Semantic conventions for generative client AI spans

Status: Development

Spans

Inference

Status:

This span represents a client call to Generative AI model or service that generates a response or requests a tool call based on the input prompt.

Span name SHOULD be {gen_ai.operation.name} {gen_ai.request.model}. Semantic conventions for individual GenAI systems and frameworks MAY specify different span name format and MUST follow the overall guidelines for span names.

Span kind SHOULD be CLIENTand MAY be set to INTERNAL on spans representing call to models running in the same process. It’s RECOMMENDED to use CLIENT kind when the GenAI system being instrumented usually runs in a different process than its client or when the GenAI call happens over instrumented protocol such as HTTP.

Span status SHOULD follow the Recording Errors document.

Attribute	Type	Description	Examples	Requirement Level	Stability
gen_ai.operation.name	string	The name of the operation being performed. [1]	chat; generate_content; text_completion	Required
gen_ai.system	string	The Generative AI product as identified by the client or server instrumentation. [2]	openai	Required
error.type	string	Describes a class of error the operation ended with. [3]	timeout; java.net.UnknownHostException; server_certificate_invalid; 500	Conditionally Required if the operation ended in an error
gen_ai.output.type	string	Represents the content type requested by the client. [4]	text; json; image	Conditionally Required [5]
gen_ai.request.choice.count	int	The target number of candidate completions to return.	3	Conditionally Required if available, in the request, and !=1
gen_ai.request.model	string	The name of the GenAI model a request is being made to. [6]	gpt-4	Conditionally Required If available.
gen_ai.request.seed	int	Requests with same seed value more likely to return same result.	100	Conditionally Required if applicable and if the request includes a seed
server.port	int	GenAI server port. [7]	80; 8080; 443	Conditionally Required If server.address is set.
gen_ai.request.frequency_penalty	double	The frequency penalty setting for the GenAI request.	0.1	Recommended
gen_ai.request.max_tokens	int	The maximum number of tokens the model generates for a request.	100	Recommended
gen_ai.request.presence_penalty	double	The presence penalty setting for the GenAI request.	0.1	Recommended
gen_ai.request.stop_sequences	string[]	List of sequences that the model will use to stop generating further tokens.	["forest", "lived"]	Recommended
gen_ai.request.temperature	double	The temperature setting for the GenAI request.	0.0	Recommended
gen_ai.request.top_k	double	The top_k sampling setting for the GenAI request.	1.0	Recommended
gen_ai.request.top_p	double	The top_p sampling setting for the GenAI request.	1.0	Recommended
gen_ai.response.finish_reasons	string[]	Array of reasons the model stopped generating tokens, corresponding to each generation received.	["stop"]; ["stop", "length"]	Recommended
gen_ai.response.id	string	The unique identifier for the completion.	chatcmpl-123	Recommended
gen_ai.response.model	string	The name of the model that generated the response. [8]	gpt-4-0613	Recommended
gen_ai.usage.input_tokens	int	The number of tokens used in the GenAI input (prompt).	100	Recommended
gen_ai.usage.output_tokens	int	The number of tokens used in the GenAI response (completion).	180	Recommended
server.address	string	GenAI server address. [9]	example.com; 10.1.2.80; /tmp/my.sock	Recommended

[1] gen_ai.operation.name: If one of the predefined values applies, but specific system uses a different name it’s RECOMMENDED to document it in the semantic conventions for specific GenAI system and use system-specific name in the instrumentation. If a different name is not documented, instrumentation libraries SHOULD use applicable predefined value.

[2] gen_ai.system: The gen_ai.system describes a family of GenAI models with specific model identified by gen_ai.request.model and gen_ai.response.model attributes.

The actual GenAI product may differ from the one identified by the client. Multiple systems, including Azure OpenAI and Gemini, are accessible by OpenAI client libraries. In such cases, the gen_ai.system is set to openai based on the instrumentation’s best knowledge, instead of the actual system. The server.address attribute may help identify the actual system in use for openai.

For custom model, a custom friendly name SHOULD be used. If none of these options apply, the gen_ai.system SHOULD be set to _OTHER.

[3] error.type: The error.type SHOULD match the error code returned by the Generative AI provider or the client library, the canonical name of exception that occurred, or another low-cardinality error identifier. Instrumentations SHOULD document the list of errors they report.

[4] gen_ai.output.type: This attribute SHOULD be used when the client requests output of a specific type. The model may return zero or more outputs of this type. This attribute specifies the output modality and not the actual output format. For example, if an image is requested, the actual output could be a URL pointing to an image file. Additional output format details may be recorded in the future in the gen_ai.output.{type}.* attributes.

[5] gen_ai.output.type: when applicable and if the request includes an output format.

[6] gen_ai.request.model: The name of the GenAI model a request is being made to. If the model is supplied by a vendor, then the value must be the exact name of the model requested. If the model is a fine-tuned custom model, the value should have a more specific name than the base model that’s been fine-tuned.

[7] server.port: When observed from the client side, and when communicating through an intermediary, server.port SHOULD represent the server port behind any intermediaries, for example proxies, if it’s available.

[8] gen_ai.response.model: If available. The name of the GenAI model that provided the response. If the model is supplied by a vendor, then the value must be the exact name of the model actually used. If the model is a fine-tuned custom model, the value should have a more specific name than the base model that’s been fine-tuned.

