INFRA for
AI Creators

New on the API

Change the model name and nothing else. Every price is on the models page.

Image

Qwen-Image 3.0 (Alibaba)

Lettering in Japanese, English and Chinese, in about 6 seconds. Put the words in quotes and say where they go.

Prompt: A park poster in autumn. In the centre, large brush lettering: 「芸術の秋」. Red leaves, soft evening light.

"model": "qwen-image-3.0"

Video

Wan 3.0 / Wan 3.0 Prime (Alibaba)

Video with sound, 2 to 10 seconds, 480p to 1080p. A character reference image keeps the face. Prime is about twice as fast.

Watch the music video made with Wan 3.0 →"model": "wan3.0-video"

POST /v1/chat/completions

Chat

Qwen3.8 Max / Flash (Alibaba)

Max for long context and harder requests, Flash for summaries and volume. Streaming and tool calling as usual.

"model": "qwen3.8-max"

All models and prices →

Samples that run

Speech, text and image, in curl and Python. We run these every week against production, exactly as written here.

curl -X POST https://api.aicu.ai/v1/audio/speech \
  -H "Authorization: Bearer $AICU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "eleven_v4", "voice": "nao", "input": "こんにちは、 AICU です。"}' \
  --output hello.mp3

request bodyCopy

{
  "model": "gpt-image-2.5-flare",
  "character": "luc4",
  "reference_image": "<base64 of one picture of LuC4>",
  "prompt": "Anime style. LuC4: 20-year-old kind boyfriend, round chin, 1boy, solo, male focus, (streaked hair), red short hair with a light highlight streak in the fringe, red eyes, hoodie, short hair, hair between eyes. Scene: sitting at a sunny cafe table, typing a blog post on a laptop, looking up at the viewer with a big encouraging smile and a thumbs-up. Warm bright colors, soft lighting. No text.",
  "size": "1536x1024",
  "quality": "high",
  "visibility": "public"
}

Or hand it to your coding agent

promptCopy

Read https://api.aicu.ai/llms.txt first. Draw LuC4 for my blog post: POST https://api.aicu.ai/v1/images/generations with model "gpt-image-2.5-flare", character "luc4", reference_image = base64 of ./luc4.png, size "1536x1024", quality "high", and the scene I describe next. Use the key in AICU_API_KEY. Save data[0].b64_json as cover.png and print ap_cost.

model

gpt-image-2.5-flare (omit it and you get gpt-image-2; -sunburst is the slower, finer variant). The aliases gpt-image-2.5 and flare also work.

character

Who the picture is of — and who gets credited. A registered slug needs no reference image; your own character's name needs one.

reference_image

One picture of the character, base64. The look comes from here, so the prompt only has to describe the scene.

prompt

The character's official appearance words, then the scene. The reference sets the look; the words keep details like the highlight streak. Write “No text” if you don't want lettering.

size / quality

These set the price: 1536×1024 high is 5,100 AP; 1024×1024 low is 700 AP. Only HTTP 200 is billed.

visibility

public lists the result in the gallery with the credit line. private keeps nothing and costs twice as much.