DeepSeek-R1-0528 Now Supports AI Function Calling on SambaCloud
DeepSeek-R1-0528 introduces function calling on SambaCloud, enhancing AI agents' ability to execute tasks efficiently with predefined tools and fast inference speeds.
SambaNova Systems has announced that DeepSeek-R1-0528, a leading open-source reasoning model, now supports function calling on its SambaCloud platform. This enhancement allows AI agents to execute predefined tools dynamically, improving real-world task automation and complex problem-solving capabilities.
What is DeepSeek-R1-0528?
DeepSeek-R1-0528 is the latest checkpoint of DeepSeek R1, originally released in January. This version significantly upgrades reasoning performance—comparable to proprietary models like OpenAI and Gemini—while adding function calling, which was absent in the original release. The model leverages reinforcement learning to enhance response accuracy, making it ideal for coding, scientific reasoning, and multi-step planning.
The Power of AI Function Calling
Function calling bridges AI models with real-world actions by enabling dynamic execution of predefined tools via APIs. This allows AI agents to:
- Fetch live data (e.g., weather, stock prices).
- Update databases.
- Control external systems.
How to Use Function Calling on SambaCloud
The process is streamlined into five steps:
- Log in to SambaCloud.
- Define function schemas in JSON.
- Configure function calls in API requests.
- Execute functions using provided parameters.
- Pass results back to the model.
The article includes a Python code example demonstrating weather data retrieval via function calling.
Integrating with CrewAI for Agentic Workflows
Partnership with CrewAI—an open-source framework for autonomous AI agents—enables advanced multi-agent collaboration. Example use cases include:
- Data scraping and analysis.
- Content generation with dynamic research.
python from crewai import Agent, Task, Crew from crewai_tools import DirectoryReadTool, FileReadTool
Related News
AWS extends Bedrock AgentCore Gateway to unify MCP servers for AI agents
AWS announces expanded Amazon Bedrock AgentCore Gateway support for MCP servers, enabling centralized management of AI agent tools across organizations.
CEOs Must Prioritize AI Investment Amid Rapid Change
Forward-thinking CEOs are focusing on AI investment, agile operations, and strategic growth to navigate disruption and lead competitively.
About the Author

David Chen
AI Startup Analyst
Senior analyst focusing on AI startup ecosystem with 11 years of venture capital and startup analysis experience. Former member of Sequoia Capital AI investment team, now independent analyst writing AI startup and investment analysis articles for Forbes, Harvard Business Review and other publications.