How to choose the best open model for AI agents based on their task
.svg){kind=icon}
We’ve sent an email with more details, including how to join or access the session. Please check your inbox (and your spam folder just in case).
LLMs are the foundation of AI agents, but as LLMs improve in capabilities and the task complexity of AI agents increases, choosing the right model for individual agents can be challenging. In particular, open models such as DeepSeek provide an incredible opportuntiy to power agents with advanced reasoning at a lower costs and with faster inference.
In this webinar, CrewAI and SambaNova will share how to evaluate open models for agents calling tools and generating content, their experience performing different tasks with different models and recommendations for selecting models based on agent tasks.
- The latest open models, and their capabilities
- How models impact the performance of AI agents
- Choosing models based on agent tasks and output
- Building agents in CrewAI with inference from SambaNova
- How to monitor and manage LLM token costs
Ready to get started?
Manage the full AI agent lifecycle — build, test, deploy, and scale — with a visual editor and ready-to-use tools.
All the power of AMP Cloud, deployed securely on your own infrastructure — on-prem or private VPCs in AWS, Azure, or GCP
An open-source orchestration framework with high-level abstractions and low-level APIs for building complex, agent-driven workflows.
