semantic-conventions/docs/attributes-registry/llm.md

Large Language Model

• Generic LLM Attributes
  • Request Attributes
  • Response Attributes
  • Event Attributes

Generic LLM Attributes

Request Attributes

Attribute	Type	Description	Examples	Stability
gen_ai.request.max_tokens	int	The maximum number of tokens the LLM generates for a request.	100
gen_ai.request.model	string	The name of the LLM a request is being made to.	gpt-4
gen_ai.request.temperature	double	The temperature setting for the LLM request.	0.0
gen_ai.request.top_p	double	The top_p sampling setting for the LLM request.	1.0
gen_ai.system	string	The name of the LLM foundation model vendor.	openai

gen_ai.system has the following list of well-known values. If one of them applies, then the respective value MUST be used; otherwise, a custom value MAY be used.

Value	Description	Stability
openai	OpenAI

Response Attributes

Attribute	Type	Description	Examples	Stability
gen_ai.response.finish_reasons	string[]	Array of reasons the model stopped generating tokens, corresponding to each generation received.	[stop]
gen_ai.response.id	string	The unique identifier for the completion.	chatcmpl-123
gen_ai.response.model	string	The name of the LLM a response was generated from.	gpt-4-0613
gen_ai.usage.completion_tokens	int	The number of tokens used in the LLM response (completion).	180
gen_ai.usage.prompt_tokens	int	The number of tokens used in the LLM prompt.	100

Event Attributes

Attribute	Type	Description	Examples	Stability
gen_ai.completion	string	The full response received from the LLM. [1]	[{'role': 'assistant', 'content': 'The capital of France is Paris.'}]
gen_ai.prompt	string	The full prompt sent to an LLM. [2]	[{'role': 'user', 'content': 'What is the capital of France?'}]

[1]: It's RECOMMENDED to format completions as JSON string matching OpenAI messages format

[2]: It's RECOMMENDED to format prompts as JSON string matching OpenAI messages format