there are many cloud providers of zero data retention llm APIs, and even cryptographic attestation.
they are not throttled, you can get an agreed rate limit.
Fast: inception labs or cerebras
Confidential: tinfoil.sh, phala
TTS/STT: groq
Routers: vercel (or openrouter if they don't have the model).
Search: unsolved, just can't get zdr, local hosted.
there are many cloud providers of zero data retention llm APIs, and even cryptographic attestation.
they are not throttled, you can get an agreed rate limit.