# Model Serving - Sandbox Models

This is the list of AI models we are currently testing and evaluating. Models listed here are not yet generally available, but they are being validated for performance, stability, and cost. Once a model passes our evaluation, it will be promoted to the Active Models list.

These are models we are looking into and considering for the production catalog. They are available on a trial basis with no SLA. Pricing and throughput may not be listed yet for models that have not been fully tested; where figures are shown, they are preliminary and may change before promotion to Active Models.

For explanations of recent additions and removals, see the Changelog.

# Sandbox Models

Model	Type	Description
moonshotai/Kimi-K3	Multimodal	Open-weight multimodal agentic model (2.8T parameters, 104B activated) optimized for long-horizon coding, agentic knowledge work, and reasoning. Native text, image, and video support with a 1-million-token context window.
MiniMaxAI/MiniMax-H3	Multimodal	Omni-modal generative system for unified text, image, video, and audio understanding. Generates video with native stereo audio at up to 2K resolution and 4–15 second durations. Supports text-to-video, first/last-frame-to-video, and reference-to-video workflows.

maas ai model serving sandbox