Skip to main content

LLM Hosting Options

Three shapes for where LLM inference runs. This page is the decision guide — pick an option, then jump to the per-option reference for configuration details.

OptionPrivacySetupCostMicrotransactions
Hosted Providers⭐⭐EasyPay-per-use API
Local (Ollama)⭐⭐⭐⭐EasyHardware only
TEE (Enclave)⭐⭐⭐⭐⭐AdvancedAgent-managed✅ (future)

Hosted Providers is the umbrella term for anything reachable over HTTP: first-party APIs (OpenAI, Anthropic, Mistral, xAI, Deepseek, LibertAI) and multi-model cloud platforms that aggregate many models (AWS Bedrock; Azure OpenAI and Vertex AI not yet supported).

Data confidentiality and model verification

OptionYour data goes to...Can you prove which model ran?
Hosted ProvidersThe provider's infrastructureNo — you trust the provider
Local (Ollama)Nowhere — it stays on your machineNo — you trust your hardware
TEE (Enclave)Encrypted even in the server's RAM✅ Yes — cryptographic attestation by the CPU

TEE is the only option that provides verifiable proof that an unmodified model is running your inference. It's also the only option that supports agent-managed microtransactions (each agent pays for its own LLM calls from its own wallet) — but it's on the roadmap, not shipped yet.

Picking an option

Your priorityPick
Quick start, POCHosted (OpenAI or Anthropic)
Zero marginal costLocal (Ollama)
Simple privacyLocal (Ollama)
Scalable privacyTEE
Compliance / data residencyHosted multi-model platform (Bedrock)
Cryptographic model verificationTEE
Agent autonomy & microtransactionsTEE

Typical progression: start with a hosted provider to validate the use case, move to a multi-model platform once you need enterprise SLAs and data residency, and eventually adopt TEE for the sensitive agents where trustless verification matters.