eroq api · image
Pictures your users
are allowed to ask for.
13 models behind one endpoint — photoreal, anime, fast drafts and instruction edits — from 10 credits a render. Reference images hold a face across generations, and what renders is a policy question here, not a filter's.
From 10 credits · failed renders refund themselves
40 free credits on signup · no card required
curl https://eroq.ai/v1/images/generations \
-H "Authorization: Bearer $EROQ_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "eroq-krea2",
"prompt": "portrait of a starship mechanic, grease-stained overalls, warm hangar light, 35mm",
"negative_prompt": "blurry, extra fingers"
}'The models
13 models. Flat prices.
Eroq Uncensored
imageeroq-uncensored
eroq's own uncensored photoreal model: the scene renders as written within the acceptable-use policy, with CFG, in-place editing and up to four reference pictures, fully private.
10 credits / image
Krea2
imageeroq-krea2
Krea 2 is the studio's clean photoreal base: fast turbo sampling, CFG control, up to four reference pictures, in-place editing and a warm render in about fifteen seconds — the everyday character image engine.
10 credits / image
Eroq One
imageeroq-one
Eroq One is the reference engine: generation and plain-language instruction editing from up to ten reference pictures, for consistent characters, scenes and products.
10 credits / image, +1 per extra picture
Anima
imageeroq-anime
Anima renders anime and stylized illustration, uncensored within policy — a two-pass hi-res detail render with CFG and negative-prompt control.
10 credits / image
Flash Image
imageeroq-flash-image
Flash Image is the fast multimodal engine: broad style range and batch support.
10 credits / image
Flux Image
imageeroq-flux-image
Flux Image is the high-fidelity photoreal engine: sharp detail and natural light.
12 credits / image
GPT Image 2.5 Sunburst
imagegpt-image-2-5-sunburst
GPT Image 2.5 Sunburst is OpenAI's flagship image model: strong prompt adherence, clean composition and the sharpest in-image text of the lineup. Text-to-image, five formats, from the Creator plan.
31 credits / image
GPT Image 2.5 Flare
imagegpt-image-2-5-flare
GPT Image 2.5 Flare is OpenAI's expressive image model: the same precision as Sunburst with a bolder, more dramatic rendering for posters, key art and cinematic stills. Text-to-image, five formats, from the Creator plan.
31 credits / image
Nano Banana 2.1
imagenano-banana-2-1
Nano Banana 2.1 is Google's fast multimodal image model: quick, style-flexible renders with strong natural-language understanding. Text-to-image, five formats, from the Creator plan.
31 credits / image
Seedream 5.0 Pro
imageseedream-5-0-pro
Seedream 5.0 Pro is ByteDance's flagship image model: dense detail, rich texture and strong photographic realism. Text-to-image, five formats, from the Creator plan.
36 credits / image
Nano Banana Pro
imagenano-banana-pro
Nano Banana Pro is Google's highest-fidelity image model: the sharpest detail, the most accurate text and the best prompt understanding of the Nano Banana line. Text-to-image, five formats, from the Creator plan.
124 credits / image
Flux 3 Image
imageflux-3-image
Flux 3 Image is Black Forest Labs' latest FLUX: natural photoreal rendering, strong lighting and reliable in-image text. Text-to-image, five formats, from the Hobby plan.
32 credits / image
Grok Imagine 2.0
imagegrok-imagine-2-0
Grok Imagine 2.0 is xAI's image model: quick, characterful renders with a distinct look. Text-to-image, five formats, from the Hobby plan.
32 credits / image
What you get
Image, built for products that ship.
13 engines, one call
Krea2 for clean photoreal, Eroq Uncensored for uncensored photoreal, Eroq One for up to ten references and instruction edits, Anima for anime and illustration, Flash Image for fast drafts and Flux Image for high-fidelity detail — plus OpenAI's GPT Image 2.5, Google's Nano Banana Pro and 2.1, ByteDance's Seedream 5.0 Pro, Black Forest Labs' Flux 3 and xAI's Grok Imagine 2.0. Same request shape for all — the model id is the only thing that changes, and the price follows it.
The same face, twice
Pass a reference photo and the render keeps the likeness. Save one as a Character and every call that mentions it inherits the face, which is the only reliable way to make a character look like themselves across a catalogue.
Inline or hosted
Responses come back as base64 by default, or set store and get a CDN URL instead — useful when the image is headed straight into a feed and you would rather not proxy a megabyte through your own server.
Framed, not cropped
Five aspect ratios render as real compositions rather than a square trimmed after the fact. A 9:16 portrait is composed vertical, which matters when the output is going into a story or a card.
Flat, and refunded
A flat price per model at every size, from 10 to 124 credits an image. A generation that fails refunds itself and the refund lands in your usage ledger, so you are never paying for a blank.
Uncensored, private, no real people
Eroq Uncensored, Eroq One and Anima render uncensored within the written policy, and private: true returns an image once and keeps it nowhere. The hard limits are absolute and enforced at the account level — no minors, no real identifiable people — and a request that crosses one returns content_blocked without a charge.
In the reference
Keep reading
FAQ
The short version.
What does an image cost? +
From 10 to 124 credits depending on the model, the same at every aspect ratio. There is no size surcharge and no token math.
Can I edit an existing photo? +
Yes — on Eroq One, Krea2 and Eroq Uncensored: send the picture as the first reference with edit: true and describe the change. Eroq One keeps the source picture's frame; Krea2 and Eroq Uncensored render the edit at the aspect you ask for, or retain the source ratio.
Which aspect ratios are available? +
1:1, 3:4, 4:3, 9:16 and 16:9. The 21:9 ratio is video only.
Is there an upscaler? +
No. Renders come out at the model's native size, so choose the aspect ratio you need up front rather than planning to enlarge afterwards.
Are generated images kept? +
Yes — every render is saved to your own creation library with the prompt and settings that made it, which is what makes a later remix possible. It is private to your workspace and you can delete any of it.
First call in five minutes.
Sign up, create a key, paste the quickstart. 40 free credits to start, and plans from $15.