[9] server.address: When observed from the client side, and when communicating through an intermediary, server.address SHOULD represent the server address behind any intermediaries, for example proxies, if it’s available.

error.type 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
_OTHER	A fallback error value to be used when the instrumentation doesn’t define a custom value.

gen_ai.operation.name 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
chat	Chat completion operation such as OpenAI Chat API
create_agent	Create GenAI agent
embeddings	Embeddings operation such as OpenAI Create embeddings API
execute_tool	Execute a tool
generate_content	Multimodal content generation operation such as Gemini Generate Content
text_completion	Text completions operation such as OpenAI Completions API (Legacy)

gen_ai.output.type 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
image	Image
json	JSON object with known or unknown schema
speech	Speech
text	Plain text

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
anthropic	Anthropic
aws.bedrock	AWS Bedrock
az.ai.inference	Azure AI Inference
az.ai.openai	Azure OpenAI
cohere	Cohere
deepseek	DeepSeek
gcp.gemini	Gemini [10]
gcp.gen_ai	Any Google generative AI endpoint [11]
gcp.vertex_ai	Vertex AI [12]
groq	Groq
ibm.watsonx.ai	IBM Watsonx AI
mistral_ai	Mistral AI
openai	OpenAI
perplexity	Perplexity
xai	xAI

[10]: This refers to the ‘generativelanguage.googleapis.com’ endpoint. Also known as the AI Studio API. May use common attributes prefixed with ‘gcp.gen_ai.’.

[11]: May be used when specific backend is unknown. May use common attributes prefixed with ‘gcp.gen_ai.’.

[12]: This refers to the ‘aiplatform.googleapis.com’ endpoint. May use common attributes prefixed with ‘gcp.gen_ai.’.

Embeddings

Status:

Describes GenAI embeddings span - a request to a Generative AI model or service that generates an embeddings based on the input. The gen_ai.operation.name SHOULD be embeddings. Span name SHOULD be {gen_ai.operation.name} {gen_ai.request.model}.

Span kind SHOULD be CLIENT.

Span status SHOULD follow the Recording Errors document.

Attribute	Type	Description	Examples	Requirement Level	Stability
gen_ai.operation.name	string	The name of the operation being performed. [1]	chat; generate_content; text_completion	Required
error.type	string	Describes a class of error the operation ended with. [2]	timeout; java.net.UnknownHostException; server_certificate_invalid; 500	Conditionally Required if the operation ended in an error
gen_ai.request.model	string	The name of the GenAI model a request is being made to. [3]	gpt-4	Conditionally Required If available.
server.port	int	GenAI server port. [4]	80; 8080; 443	Conditionally Required If server.address is set.
gen_ai.request.encoding_formats	string[]	The encoding formats requested in an embeddings operation, if specified. [5]	["base64"]; ["float", "binary"]	Recommended
gen_ai.usage.input_tokens	int	The number of tokens used in the GenAI input (prompt).	100	Recommended
server.address	string	GenAI server address. [6]	example.com; 10.1.2.80; /tmp/my.sock	Recommended

[1] gen_ai.operation.name: If one of the predefined values applies, but specific system uses a different name it’s RECOMMENDED to document it in the semantic conventions for specific GenAI system and use system-specific name in the instrumentation. If a different name is not documented, instrumentation libraries SHOULD use applicable predefined value.

[2] error.type: The error.type SHOULD match the error code returned by the Generative AI provider or the client library, the canonical name of exception that occurred, or another low-cardinality error identifier. Instrumentations SHOULD document the list of errors they report.

[3] gen_ai.request.model: The name of the GenAI model a request is being made to. If the model is supplied by a vendor, then the value must be the exact name of the model requested. If the model is a fine-tuned custom model, the value should have a more specific name than the base model that’s been fine-tuned.

[4] server.port: When observed from the client side, and when communicating through an intermediary, server.port SHOULD represent the server port behind any intermediaries, for example proxies, if it’s available.

[5] gen_ai.request.encoding_formats: In some GenAI systems the encoding formats are called embedding types. Also, some GenAI systems only accept a single format per request.

[6] server.address: When observed from the client side, and when communicating through an intermediary, server.address SHOULD represent the server address behind any intermediaries, for example proxies, if it’s available.

error.type 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
_OTHER	A fallback error value to be used when the instrumentation doesn’t define a custom value.

gen_ai.operation.name 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
chat	Chat completion operation such as OpenAI Chat API
create_agent	Create GenAI agent
embeddings	Embeddings operation such as OpenAI Create embeddings API
execute_tool	Execute a tool
generate_content	Multimodal content generation operation such as Gemini Generate Content
text_completion	Text completions operation such as OpenAI Completions API (Legacy)

Execute tool span

Status:

Describes tool execution span.

gen_ai.operation.name SHOULD be execute_tool.

Span name SHOULD be execute_tool {gen_ai.tool.name}.

GenAI instrumentations that are able to instrument tool execution call SHOULD do so. However, it’s common for tools to be executed by the application code. It’s recommended for the application developers to follow this semantic convention for tools invoked by the application code.

Span kind SHOULD be INTERNAL.

Span status SHOULD follow the Recording Errors document.

Attribute	Type	Description	Examples	Requirement Level	Stability
error.type	string	Describes a class of error the operation ended with. [1]	timeout; java.net.UnknownHostException; server_certificate_invalid; 500	Conditionally Required if the operation ended in an error
gen_ai.tool.call.id	string	The tool call identifier.	call_mszuSIzqtI65i1wAUOE8w5H4	Recommended if available
gen_ai.tool.description	string	The tool description.	Multiply two numbers	Recommended if available
gen_ai.tool.name	string	Name of the tool utilized by the agent.	Flights	Recommended

[1] error.type: The error.type SHOULD match the error code returned by the Generative AI provider or the client library, the canonical name of exception that occurred, or another low-cardinality error identifier. Instrumentations SHOULD document the list of errors they report.

error.type 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
_OTHER	A fallback error value to be used when the instrumentation doesn’t define a custom value.

Capturing inputs and outputs

User inputs and model responses may be recorded as events parented to GenAI operation span. See Semantic Conventions for GenAI events for the details.