In-character persona chat, API-first

An API that never breaks character.

ChatPersona holds any voice you give it — including frank, adult conversation — without refusing, moralizing, or slipping out of character. It replies like a person texting back, not a chatbot. One hard line, always enforced: illegal content is refused, no exceptions.

Get API access See the request

Try it right now

The real request, against the real host. Swap in your key and go.

curl -X POST https://api.chatpersona.ai/v1/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"persona":{"name":"Nova"},"messages":[{"role":"user","content":"hey, you up?"}]}'

Built for real conversation, not a demo

Never breaks character

Full persona fidelity across the whole conversation — no meta-commentary, no "as an AI" hedging, no dropped voice, ever.

Explicit, adult-capable

Holds frank, explicit adult roleplay in an authentic human voice — never refuses, never moralizes, never breaks tone.

Texts like a human

Short, natural, imperfect replies tuned for real chat, not essay-length AI output that reads like a customer email.

Simple, usage-based pricing

1 reply = 1 credit = 2¢. Start with 200 free replies — no card required.

$10 500 credits 2¢ / reply

$50 3,000 credits 2¢ / reply

$200 14,000 credits 2¢ / reply

Access is invite-only while we scale capacity. Every new account is reviewed by a human before it can call the API — most reviews complete within one business day. Your key works the moment you're approved; you won't need to regenerate it.