Solution
The roleplay AI API
General assistants summarize; characters inhabit. eroq's RP+ and RP mini are tuned for exactly one job — staying in persona across long, hot-temperature scenes — and exposed through an API shaped so existing chat code ports in minutes.
50 free credits · no card · private mode on every account
Tuning you cannot prompt your way into
Roleplay breaks models in specific ways: repetition loops by message 30, trained-in filler at high temperature, persona drift as the transcript outgrows the sheet, and fourth-wall breaks at the first intense turn. RP+ ships with per-model-family sampling profiles against all four — measured on production traffic from our own character platforms, re-measured when models move.
An API shaped for character products
The surface is the OpenAI chat convention plus the parameters character work actually needs:
- →A top-level context field for character sheets and world state — kept out of your transcript management.
- →System turns that replace our neutral preamble entirely when you want full control.
- →Stateless by design: you own memory, windows and summaries — the only architecture that lets you control drift.
- →SSE streaming with a final usage event; flat 1 or 3 credits per completion, streamed or not.
- →Uncensored range within a written AUP — dark and intense scenes render instead of refusing.
From zero to a talking character
The tutorial covers the whole pattern — persona prompt, history window, streaming relay, unit economics — and the free 50 credits cover an evening of testing. Budget rule of thumb: an engaged user sending 80 messages a day costs about $0.80 of model spend on RP mini.
One call to see it
curl https://eroq.ai/v1/chat/completions \
-H "Authorization: Bearer $EROQ_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "eroq-rp-plus",
"context": "Mira: sardonic starship mechanic, dry humor, hates small talk. Scene: engine bay, mid-shift.",
"messages": [
{
"role": "user",
"content": "The reactor is making that noise again."
}
]
}'Base URL https://eroq.ai/v1 · full reference in the docs
| Model | Kind | Price |
|---|---|---|
| eroq-rp-plus | chat | 3 credits / completion |
| eroq-rp-mini | chat | 1 credit / completion |
| eroq-uncensored | image | 10 credits / image |
| eroq-krea2 | image | 10 credits / image |
| eroq-one | image | 20 credits / image |
| eroq-anime | image | 10 credits / image |
| eroq-motion-one | video | 12 credits / second |
| eroq-motion-pro | video | 30 credits / second |
| seedance-2-5 | video | 62 credits / second |
| veo-3-1 | video | 106 credits / second |
| sora-2-pro | video | 80 credits / second |
| kling-3-pro | video | 45 credits / second |
| seedance-2-0 | video | 40 credits / second |
| hailuo-3 | video | 35 credits / second |
| runway-gen-4-5 | video | 32 credits / second |
| veo-3-1-fast | video | 27 credits / second |
| kling-3 | video | 34 credits / second |
| seedance-2-0-fast | video | 24 credits / second |
| hailuo-3-max | video | 22 credits / second |
| grok-imagine | video | 37 credits / second |
| seedance-2-0-mini | video | 9 credits / second |
| veo-3-1-lite | video | 14 credits / second |
| wan-3 | video | 27 credits / second |
| eroq-flash-image | image | 10 credits / image |
| eroq-flux-image | image | 12 credits / image |
| gpt-image-2-5-sunburst | image | 31 credits / image |
| gpt-image-2-5-flare | image | 31 credits / image |
| nano-banana-2-1 | image | 31 credits / image |
| seedream-5-0-pro | image | 36 credits / image |
| nano-banana-pro | image | 124 credits / image |
| flux-3-image | image | 32 credits / image |
| grok-imagine-2-0 | image | 32 credits / image |
Full table on the pricing page.
Questions builders ask
What is the best AI for roleplay? +
For character products, we make the case for RP+: persona-tuned sampling, no refusal wall (a written policy instead), flat credit pricing and a context field built for character sheets. Mainstream flagships write beautiful prose but refuse dark or intense scenes; open-source RP finetunes win for self-hosters. The full ranked comparison is on our blog.
Is the roleplay API compatible with OpenAI client code? +
The request and response shapes follow the OpenAI chat convention — most integrations port by changing the base URL, key and model id. Streaming uses standard SSE chunks.
How do I keep a character consistent over hundreds of messages? +
Send a conduct-focused system prompt or the context field, window your history to 20–40 turns, and filter out any turn where the model broke character. The engine's sampling profiles handle repetition and filler.
Is the roleplay API uncensored? +
Yes, within a written acceptable-use policy: the story goes where it goes, with no filter layered on top. Minors, real identifiable people and illegal content are banned absolutely.
What is the difference between RP+ and RP mini? +
Same API and persona handling; RP+ (3 credits) is the flagship for texture and long scenes, RP mini (1 credit) is sized for high-volume products. Many products mix both.