# Model Serving - Preview 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 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.

# Preview Models

Input and Output (Credits/M Tokens): credits per million tokens. Context window: maximum tokens per API call. Disposition: what happens to the model once its preview ends. A --- means the value is not available yet for this model.

# Reasoning

Models for deliberate, step-by-step thinking and chain-of-thought tasks.

Model Name	Health	Version	Preview End Date	Disposition	Model	License type	Input (Credits/M Tokens)	Output (Credits/M Tokens)	Context window	Description
`inference-glm5-preview`	---	5.3	16.11.2026	Production Hosting	zai-org/GLM-5.3	GLM 5.3 License	1.1667	3.6667	131K	Open-weight successor to GLM 5.2 (753B parameters; same base model, post-training gains). Optimized for complex coding and long-horizon agentic tasks, with stronger software-engineering and terminal performance than GLM 5.2.

# Multimodal

Vision-language models for image understanding, analysis, and text generation from visual input.

Model Name	Health	Version	Preview End Date	Disposition	Model	License type	Input (Credits/M Tokens)	Output (Credits/M Tokens)	Context window	Description
`inference-kimi-k3-preview`	---	3	16.11.2026	Not Planned for Hosting	moonshotai/Kimi-K3	Kimi K3 License	---	---	512K	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.
`inference-deepseek-v4-flash-preview`	---	4.1	16.11.2026	Production Hosting	deepseek-ai/DeepSeek-V4.1-Flash-1017	MIT License	0.2500	1.0000	1M	High-performance, multimodal Mixture-of-Experts (MoE) model optimized for advanced reasoning, coding, agentic workflows and long-context processing.

maas ai model serving preview