How do I move to production?
Overview of the process to your fully managed LLM API key so you can run inference in production
To deploy an LLM into production through Konko AI's fully managed service follow these steps:
Step #1: submit your requirements - fill out this Production Deployment Request with your requirements (this usually takes no more than 5 min)
Step #2: set-up call with Konko AI - to clarify outstanding questions on your production requirements (scheduling link)
From there your Konko AI team will set-up your production deployment in-line with your security, privacy, throughput and latency requirements.
Once set-up we will securely share your production deployment API-key with you.
Quick links
Updated 8 months ago
What’s Next