Every model, one key

Alibaba

Qwen3.8 2.4T

Text to text·qwen3-8

In the AI Director: writes Indonesian well · plans up to 24 shots at a time

DeepSeek

DeepSeek V4.1 Flash

Text to text·deepseek-v4-1-flash

In the AI Director: writes Indonesian well · plans up to 30 shots at a time

Krea

2 Turbo · auray-ai/krea-2-turbo/text-to-image

A prompt, a style and an aspect ratio in. A finished image out.

Text to image·auray-ai/krea-2-turbo/text-to-image

Text → Image

Priced per image

MiniMax

H3 · auray-ai/minimax-h3/text-to-video

A scene in. Video with its own audio out, 768p at 24 fps.

Text to video·auray-ai/minimax-h3/text-to-video

Text → Video · Story · First frame +1

Priced by clip length

MiniMax

H3 V2

Text to video·auray-ai/minimax-h3-v2/text-to-video

Text → Video · References

Priced by clip length

MiniMax

Music 3

Words and a mood in. A full song with vocals out, 44.1 kHz stereo.

Text to audio·auray-ai/minimax-music-3/text-to-audio

Song · Instrumental · Cover / remix

Priced per second it makes

Moonshot AI

Kimi K3

Text to text·kimi-k3

Tencent

Hunyuan3D Omni

One image in. A textured, rigged mesh out.

Image to 3D·auray-ai/hunyuan-3d/image-to-3d

3D from image · Rigged character · Guided 3D

Priced by quality tier

Z.ai

GLM-5.3

Text to text·glm-5-3

Z.ai

GLM-5.3 Flash

Text to text·glm-5-3-flash

In the AI Director: writes Indonesian well · plans up to 24 shots at a time

Alibaba

HappyHorse 1.1

Multimodal video generation with stronger motion expressiveness, multi-image reference consistency, and improved audio-visual sync

Text to video·auray-serverless/alibaba/happyhorse-1-1

Text → Video

Priced per second it makes

Alibaba

HappyHorse-1.0

Text-to-video and image-to-video model with 1080p output and short-form clip control

Text to video·auray-serverless/alibaba/happyhorse-1-0

Text → Video · Edit video

Priced per second it makes

Alibaba

Qwen-Image

Qwen-Image high fidelity text aware image generation model

Text to image·auray-serverless/alibaba-qwen-image

Text → Image · Image → Image · Repaint area +1

Priced per megapixel

Alibaba

Qwen-Image-2.0

Unified image generation and editing with professional text rendering

Text to image·auray-serverless/alibaba/qwen-image-2-0

Text → Image · Edit & combine

Priced per megapixel

Alibaba

Qwen-Image-2.0-Pro

Enhanced image generation and precision editing for professional workflows

Text to image·auray-serverless/alibaba/qwen-image-2-0-pro

Text → Image · Edit & combine

Priced per megapixel

Alibaba

Qwen-Image-3.0

Unified image generation and editing that balances visual quality, layout fidelity, and response speed

Text to image·auray-serverless/alibaba/qwen-image-3-0

Text → Image · Edit & combine · Split into layers

Priced per megapixel

Alibaba

Qwen-Image-3.0-Pro

High-control image generation and editing for dense layouts, small text rendering, and multilingual visual design

Text to image·auray-serverless/alibaba/qwen-image-3-0-pro

Text → Image · Edit & combine

Priced per megapixel

Alibaba

Qwen-Image-Edit

High fidelity text guided image editing for Qwen

Image to image·auray-serverless/alibaba-qwen-image-edit

Edit & combine

Priced per megapixel

Alibaba

Qwen-Image-Edit-2511

Advanced instruction-driven image editing model

Image to image·auray-serverless/alibaba/qwen-image-edit-2511

Edit & combine

Priced per megapixel

Alibaba

Qwen-Image-Edit-Plus

Advanced multi image editing with precise ControlNet guidance

Image to image·auray-serverless/alibaba-qwen-image-edit-plus

Edit & combine

Priced per megapixel

Alibaba

Qwen3-TTS 1.7B Base

High-quality multilingual text-to-speech with voice cloning and ultra-low latency

Audio to audio·auray-serverless/alibaba/qwen-3-tts-1-7b-base

Voice clone

Priced per character

Alibaba

Qwen3-TTS 1.7B CustomVoice

Text-to-speech with preset premium timbres and precise style control

Text to audio·auray-serverless/alibaba/qwen-3-tts-1-7b-customvoice

Text → Speech

Priced per character

Alibaba

Qwen3-TTS 1.7B VoiceDesign

Text-to-speech with voice creation from natural language descriptions

Text to audio·auray-serverless/alibaba/qwen-3-tts-1-7b-voicedesign

Text → Speech

Priced per character

Alibaba

Wan2.5-Preview

Wan2.5-Preview AI Text to Video with Native Audio

Text to video·auray-serverless/alibaba-wan2-5-preview

Text → Video · First frame · Audio → Video

Priced per megapixel-second