base_url at their endpoint, so the OpenInference OpenAI instrumentor traces them the same way it traces OpenAI itself. One setup covers all of them.
Setup
1
Install the instrumentor and the OTLP exporter
2
Point the exporter at AgentMark and instrument OpenAI
Use your AgentMark API key and app id from project settings.
3
Point the OpenAI client at your provider
Set
base_url to the provider’s endpoint and use the client as usual. Each call arrives in AgentMark as a span. See Traces and logs.Common endpoints
Any provider with an OpenAI-compatible chat completions endpoint works the same way.
What AgentMark captures
These calls produce the same OpenInference spans as a direct OpenAI call. AgentMark maps model, token usage, input and output messages, tool calls, and span kind onto its normalized trace fields, and token counts feed cost tracking. See OpenInference for the full attribute mapping.Next steps
OpenAI
The direct OpenAI provider page
Traces and logs
Explore traces once they arrive
Have questions?
Reach out any time:
- Email the team at hello@agentmark.co for support
- Schedule an Enterprise Demo to learn about AgentMark’s business solutions