Home

Clay Announcements
Clay Support
Discuss Anything
Feedback & Requests
GTM Career Advice
Introduce Yourself
Member Spotlight
Share Content and Events
Share Full-time Jobs
Share Part Time Jobs
Share Tables, Tools, and Workflows

Community Guidelines

Explore Events
Learn Clay here
Clay Cup

Powered by Tightknit

Feedback & Requests

Request for Clay to Integrate LLM Models on TPUs for Faster Research | Clay

Feedback & Requests

Request for Clay to Integrate LLM Models on TPUs for Faster Research

·Feb 13, 2025 09:16 PM·

hello! would love to see Clay have native integrations for LLM models hosted on TPUs/fast inference chips (eg Llama on Cerebras or Groq). Would make some of the deeper research tasks on large lists so much faster!

3 comments

· Sorted by Oldest

Channeled
APP
·
·
Currently, we offer native integrations with several powerful LLM models including OpenAI's GPT models, Google's Gemini Pro, and Anthropic's Claude. These integrations are designed to support various AI tasks including data cleaning, summarization, copywriting, and deeper research tasks.While we don't currently have native integrations for TPU/fast inference chip-hosted models like Llama on Cerebras or Groq, our existing AI integrations provide robust capabilities for research tasks. You can access these models either through our Clay-managed account or by using your own API keys for specific models. Sources: Gemini: Generate text with Google Gemini Use AI integration overview | Documentation | Clay University Prompt Engineering Crash Course [Limitless Research] - Clay University
Channeled
APP
·
·
Is that what you were looking for?
Channeled
APP
·
·
Hi Wes H.! This thread was recently closed by our Support team. If you have a moment, please share your feedback: