Black Friday

−50 % sur une année entière, tous les forfaits

J’en profite
eroq

Solution

The roleplay AI API

General assistants summarize; characters inhabit. eroq's eroq RP+ and eroq 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.

40 crédits offerts · sans carte · mode privé sur tous les comptes

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. eroq 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, 3 or 20 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 40 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 eroq RP mini.

Un appel pour voir

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."
    }
  ]
}'

URL de base https://eroq.ai/v1 · référence complète dans la doc

ModèleTypePrix
eroq-rp-pluschat3 crédits / réponse
eroq-rp-minichat1 crédit / réponse
claude-fable-5-2chat20 crédits / réponse
eroq-uncensoredimage10 crédits / image
eroq-krea2image10 crédits / image
eroq-oneimage10 crédits / image, +1 par image supplémentaire
eroq-animeimage10 crédits / image
eroq-motion-onevideo29 crédits / seconde
eroq-motion-provideo30 crédits / seconde
seedance-2-5video98 crédits / seconde
veo-3-1video169 crédits / seconde
kling-3-provideo71 crédits / seconde
seedance-2-0video64 crédits / seconde
hailuo-3video55 crédits / seconde
runway-gen-4-5video51 crédits / seconde
veo-3-1-fastvideo43 crédits / seconde
kling-3video54 crédits / seconde
seedance-2-0-fastvideo39 crédits / seconde
hailuo-3-maxvideo34 crédits / seconde
grok-imaginevideo60 crédits / seconde
seedance-2-0-minivideo15 crédits / seconde
veo-3-1-litevideo22 crédits / seconde
wan-3video43 crédits / seconde
eroq-flash-imageimage10 crédits / image
eroq-flux-imageimage12 crédits / image
gpt-image-2-5-sunburstimage31 crédits / image
gpt-image-2-5-flareimage31 crédits / image
nano-banana-2-1image31 crédits / image
seedream-5-0-proimage36 crédits / image
nano-banana-proimage124 crédits / image
flux-3-imageimage32 crédits / image
grok-imagine-2-0image32 crédits / image

Tableau complet sur la page des tarifs.

Confidentialité

Privé et sans restrictions

  • →Aucun filtre sur les moteurs d’eroq : une politique écrite à la place.
  • →Ils ne gardent rien, et rien ne s’entraîne sur ton travail.
  • →Le mode privé ne garde aucun fichier.

Les questions des développeurs

What is the best AI for roleplay? +

For character products, we make the case for eroq 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 eroq RP+ and eroq RP mini? +

Same API and persona handling; eroq RP+ (3 credits) is the flagship for texture and long scenes, eroq RP mini (1 credit) is sized for high-volume products. Many products mix both.

Premier appel en cinq minutes.