PrivateCloud AI model catalog

Run Every AI Model

Fast, economical, private, and secure. No subscriptions, no restrictions.

Browse models Learn more
Models
1023
Providers
45
Categories
25

Everything in one catalog

Find the right model faster with search, filters, and direct access to the console.

Browse across providers View different model families in one organized catalog.
Filter by type and provider Narrow the list quickly to find the model that fits your task.
Open the console instantly Click any model card to jump into the endpoint console.
Use saved subsets Switch between all models, recommended models, and favorites.

Find the right model faster

A clear path from discovery to selection to console access.

Search, filter, and launch
Discover

Start with a single catalog that brings models together in one place.

Compare

Use search and filters to narrow down providers, categories, and model families.

Launch

Open the model console directly from the catalog when you are ready to use it.

Featured models

A quick starting point for exploring the catalog.

Click any card to continue
wavespeed-ai/wan-2.2/animate-2
wavespeed-ai motion-control
Wan 2.2 Animate 2 is the next-generation Wan character animation model: an end-to-end DiT that makes the character in a reference image perform the motion of a driving video, with no pose extraction, prompt-controlled background, and strong identity preservation; generates 480p/720p videos up to 120s. Ready-to-use REST inference API, best performance, no coldstarts.
wavespeed-ai/qwen3-tts/voice-clone
wavespeed-ai audio-to-audio
Qwen3 TTS Voice Clone: Clone any voice from a reference audio and generate speech in that voice. Ready-to-use REST inference API, best performance, no cold starts.
openai/gpt-image-2/text-to-image
openai text-to-image
OpenAI's GPT Image 2 Text-to-Image generates high-quality images from natural-language prompts. Ready-to-use REST inference API, best performance, no coldstarts.
alibaba/wan-2.7/image-to-video-spicy
alibaba image-to-video
Alibaba WAN 2.7 Spicy converts images into unlimited high-quality videos with smooth animations optimized for scalable content generation. Ready-to-use REST inference API, best performance, no cold starts.
alibaba/wan-3.0/text-to-video
alibaba text-to-video
Alibaba WAN 3.0 Text-to-Video generates videos from text prompts with flexible 2-30 second duration, resolution, aspect ratio, audio, and deep-thinking controls. Ready-to-use REST inference API, best performance, no cold starts.
kwaivgi/kling-v3.0-std/motion-control
kwaivgi motion-control
Kling 3.0 Standard delivers top-tier video-to-video generation with smooth motion, cinematic visuals, accurate prompt adherence, and native audio for ready-to-share clips. Ready-to-use REST inference API, best performance, no cold starts.

Explore the full catalog

Search, filter, and open the console for any model.

Live catalog
Separate terms with commas, then choose whether every term must match or any term can match.
Showing: 0
Total: 1023
Providers
alibaba
50
black-forest-labs
9
bria
24
bytedance
79
character-ai
2
chatterbox
2
clarity-ai
5
decart
2
elevenlabs
12
google
48
heygen
2
hitem3d
2
hyper3d
4
ideogram-ai
12
inworld
3
kwaivgi
73
leonardoai
1
lightricks
5
luma
16
meshy
3
meta
2
microsoft
5
midjourney
2
minimax
38
mirelo-ai
6
mureka-ai
20
nvidia
8
openai
16
pika
7
pixverse
27
pruna-ai
14
recraft-ai
22
reve
3
runwayml
5
skywork-ai
3
sonilo
6
sourceful
2
sync
6
topaz
4
tripo3d
6
veed
4
vidu
39
wavespeed-ai
407
x-ai
15
z-ai
2
Types
ai-remover
16
audio-to-audio
15
audio-to-video
3
content-moderation
5
digital-human
41
image-to-3d
23
image-to-image
142
image-to-text
18
image-to-video
205
llm
7
lora-support
65
motion-control
14
portrait-transfer
11
speech-to-text
12
text-to-3d
8
text-to-audio
66
text-to-image
135
text-to-video
107
training
13
upscaler
23
video-dubbing
12
video-effects
6
video-extend
24
video-to-text
7
video-to-video
45
Ratings
G
0
PG
0
R
0
XXX
209

Models

Click a model card to open the endpoint console.

No filters