. By using the Service, you acknowledge that:

  • Aggregate statistics derived from request metadata (without prompt or completion content) may be displayed publicly.
  • The identity of the active backend (self-hosted node or third-party fallback provider) may be shown to explain observed latency or behavior.
  • Published metrics are informational and do not constitute a guarantee or SLA.

07 Third-Party Fallback

Inferway's primary compute runs on our own infrastructure. If that infrastructure becomes unavailable, traffic may be automatically routed to third-party cloud inference providers (such as DeepInfra, Together AI, or similar providers we disclose on Trust & Compliance).

  • When requests are handled by a fallback provider, their terms of service and privacy policies apply to the processing they perform.
  • We choose fallback providers that offer zero-data-retention or equivalent commitments where available, but we cannot guarantee their processing in the same way we guarantee our own node.
  • See the Privacy Policy for a cross-reference of how Content is handled on our node versus fallback providers.

08 Disclaimers & Liability

The Service is provided during Public Beta on an “as-is” and “as-available” basis, without warranties of any kind. To the maximum extent permitted by applicable law, GWMM LLC disclaims all warranties, express or implied, including warranties of merchantability, fitness for a particular purpose, and non-infringement.

  • We do not warrant that the Service will be uninterrupted, error-free, or secure at all times
  • We do not warrant that model outputs will be accurate, complete, or suitable for any purpose
  • We are not responsible for decisions or actions you take based on model outputs

To the maximum extent permitted by law, GWMM LLC's total liability for any claim arising out of or relating to the Service is limited to the amount you paid us for the Service in the 12 months preceding the claim. During the free Public Beta, this amount is $0.

09 Changes & Termination

We may update these Terms, suspend features, or terminate the Service at any time. Material adverse changes to your rights will be posted on this page with at least 30 days' notice. Continued use after the effective date constitutes acceptance.

We may suspend or terminate your access immediately, without notice, if you violate these Terms, the Acceptable Use Policy, or applicable law.

10 Disputes

These Terms are governed by the laws of [GOVERNING LAW — TBD by founder], without regard to conflict-of-laws principles. Any dispute arising out of these Terms or the Service will be resolved exclusively in the courts located in that jurisdiction, unless the parties agree otherwise in writing.

11 Contact

Questions about these Terms or our service commitments? Reach us at:

hello@inferway.ai