eroq api · public beta
Expressive AI,
one API.
The uncensored roleplay engine behind millions of conversations — plus image, video and voice — in one credit-metered API. Flat pricing, streaming, no surprise bills.
NSFW-friendly by policy · adults only, always
50 free credits on signup · no card required
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."
}
]
}'Trusted by
6
models, one key
1 cr
cheapest completion
SSE
token streaming
0
outputs retained
Partnering with global industry leaders to power your creative output
The catalogue
Six models, one store. Flat prices.
RP+
chateroq-rp-plus
Our production roleplay engine: stays in character across long scenes, tuned sampling against repetition and filler, streams over SSE. The model behind millions of conversations on our consumer network.
3 credits / completion
RP mini
chateroq-rp-mini
The economical tier for high-volume products. Same API shape and same persona handling as RP+, sized for latency and cost.
1 credit / completion
Image One
imageeroq-image-one
Character-grade image generation with negative prompts and CFG control. Returns the image inline — we never retain your outputs.
10 credits / image
Image Anime
imageeroq-image-anime
A diffusion family tuned for anime, manga and stylized illustration. Same controls and price as Image One.
10 credits / image
Image Art
imageeroq-image-art
A prose-driven engine for artistic and painterly renders — it follows long, descriptive prompts closely.
10 credits / image
Motion One · Wan
videoeroq-motion-one
Wan-powered text-to-video for 5 or 10 second clips, fully NSFW-capable. Rendering is slow by nature (up to a few minutes) — the request holds until the clip is ready.
100 credits / 5s clip
Seedance 1.0 Pro
videoseedance-1-pro
ByteDance's flagship motion model: 1080p, coherent physics, native aspect-ratio control and image-to-video casting. Moderated upstream — SFW work only.
140 credits / 5s clip
Seedance 1.0 Lite
videoseedance-1-lite
The fast, economical Seedance tier — iterate on a shot in drafts, then render the keeper on Pro. Moderated upstream — SFW work only.
60 credits / 5s clip
Kling 2.5 Turbo
videokling-2-5-turbo
Kuaishou's motion flagship — remarkably fluid movement, strong faces, native aspect control and image-to-video casting. Moderated upstream — SFW work only.
120 credits / 5s clip
Hailuo 02 · MiniMax
videohailuo-02
MiniMax's Hailuo engine — cinematic camera language and convincing physics, with image-to-video casting. Moderated upstream — SFW work only.
100 credits / 5s clip
Veo 3 Fast
videoveo-3-fast
Google's Veo 3 Fast renders the soundtrack WITH the picture — ambient noise, effects, even dialogue. Fixed 8-second clips at up to 1080p. Moderated upstream — SFW work only.
256 credits / 8s clip
Voice One
speecheroq-voice-one
Natural speech synthesis with a curated voice roster. Returns MP3 audio directly.
3 credits / 100 characters
Voice Turbo
speecheroq-voice-turbo
The high-volume voice tier: lower latency and a lower price, same roster and cloned voices as Voice One.
2 credits / 100 characters
Scribe One
transcriptioneroq-scribe-one
Transcription with automatic language detection, built for voice-message-length audio.
5 credits / request
Store
storageeroq-store
NSFW-friendly object storage on a global CDN — host what you generate without a mainstream bucket terminating you. Upload once, serve forever, fair use included.
2 credits / 10 MB uploaded
Why eroq
Built for character products, not chatbots.
Stays in character
RP+ is tuned for persona work: repetition damping, filler suppression, and sampling that survives 200-message scenes. A context field carries the character sheet; a messaging mode answers like texting when your product is DMs, not novels.
Uncensored by design
Fiction goes where your users take it. NSFW roleplay and imagery between adults render instead of refusing — the wall is our acceptable-use policy (no minors, no real people, ever), not a filter’s mood.
Credits, not invoices
Prepaid credits with flat per-call costs. An image is 10 credits every time — no token math, no surprise bill, and failed generations refund themselves.
One API for every medium
Chat that can look at the pictures your users send, image and short-video generation, speech both ways, and NSFW-friendly CDN storage for the outputs — one key, one error shape, OpenAI-style requests that port in minutes.
Streaming first
Server-sent events on chat with the standard chunk format. First tokens reach your UI while the model is still writing.
Docs that cannot drift
Reference pages, openapi.json and llms.txt are generated from the same spec the endpoints charge from. If the docs say 3 credits, the meter says 3 credits.
Pricing
Top up. Build. Repeat.
Starter
$10
1,000 credits
Try every model properly.
Builder
+10%$50
5,500 credits
Enough to ship a beta.
Scale
+20%$100
12,000 credits
Production traffic, best rate.
Prefer a subscription? Monthly plans from $9 carry bonus credits and 2–4× rate limits.
FAQ
The short version.
What is a credit worth? +
Packs start at $10 for 1,000 credits — about a cent each, with bonus credits on larger packs. A chat completion costs 1–3 credits, an image 10, a 5-second clip 100.
Is the API OpenAI-compatible? +
The request and response shapes follow the OpenAI convention (chat/completions, images/generations, audio/speech), so most client code ports by changing the base URL, key and model id. We are not affiliated with OpenAI.
Do you store my generations? +
No. Images, clips and audio return inline in the response and are not retained. Store what you want to keep.
What happens when a generation fails? +
The call is refunded automatically and the refund appears in your usage ledger. You only pay for output.
Is NSFW content allowed? +
Yes — that is the point. eroq is NSFW-friendly by policy: uncensored roleplay, adult fiction and mature imagery between adult characters are supported across chat, image and video. The hard limits are absolute: no minors, no real-person impersonation, nothing illegal. See the acceptable-use policy.
Will the model refuse my users mid-scene? +
Our engines are selected so adult scenes render instead of hitting a refusal wall. Requests outside the acceptable-use policy return an explicit content_blocked error rather than a lecture — and are never charged.
From the engine room.
all articles →Aug 28, 2026 · 7 min
Best AI for roleplay in 2026 — ranked for character chat and immersive RP
The models that actually hold a character in 2026 — mainstream flagships, open-source RP finetunes and purpose-built engines, ranked on consistency, refusal behavior, repetition resistance and cost. With the criteria the other lists soften.
Aug 28, 2026 · 3 min
Character.AI alternatives in 2026 — for users who hit the filter, and builders who ship
Where people go when Character.AI's filter breaks their story — and what developers use to build the alternative themselves. Frontends, APIs and engines compared, with honest trade-offs.
Aug 28, 2026 · 2 min
The NSFW alternative to the OpenAI API — same shape, no wall
Your OpenAI integration works until the content does't pass the filter. eroq keeps the request shape and swaps the policy: uncensored roleplay, images and voice for adult products, ported in three strings.
First call in five minutes.
Sign up, create a key, paste the quickstart. 50 free credits are enough to try every model.