Comparison
Span vs Tracing
Span and Tracing are both common AI/LLM terms but cover different ideas. Here is a quick side-by-side.
When you would reach for Span
Span comes up when the question is fundamentally about infrastructure.
An LLM span: model=gpt-4o, input=system+user msgs, output=response text, tokens_in=820, tokens_out=410, latency=1.8s, cost=$0.0061.
When you would reach for Tracing
Tracing comes up when the question is fundamentally about infrastructure.
A trace showing: user_query → retrieve(top_k=5) → rerank → completion(gpt-4o) with each step's tokens, latency, and content visible.
Frequently asked
What is the difference between Span and Tracing?
Span: A span is a single unit of work within a trace — one LLM call, one tool call, one retrieval — with a start time, end time, attributes (model, tokens, cost), and a parent span that links it into the trace tree. Tracing: Tracing captures the full causal tree of an LLM request — the user input, retrieval calls, tool calls, intermediate prompts, and the final response — as a hierarchy of timed spans you can replay and inspect.
When should I use Span vs Tracing?
Span is the right concept when you are focused on infrastructure. Tracing applies when you are focused on infrastructure.
Are Span and Tracing the same thing?
No. Span is infrastructure; Tracing is infrastructure. They are related but address different parts of the AI stack.