Seedance 2.0 is live on the API — view the model →

Browse 1,000+ AI models

Image, video, audio, 3D and avatar models — every one available through a single unified API and one key. Try any model in the browser, then ship it with one REST call. New accounts get free starter credits, no card required.

text-to-image
runweave-ai / ernie-image / text-to-image
$0.0300

Baidu ERNIE Image generates high-quality images from text prompts in English, Chinese, and Japanese, with flexible sizing and LLM-enhanced prompt expansion.

text-to-image
runweave-ai / ernie-image / text-to-image-turbo
$0.0300

Baidu ERNIE Image Turbo is a distilled, 8-step version of ERNIE Image for fast, low-cost generation. Supports English, Chinese, and Japanese prompts with flexible sizing.

text-to-image
runweave-ai / nucleus-image / text-to-image
$0.0100

Baidu ERNIE Image generates high-quality images from text prompts in English, Chinese, and Japanese, with flexible sizing and LLM-enhanced prompt expansion.

image-to-image
runweave-ai / patina / image-to-map
$0.0600

PATINA generates seamless high-resolution PBR material maps (basecolor, normal, roughness, metalness, height) from a single image, ready for use in Unreal, Unity, Blender, and other 3D pipelines.

text-to-image
runweave-ai / patina / material
$0.4800

PATINA Material generates complete seamlessly tiling PBR material sets (basecolor, normal, roughness, metalness, height) from text prompts — perfect for game engines, 3D rendering, and material libraries.

image-to-image
runweave-ai / patina / material-extract
$1.0200

PATINA Material Extract turns any photograph or reference image into a complete seamlessly tiling PBR material set (basecolor, normal, roughness, metalness, height), guided by a text prompt.

video-to-video
runweave-ai / void-video-inpainting / mask
$0.0500

Baidu ERNIE Image generates high-quality images from text prompts in English, Chinese, and Japanese, with flexible sizing and LLM-enhanced prompt expansion.

speech-to-text
nvidia / nemotron-3-nano-omni / audio
$0.0100

NVIDIA Nemotron 3 Nano Omni is an open, efficient reasoning model for enterprise agentic workflows, built on a 30B A3B hybrid Transformer-Mamba MoE architecture.

llm
nvidia / nemotron-3-nano-omni / text
$0.0100

NVIDIA Nemotron 3 Nano Omni is an open, efficient reasoning model for enterprise agentic workflows, built on a 30B A3B hybrid Transformer-Mamba MoE architecture.