Model Library
Choose from ready-to-go models -- Or bring your own custom model.
Featured Models
text vision
Kimi K2.6
Kimi K2.6 is an open-source, native multimodal agentic MoE model from Moonshot AI with 1T total parameters, 32B activated
text vision
Qwen3.6 35B A3B
Agentic coding MoE with hybrid Gated DeltaNet and vision support
text vision
Gemma 4 31B IT
Gemma 4 31B dense vision-language model by Google with 256K context and thinking mode
text vision
Qwen3.5 27B
Dense 27B vision-language model with unified multimodal reasoning
video
LTX-2.3
LTX-2.3 is a DiT-based audio-video foundation model with improved quality and prompt adherence for synchronized video and audio
image
FLUX.2 [dev]
Rectified flow transformer capable of generating, editing and combining images based on text instructions
Deploy Custom AI Environments
