In the appsText to image
Krea
KreaKrea 2 Turbo
A prompt, a style and an aspect ratio in. A finished image out.
Pictured: An astronaut, the visor reflecting a planet, made with Krea 2 Turbo
Model catalogue
Every model, one key
329 models from 40 makers, each at its own address — one key, one balance of credits, the same job states.
- Running now
- 329
- Makers
- 40
Tencent
OpenAI
ByteDance
Google
Kling AI329 models
With something to show 42
ImageIn the apps
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
VideoIn the apps
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
AudioIn the apps
3DIn the apps
Image
Alibaba
Qwen-Image-2.0
Unified image generation and editing with professional text rendering
Text to image
Image
Alibaba
Wan2.7 Image Pro
Premium image generation with enhanced composition stability and precise prompt comprehension
Text to image
Image
![Coastal Radar Station Rental Interior, made with FLUX.1 [dev]](/gallery/bfl-flux-1-dev.webp)
Image
![Coastal Floodgate Winter Lighting Visualization, made with FLUX.1 Kontext [dev]](/gallery/bfl-flux-1-kontext-dev.webp)
Image
Black Forest Labs
FLUX.1 Kontext [dev]
Open image editing model for fast iterative workflows
Image to image
![Rooftop Beekeeping Suit Try-On, made with FLUX.1 Kontext [max]](/gallery/bfl-4-1.webp)
Image
Black Forest Labs
FLUX.1 Kontext [max]
High fidelity FLUX.1 Kontext max for precise image edits
Image to image
![Subsea Cable Engineer Editorial Portrait, made with FLUX.1.1 [pro]](/gallery/bfl-2-1.webp)
Image
![Converted Bowling Alley Office Interior, made with FLUX.1.1 [pro] Ultra](/gallery/bfl-2-2.webp)
Image
Black Forest Labs
FLUX.1.1 [pro] Ultra
High speed 4MP FLUX image generation for production apps
Text to image
And on the same key 287
AurayIn the apps
DeepSeek V4.1 Flash
AurayIn the apps
GLM-5.3 Flash
AurayIn the apps
Kimi K3
Alibaba
HappyHorse 1.1
Multimodal video generation with stronger motion expressiveness, multi-image reference consistency, and improved audio-visual sync
Alibaba
HappyHorse-1.0
Text-to-video and image-to-video model with 1080p output and short-form clip control
Alibaba
Qwen-Image-3.0
Unified image generation and editing that balances visual quality, layout fidelity, and response speed
Alibaba
Qwen-Image-3.0-Pro
High-control image generation and editing for dense layouts, small text rendering, and multilingual visual design
Alibaba
Qwen2.5-VL-3B-Instruct
Instruction-tuned vision-language model for image and text understanding
Alibaba
Qwen3-TTS 1.7B Base
High-quality multilingual text-to-speech with voice cloning and ultra-low latency
Alibaba
Qwen3-TTS 1.7B CustomVoice
Text-to-speech with preset premium timbres and precise style control
Alibaba
Qwen3-TTS 1.7B VoiceDesign
Text-to-speech with voice creation from natural language descriptions
Alibaba
Wan2.7
Multimodal video generation with reference consistency, video editing, and native audio
Alibaba
Wan2.7 Image
Unified image generation and editing with avatar customization, color control, and multilingual text rendering
Alibaba
Wan3.0
All-in-one multimodal video generation with native 30-second clips, large reference capacity, and precise video editing
Alibaba
Wan3.0 Prime
Lower-latency Wan3.0 video generation with the same multimodal workflows and output quality
Anthropic
Claude Fable 5
Frontier multimodal agentic model for long-horizon coding, research, and complex professional work
Anthropic
Claude Haiku 4.5
Fast multimodal language model for low-latency agents and scaled reasoning workloads
Anthropic
Claude Opus 4.7
Frontier multimodal reasoning model for advanced coding, long-running agents, and complex knowledge work
Anthropic
Claude Opus 4.8
Frontier multimodal reasoning model for advanced coding, agent systems, and long-context knowledge work
Anthropic
Claude Sonnet 4.6
Versatile multimodal language model for coding, agents, computer use, and production reasoning
Baidu
ERNIE-Image
General-purpose 8B text-to-image model with strong instruction following, text rendering, and structured layout control
Baidu
ERNIE-Image-Turbo
Distilled 8-step ERNIE image variant for faster generation with strong aesthetics and efficient prompting
Black Forest Labs
FLUX 3 Video
Multimodal video generation with native synchronized audio across styles and modes
Black Forest Labs
FLUX Video Upscale
FLUX-powered video upscaling with precise and creative enhancement modes
Black Forest Labs
FLUX Virtual Try-On
Low-latency virtual try-on for transferring garments onto a person image with strong identity and garment fidelity
Want them as one table? Models by task in the API reference lists every address by what it makes.
One key for all of them
Pick any of them in the app, or call its address from your own code — one key, one balance of credits.