Models
Every engine, named and priced
eroq does not hide its models behind a brand. Pick the engine for the shot — Seedance for casts and long takes, Veo for sound, Kling for faces, Hailuo for drama, Motion One for uncensored, private clips — plus image models, voices and roleplay chat, all on one key and one credit balance.
Video engines
eroq Motion OneNew
eroq-motion-one
Our own engine — uncensored, native audio
Motion Pro
eroq-motion-pro
Uncensored clips, 5 to 15 seconds
Seedance 2.5Top
seedance-2-5
The long-take flagship — up to 30 seconds with sound
Veo 3.1
veo-3-1
Google’s flagship — up to 4K with native audio
Kling 3.0 Pro
kling-3-pro
Fluid motion, expressive faces
Seedance 2.0
seedance-2-0
Character consistency, up to 4K
Hailuo 3
hailuo-3
2K cinematic physics, subject references
Runway Gen-4.5
runway-gen-4-5
Cinematic motion, strong prompt adherence
Veo 3.1 Fast
veo-3-1-fast
Veo quality, faster and a quarter of the price
Kling 3.0
kling-3
Kling motion at the standard tier
Seedance 2.0 Fast
seedance-2-0-fast
Seedance references and sound, faster
Hailuo 3 Max
hailuo-3-max
Fast Hailuo motion, 768p
Grok Imagine
grok-imagine
Quick clips from a prompt or a start image
Seedance 2.0 Mini
seedance-2-0-mini
The most affordable clip on eroq
Veo 3.1 Lite
veo-3-1-lite
Veo with sound, on every account
Wan 3.0
wan-3
Up to 30 seconds, references and sound
Image models
Eroq UncensoredTop
eroq-uncensored
Uncensored photoreal, fully private
Krea2
eroq-krea2
Clean photoreal for character renders
Eroq OneTop
eroq-one
Generation + instruction editing, up to 10 reference images
Anima
eroq-anime
Anime illustration, uncensored
Flash Image
eroq-flash-image
Fast multimodal renders, broad style range
Flux Image
eroq-flux-image
High-fidelity photoreal
GPT Image 2.5 SunburstNew
gpt-image-2-5-sunburst
OpenAI's flagship — precise text, composition and control
GPT Image 2.5 FlareNew
gpt-image-2-5-flare
OpenAI's image model tuned for expressive, dramatic frames
Nano Banana 2.1New
nano-banana-2-1
Google's fast multimodal image model
Seedream 5.0 ProNew
seedream-5-0-pro
ByteDance's flagship — rich detail and texture
Nano Banana ProNew
nano-banana-pro
Google's highest-fidelity image model
Flux 3 ImageNew
flux-3-image
Black Forest Labs' FLUX.3 — photoreal and typography
Grok Imagine 2.0New
grok-imagine-2-0
xAI's fast, characterful image model
Voice
Music
Text & roleplay
Speech-to-text
Compare them head to head
Frequently asked questions
How many AI models does eroq offer?
35 — image and video engines, speech, transcription and roleplay chat. One key, one credit balance for all of them.
Which models are uncensored?
Chat (eroq RP+, eroq RP mini), the Eroq Uncensored, Eroq One and Anima image models, voice, and Motion One and Motion Pro for video — within a written acceptable-use policy. Every eroq-run model also retains nothing upstream, which makes them the ones to pick with Private mode on. The third-party video engines are moderated by their providers.
Do I need a plan to use every model?
No plan is needed for chat, voice, our own image engines and the eroq Motion One, Motion Pro, Seedance 2.0 Mini & Veo 3.1 Lite video engines. Hobby unlocks Veo 3.1 Fast, Kling 3.0, Seedance 2.0 Fast, Hailuo 3 Max & Wan 3.0 and Flux 3 Image & Grok Imagine 2.0; Creator and above unlock Seedance 2.5, Veo 3.1, Kling 3.0 Pro, Seedance 2.0, Hailuo 3, Runway Gen-4.5 & Grok Imagine, plus GPT Image 2.5 Sunburst, GPT Image 2.5 Flare, Nano Banana 2.1, Seedream 5.0 Pro & Nano Banana Pro.
How are models priced?
Flat credits per call for chat (1–3), images (10), speech (2–3 per 100 characters) and transcription (1 per minute of audio). Video is priced per second of clip by engine, resolution and sound — from 7 credits a second (eroq Motion One) to 329 (Seedance 2.0). Failed generations refund themselves.