Semantic conventions for OpenAI operations

Status: Development

The Semantic Conventions for OpenAI extend and override the semantic conventions for Gen AI Spans and Gen AI Metrics.

gen_ai.system MUST be set to "openai".

OpenAI Spans

These attributes track input data and metadata for a request to an OpenAI model. The attributes include general Generative AI attributes and ones specific the OpenAI.

Attribute	Type	Description	Examples	Requirement Level	Stability
gen_ai.operation.name	string	The name of the operation being performed. [1]	chat; text_completion; embeddings	Required
gen_ai.request.model	string	The name of the GenAI model a request is being made to. [2]	gpt-4	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.openai.request.service_tier	string	The service tier requested. May be a specific tier, default, or auto.	auto; default	Conditionally Required [4]
gen_ai.openai.response.service_tier	string	The service tier used for the response.	scale; default	Conditionally Required [5]
gen_ai.output.type	string	Represents the content type requested by the client. [6]	text; json; image	Conditionally Required [7]
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.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. [8]	80; 8080; 443	Conditionally Required If server.address is set.
gen_ai.openai.response.system_fingerprint	string	A fingerprint to track any eventual change in the Generative AI environment.	fp_44709d6fcb	Recommended
gen_ai.request.encoding_formats	string[]	The encoding formats requested in an embeddings operation, if specified. [9]	["base64"]; ["float", "binary"]	Recommended
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_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. [10]	gpt-4-0613	Recommended
gen_ai.usage.input_tokens	int	The number of tokens used in the prompt sent to OpenAI.	100	Recommended
gen_ai.usage.output_tokens	int	The number of tokens used in the completions from OpenAI.	180	Recommended
server.address	string	GenAI server address. [11]	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.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.

[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.openai.request.service_tier: if the request includes a service_tier and the value is not ‘auto’

[5] gen_ai.openai.response.service_tier: if the response was received and includes a service_tier

[6] gen_ai.output.type: This attribute SHOULD be set to the output type requested by the client: - json for structured outputs with defined or undefined schema - image for image output - speech for speech output - text for plain text output The 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.

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

[8] 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.

[9] 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.

[10] 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.

[11] 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.openai.request.service_tier 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
auto	The system will utilize scale tier credits until they are exhausted.
default	The system will utilize the default scale tier.

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
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

OpenAI Metrics

OpenAI metrics follow Generative AI metrics with the noted additional attributes. Individual systems may include additional system-specific attributes. It is recommended to check system-specific documentation, if available.

Metric: gen_ai.client.token.usage

Reports the usage of tokens following the common gen_ai.client.token.usage definition.

Additional attributes:

Attribute	Type	Description	Examples	Requirement Level	Stability
gen_ai.openai.response.service_tier	string	The service tier used for the response.	scale; default	Recommended
gen_ai.openai.response.system_fingerprint	string	A fingerprint to track any eventual change in the Generative AI environment.	fp_44709d6fcb	Recommended

Metric: gen_ai.client.operation.duration

Measures the to complete an operation following the common gen_ai.client.operation.duration definition.

Additional attributes:

Attribute	Type	Description	Examples	Requirement Level	Stability
gen_ai.openai.response.service_tier	string	The service tier used for the response.	scale; default	Recommended
gen_ai.openai.response.system_fingerprint	string	A fingerprint to track any eventual change in the Generative AI environment.	fp_44709d6fcb	Recommended