Terms of Service

By creating an account or sending requests to the Siftfy API, you agree to these terms. If you don't agree, don't use the service.

These terms explain how you may use Siftfy's hosted spam-classification API, including account responsibilities, acceptable use, billing, rate limits, service availability, ownership of submitted content, and liability limits. They apply when you create an account, generate API keys, or send requests to the service.

The service

Siftfy ("we", "us") operates a hosted spam-classification API at api.siftfy.io. The service classifies arbitrary text and returns a calibrated probability that the input is spam. Available tiers, rate limits, and prices are listed at /pricing.

Acceptable use

You agree not to:

• Use the service to harass, defame, or violate the rights of others.
• Attempt to reverse-engineer, scrape, or extract the underlying model weights.
• Bypass rate limits, share API keys across uncontracted tenants, or resell access without written permission.
• Use the service in life-safety, medical, legal, or other contexts where misclassification would cause material harm. Spam scores are probabilistic and not suitable for sole reliance in such contexts.
• Submit content you don't have the right to process.

Your account

You are responsible for activity under your account and for keeping your API keys confidential. Notify us immediately if you suspect a key has been compromised, by emailing hi@siftfy.io or revoking the key from your dashboard.

Billing

The Free tier costs $0 and includes the request quota documented at /pricing. Paid plans bill monthly in arrears via Stripe; usage above the included quota is metered and billed on the same invoice. You can change or cancel your plan at any time; cancellation takes effect at the end of the current billing period.

Service availability

We aim for high availability but don't guarantee uninterrupted service on any tier. We may perform maintenance, change rate limits, or evolve the API with reasonable notice. Material breaking changes to /v1/* will be announced in advance via email and the changelog.

Model behaviour

The classifier produces calibrated probabilities, not ground-truth labels. You are responsible for choosing a threshold appropriate to your use case and for any downstream action taken on a score. Performance is measured on public benchmarks; your traffic distribution may differ.

Intellectual property

You retain all rights to the content you submit. We claim no license to training data, model fine-tuning, or any other use beyond classifying the request and returning a response. The Siftfy name, logo, and site content remain our property.

Termination

You may close your account at any time from the dashboard. We may suspend or terminate accounts for violations of these terms, abusive traffic, or unpaid invoices, with notice where reasonable.

Disclaimers and liability

The service is provided "as is" without warranties of any kind, express or implied. To the maximum extent permitted by law, our total liability for any claim arising from your use of the service is limited to the fees you paid to us in the twelve months preceding the claim.

Governing law

These terms are governed by the laws of the jurisdiction in which Siftfy is incorporated. Disputes will be resolved in the courts of that jurisdiction.

Changes

We will update this page with material changes and refresh the "last updated" date above. Continued use of the service after a change constitutes acceptance of the revised terms.

Common terms questions

Contact

Questions about these terms? Email hi@siftfy.io.