Choose the model
CutPro's full catalog of AI models: text, embeddings, image, video, voice, music, sound, avatars, 3D and tools, with prices and what each takes.
Every model CutPro runs is in GET /models: chat models (Claude, GPT, Gemini, Grok, DeepSeek, Qwen, Llama, Mistral and more), embeddings, image, video, voice, music, sound effects, talking avatars, 3D and image and video tools. GET /models/featured lists only the strongest of each kind, for when the user picks none.
curl "https://api.cut.pro/api/v1/models?kind=music" \
-H "X-Api-Key: $CUTPRO_API_KEY"{
"models": [
{
"id": "suno/music-generate",
"name": "Suno Generate Music",
"maker": "suno",
"kind": "music",
"endpoint": "generations",
"featured": false,
"pricing": [{ "unit": "run", "credits": 13.73, "mode": null, "resolution": null, "silent_credits": null, "usd": 0.246, "brl": 0.822 }],
"priced_by_request": true,
"parameters": {
"properties": {
"custom_lyrics": { "type": "boolean" },
"instrumental": { "type": "boolean" },
"version": { "type": "string" },
"style": { "type": "string" },
"lyrics": { "type": "string" }
},
"required": ["custom_lyrics", "instrumental", "version"]
}
}
]
}Narrow it with kind, endpoint, q (part of the id or the name) or id.
| Field | What it is for |
|---|---|
kind | What the model makes: text, embedding, image, video, speech (a voice), music, audio (sound effects, music and audio edits), avatar (a person speaking from a photo and a sound), model3d, tool (edits an image: upscale, remove the background, erase) or videoedit (edits a video). |
endpoint | Where it runs: generations (Generate with AI), chat_completions or embeddings (Chat and embeddings). |
pricing | Credits per unit: image, second, minute, 1k_characters, run (per run), megapixel (of the result; for a video, of every frame) or per million tokens (1m_input_tokens, 1m_output_tokens, 1m_tokens; for a video, its tokens are each frame's pixels divided by 1,024). |
pricing[].usd, pricing[].brl | What that row's credits cost in dollars and in reais, at the cheapest credit pack. null while the price is not available. |
priced_by_request | true when the total depends on the request's fields (length, quality): always read it from POST /generations/quote. |
parameters | The model's extra fields under CutPro's own names (negative_prompt, steps, guidance, style, lyrics and the like), sent in options of POST /generations. prompt, seconds, aspect_ratio, voice, seed, images, sounds and video are placed for you. It works for the curated image, video and voice models too. |
supported_parameters | For a text model, the fields it takes beyond messages, such as reasoning_effort, reasoning, tools and response_format. |
context_length, max_output_tokens | For text models. |
scores | How people rate the model in public blind votes (LMArena and Artificial Analysis), per mode, from 0 to 100: twice its odds of beating the best rated model offered here for that mode, so 100 is level with it and 50 loses three votes in four. A mode no board rates is left out. |
modes, resolutions, seconds, voices and the rest | For the image, video and voice models CutPro curates. |
Public prices, no key
To show a price before someone has a key, or to compare models from a script, GET https://api.cut.pro/public/generations/models returns the image, video and voice models with the price of each unit in credits, dollars and reais, with no authentication. Money is at the cheapest credit pack, and the data is at most five minutes old. The same table is at cut.pro/en/models, with one page per model.
curl "https://api.cut.pro/public/generations/models"Prices can change at any time. Read them from here or, for the exact total of a generation, from POST /generations/quote. Never hard-code a price.
Create AI characters and swap the person in the video
Create a realistic person from traits, face photos or a ready-made character, and put them in any video or product photo.
Generate image, video, voice, music, sound and 3D
Choose a model, confirm the price, generate from text, images, video or sound and use the result in the editor or in a post.