AirCubeAirCube
Core Concepts

Models

All available AI models on AirCube with their slugs, tasks, and pricing.

AirCube provides access to 55+ AI models through a unified API. Each model is identified by a slug that you include in the request URL.

Programmatic discovery

Get the full model list at runtime:

curl https://aircube.ai/api/v3/models \
  -H "Authorization: Bearer $AIRCUBE_API_KEY"

Returns every model's slug, tasks, type, and price_from_usd. See List Models for the full reference.

URL format

POST https://aircube.ai/api/v3/{model-slug}/{task}

Example:

POST https://aircube.ai/api/v3/seedream-v5.0-pro/text-to-image
POST https://aircube.ai/api/v3/seedance-2.0/image-to-video
POST https://aircube.ai/api/v3/qwen3-tts/text-to-speech

Image models

SlugNameTasksFrom
seedream-v5.0-proSeedream 5.0 Protext-to-image, image-to-image$0.045
seedream-v5.0-liteSeedream 5.0 Litetext-to-image, image-to-image$0.04
seedream-v4.5Seedream 4.5text-to-image, image-to-image$0.04
gpt-image-2GPT Image 2text-to-image, image-to-image$0.01
gpt-image-1.5GPT Image 1.5text-to-image, image-to-image$0.01
gpt-image-1GPT Image 1text-to-image, image-to-image$0.02
gemini-3-pro-imageGeminitext-to-image, image-to-image$0.038
gemini-2.5-flash-imageGeminitext-to-image, image-to-image$0.038
qwen-imageQwen Image 2.0text-to-image, image-to-image$0.02
qwen-image-2.0Qwen Image 2.0text-to-image, image-to-image—
qwen-image-2.0-proQwen Image 2.0 Protext-to-image, image-to-image—
nano-banana-proNano Banana Protext-to-image, image-to-image$0.15
nano-banana-2Nano Banana 2text-to-image, image-to-image—
nano-bananaNano Bananatext-to-image, image-to-image—
wan-2.7Wan 2.7text-to-image, image-to-image, text-to-video, image-to-video$0.04
flux-kontextFlux Kontextimage-to-image$0.05
flux-1.1Flux 1.1text-to-image$0.04
z-imageZ-Imagetext-to-image$0.01
z-image-turboZ-Imagetext-to-image, image-to-image$0.01
sdxlSDXLtext-to-image$0.02

Video models

SlugNameTasksFrom
seedance-2.5Seedance 2.5text-to-video, image-to-video, reference-to-video, video-to-video, video-extend$0.76
seedance-2.0Seedance 2.0text-to-video, image-to-video, reference-to-video, video-to-video, video-extend$0.48
seedance-2.0-fastSeedance 2.0 Fasttext-to-video, image-to-video, reference-to-video, video-to-video, video-extend$0.26
seedance-2.0-miniSeedance 2.0 Minitext-to-video, image-to-video, reference-to-video, video-to-video, video-extend$0.14
happyhorse-1.0HappyHorse 1.0text-to-video, image-to-video$0.40
kling-v3.0-stdKling 3.0text-to-video, image-to-video$0.50
kling-v3.0-proKling 3.0text-to-video, image-to-video$0.50
kling-v3.0-4kKling 3.0text-to-video, image-to-video$0.50
kling-v2.6-proKling 2.1text-to-video, image-to-video$0.35
kling-v2.6-stdKling 2.1text-to-video, image-to-video$0.35
kling-v2.1-i2v-proKling 2.1image-to-video$0.35
kling-v2.1-i2v-standardKling 2.1image-to-video$0.35
kling-v2.1-i2v-masterKling 2.1image-to-video$0.35
veo3.1Veo 3.1text-to-video, image-to-video, reference-to-video, video-extend$1.20
veo3.1-fastVeo 3.1 Fasttext-to-video, image-to-video, video-extend$0.60
veo3.1-liteVeo 3.1image-to-video$1.20
hailuo-2.3Hailuo 02image-to-video$0.30
hailuo-02Hailuo 02text-to-video, image-to-video$0.30
luma-ray-2Luma Ray 2text-to-video, image-to-video$1.00
wan-2.6Wan 2.6text-to-video, image-to-video, reference-to-video$0.50
wan-2.5Wan 2.5image-to-video$0.25
wan-2.2-spicyWan 2.2 Spicyimage-to-video, video-extend$0.20
minimax-h3-spicyMiniMax H3 Spicytext-to-video, image-to-video, reference-to-video$0.56
sora-2Sora 2text-to-video, image-to-video—
sora-2-proSora 2text-to-video, image-to-video—
q3Vidu Q3 Protext-to-video, image-to-video$0.43
q3-turboVidu Q3 Proimage-to-video$0.43

Audio models

SlugNameTasksFrom
eleven-v3ElevenLabs v3text-to-speech$0.05
multilingual-v2ElevenLabs Multilingualtext-to-speech$0.05
qwen3-ttsQwen3 TTStext-to-speech$0.05
speech-2.6-hdMiniMax Speech 2.6text-to-speech$0.05
music-2.5MiniMax Music 2.5text-to-music$0.15
ace-step-1.5ACE-Step 1.5text-to-music$0.01
elevenlabs-musicElevenLabs Musictext-to-music$0.40

Face Swap

SlugNameEndpoint
face-swapFace SwapSee Face Swap API

Task types

The task in the URL tells the API what to generate:

TaskDescriptionKey parameters
text-to-imageImage from textprompt, aspect_ratio, resolution
image-to-imageEdit/transform an imageprompt, image, resolution
text-to-videoVideo from textprompt, duration, resolution
image-to-videoAnimate a still imageimage, prompt, duration
reference-to-videoVideo from reference mediaprompt, reference_images, reference_videos
video-to-videoTransform a videoprompt, image (video URL)
video-extendExtend video durationimage (video URL), duration
text-to-speechSpeech from textprompt, voice
text-to-musicMusic from textprompt, duration

See Submit Generation for the full parameter reference per task.

Pricing

Prices vary by model, resolution, and duration. The "From" column shows the lowest per-generation price. For the full pricing grid, visit the pricing page.

Credits are charged at submission. Failed generations are automatically refunded.

On this page