Frequently Asked Questions

Answers to the most common questions about using SEDI.

FAQ

Frequently asked questions

Everything you need to know about the platform.

What is this platform?

An AI inference platform. Deploy models as production APIs, generate embeddings, build RAG pipelines, and monitor usage - all without managing GPUs or infrastructure.

What models do you support?

LLaMA, Mistral, GPT variants, BERT, CLIP, Whisper, Stable Diffusion, and any model from HuggingFace through our custom deployment pipeline.

Can I use a custom endpoint?

Yes. Every deployment gets a dedicated API endpoint. Pro plans support custom subdomains. Enterprise plans support vanity URLs and private network endpoints.

Is there a free tier?

The Hobby plan is free and includes 1M tokens per month. No credit card required.

How is Enterprise different?

Private GPU clusters, dedicated VPC, SLA guarantees, SSO/SAML, audit logging, and priority support.

Can I cancel anytime?

Yes. No contracts, no lock-in. Cancel from the dashboard. Your data stays accessible for 30 days.

Is my data used for training?

Never. Your input and output data is never used to train or fine-tune models. SOC 2 and GDPR compliant.

How does pricing scale?

Pricing scales with tokens processed and GPU hours. Automatic discounts apply at higher usage tiers. Enterprise pricing is custom - contact sales.