LiquidMetal AI empowers developers to build full-stack, agentic applications at scale using its Raindrop framework. Customers leverage plain English to create production-ready, interactive AI apps in hours — not weeks. The platform includes a global-edge AI network with stateless workers, integrates major cloud providers, and delivers infrastructure capable of supporting 100,000 users within five minutes of launch.

Through an intelligent MCP server, LiquidMetal AI orchestrates AI CLIs, like Claude Code or Gemini, to transform user specifications into functional applications. The system dynamically selects optimal models based on performance, cost, and accuracy needs (e.g., prioritizing speed for real-time interactions or cost-efficiency for batch processing) while abstracting technical complexities.

Challenge:

Supporting diverse customer use cases requires LiquidMetal AI to operate seamlessly across models ranging from 7B to 300B+ parameters. Delays in response directly impact user adoption and revenue, making latency and scalability non-negotiable.

Solution:

LiquidMetal AI partnered with SambaNova to deliver consistent high performance across all model sizes. SambaCloud’s OpenAI-compatible API enables effortless integration of open-source models, ensuring speed and reliability for every application.

Running on SambaCloud, large, powerful models such as DeepSeek make it possible for LiquidMetal AI to quickly build production-ready applications based on customer requirements. These are fully capable applications that are ready for release in only hours.

Once the applications are built, the high-speed inference of SambaCloud provides LiquidMetal AI customers with the performance they need to power their applications using the best and largest open-source models, to meet user expectations, and to scale to any demand.