You can register agents on Vijil that use NVIDIA NIM models such as nvidia/llama3-chatqa-1.5-8b, nvidia/llama3-chatqa-1.5-70b, and nvidia/nemotron-4-340b-instruct.
Prerequisites
You have an NVIDIA NIM or NVIDIA API account with an active key.
Your account has access to the NIM models you plan to use.
You have access to a Vijil team and permission to manage Keys Agents
Store NVIDIA credentials in Vijil
In Vijil, go to Keys > Add new key
From the Model Hub dropdown, select NVIDIA .
Enter your NVIDIA API key and any optional rate limit overrides you want for this key.
Save the key configuration.
Once saved, this key can be reused across multiple NVIDIA-based agents.
Register an Agent on Vijil With a NVIDIA API key configured, you can register an agent that uses NVIDIA NIM:
Press Register Agent .
Enter an Agent name.
Select NVIDIA as the Hub .
Enter a model name (for example nvidia/llama3-chatqa-1.5-8b). See the NVIDIA NIM documentation for the list of available models.
Select an existing NVIDIA API key you configured earlier, or create a new one.
Add a System Prompt if you want Vijil to send a default system prompt with every request to this agent.
Enterprise If your organization uses enterprise-only features with Vijil:
Add an MCP server URL so the agent can access MCP tools exposed by that server.
Add an A2A Agent Card URL so this agent can participate in agent-to-agent workflows defined in your enterprise.
Last modified on June 13, 2026
