Integration
eroq for SillyTavern
SillyTavern is where the serious roleplay happens; eroq is an API built for exactly that traffic. The endpoint is OpenAI-shaped, so connecting is three fields in the connection panel — no proxy, no wrapper scripts — and the models on the other side are tuned for long, in-character, uncensored scenes.
50 free credits · no card · adults only, by policy
Connect in under a minute
From SillyTavern's API connections panel:
- →API type: Chat Completion — source: Custom (OpenAI-compatible).
- →Custom Endpoint (Base URL): https://eroq.ai/v1
- →API Key: create one in the eroq dashboard — new accounts get 50 free credits.
- →Model: use "Fetch models" (we serve GET /v1/models) or type eroq-rp-plus / eroq-rp-mini directly.
Models that hold character, prices that hold still
RP+ and RP mini are persona engines, not assistants: tuned sampling against repetition and filler across hundred-message scenes, a context field built for character cards, SSE streaming, and uncensored range governed by a written policy — adult fiction between adult characters stays in character; minors and real identifiable people are banned absolutely.
Billing is flat per completion — RP+ at 3 credits, RP mini at 1 credit (~1¢) — so a long card costs the same as a short one and heavy evenings stay plannable. Failed generations refund automatically, and prompts are processed in memory, never retained.
RisuAI, Agnai and every other OpenAI-shaped frontend
The same three fields work in any frontend with a custom OpenAI-compatible source — RisuAI, Agnai and the rest of the BYO-key family connect identically. And the key you chat with also unlocks the rest of the stack when you want it: Image One for scene art at 10 credits, Voice One to hear the reply at 3 credits per 100 characters.
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-image-one | image | 10 credits / image |
| eroq-motion-one | video | 100 credits / 5s clip |
Full table on the pricing page.
Questions builders ask
How do I connect eroq to SillyTavern? +
Chat Completion API → Custom (OpenAI-compatible) → endpoint https://eroq.ai/v1 → paste your eroq API key → fetch models and pick eroq-rp-plus or eroq-rp-mini. That is the whole setup.
Which eroq model is best for SillyTavern? +
RP+ (3 credits per completion) for the best in-character writing on long scenes; RP mini (1 credit) when you chat heavily and want the economical tier. Same API shape and same persona handling on both.
Is it actually uncensored? +
For adult fiction between adult characters, yes — in character, without refusal drift, under a written acceptable-use policy. Content involving minors or real identifiable people is banned absolutely and returns an explicit error, never a charge.
What does heavy roleplay cost? +
Flat per reply: 1 credit (~1¢) on RP mini, 3 on RP+. Packs start at $10 for 1,000 credits, and the 50 free signup credits are enough to run a real evening of scenes before paying anything.
Does this work with RisuAI or Agnai? +
Yes — any frontend with a custom OpenAI-compatible source connects with the same endpoint, key and model id.