Core Concepts
Models
Browse the AI models available through the AirCube API and learn how to use them.
AirCube provides access to 87+ AI models through a unified API. Each model is identified by a slug that you include in the request URL.
URL format
POST https://aircube.ai/api/v3/{model-slug}/{task}For models with provider-scoped variants:
POST https://aircube.ai/api/v3/{provider}/{model}/{task}Image models
| Model slug | Display name | Supported tasks |
|---|---|---|
seedream-v5.0-pro | Seedream 5.0 Pro | text-to-image |
gpt-image-2 | GPT Image 2 | text-to-image |
flux-1.1 | Flux 1.1 | text-to-image |
flux-2-klein | Flux 2 Klein | text-to-image |
qwen-image | Qwen Image 2.0 | text-to-image |
qwen-image/edit-2511 | Qwen Image Edit 2511 | image-editing |
recraft-v3 | Recraft V3 | text-to-image |
ideogram-v3 | Ideogram V3 | text-to-image |
Video models
| Model slug | Display name | Supported tasks |
|---|---|---|
seedance-2.0 | Seedance 2.0 | text-to-video, image-to-video |
kling-v3.0-std | Kling 3.0 | text-to-video, image-to-video |
veo3.1 | Veo 3.1 | text-to-video |
sora-2 | Sora 2 | text-to-video, image-to-video |
wan-2.1 | Wan 2.1 | text-to-video, image-to-video |
hailuo-v2 | Hailuo V2 | text-to-video, image-to-video |
luma-ray-2 | Luma Ray 2 | text-to-video, image-to-video |
Audio models
| Model slug | Display name | Supported tasks |
|---|---|---|
eleven-v3 | ElevenLabs v3 | text-to-speech |
qwen3-tts | Qwen3 TTS | text-to-speech |
music-2.5 | MiniMax Music 2.5 | text-to-music |
Special models
| Model slug | Display name | Endpoint |
|---|---|---|
face-swap | Face Swap | See Face Swap API |
How task types work
The task segment in the URL tells the API what kind of generation to perform. It also determines the output type:
| Task contains | Output type |
|---|---|
video | video |
audio, music, speech, tts | audio |
| anything else | image |
Common task types include:
text-to-image— generate an image from a text promptimage-to-image— transform an existing imageimage-editing— edit specific parts of an imagetext-to-video— generate a video from a text promptimage-to-video— animate a still image into a videoreference-to-video— generate a video using reference mediatext-to-speech— synthesize speech from texttext-to-music— generate music from a text prompt
Browse all models
The tables above show a selection of popular models. For the complete list with real-time availability and pricing, visit the model catalog and pricing page.