Paitho routes every LLM call through your own provider keys. We never touch your token bill, and we publish exact usage per draft.
No black-box markup. Every token shows up on your provider's bill, not ours.
Per-draft token count. Per-vertical model choice. Per-tenant spend cap.
Prompt and response only ever touch your provider's account. We see the metadata; they see the content.
Your prompts, your keys, your call history. Export the lot anytime.
Three real operator profiles, priced at current published rates. Token counts are averages from our own production traffic.
AES-256 per-tenant keychain. Each workspace's keys are encrypted with a workspace-scoped DEK, wrapped by a region-scoped KEK in KMS.
Logs reference an opaque key_id only. Even our SREs can't read your keys from any log line, dump, or trace.
Per-key spend cap, per-tenant monthly budget, configurable alert thresholds. Pipeline pauses gracefully when you hit a ceiling.
Add Anthropic, OpenAI, Google, or any supported provider. Paitho routes calls. Your provider invoices you.
Buy a credit pack from Paitho. We handle provider keys, model routing, and cost optimization. You get one invoice.
Either way, you only ever pay what the model costs. We just remove the markup.