Gen AI

GenAI Attributes

This document defines the attributes used to describe telemetry in the context of Generative Artificial Intelligence (GenAI) Models requests and responses.

AttributeTypeDescriptionExamplesStability
gen_ai.agent.descriptionstringFree-form description of the GenAI agent provided by the application.Helps with math problems; Generates fiction storiesDevelopment
gen_ai.agent.idstringThe unique identifier of the GenAI agent.asst_5j66UpCpwteGg4YSxUnt7lPYDevelopment
gen_ai.agent.namestringHuman-readable name of the GenAI agent provided by the application.Math Tutor; Fiction WriterDevelopment
gen_ai.conversation.idstringThe unique identifier for a conversation (session, thread), used to store and correlate messages within this conversation.conv_5j66UpCpwteGg4YSxUnt7lPYDevelopment
gen_ai.data_source.idstringThe data source identifier. [1]H7STPQYONDDevelopment
gen_ai.input.messagesanyThe chat history provided to the model as an input. [2][
  {
    “role”: “user”,
    “parts”: [
      {
        “type”: “text”,
        “content”: “Weather in Paris?"
      }
    ]
  },
  {
    “role”: “assistant”,
    “parts”: [
      {
        “type”: “tool_call”,
        “id”: “call_VSPygqKTWdrhaFErNvMV18Yl”,
        “name”: “get_weather”,
        “arguments”: {
          “location”: “Paris”
        }
      }
    ]
  },
  {
    “role”: “tool”,
    “parts”: [
      {
        “type”: “tool_call_response”,
        “id”: " call_VSPygqKTWdrhaFErNvMV18Yl”,
        “result”: “rainy, 57°F”
      }
    ]
  }
]
Development
gen_ai.operation.namestringThe name of the operation being performed. [3]chat; generate_content; text_completionDevelopment
gen_ai.output.messagesanyMessages returned by the model where each message represents a specific model response (choice, candidate). [4][
  {
    “role”: “assistant”,
    “parts”: [
      {
        “type”: “text”,
        “content”: “The weather in Paris is currently rainy with a temperature of 57°F."
      }
    ],
    “finish_reason”: “stop”
  }
]
Development
gen_ai.output.typestringRepresents the content type requested by the client. [5]text; json; imageDevelopment
gen_ai.provider.namestringThe Generative AI provider as identified by the client or server instrumentation. [6]openai; gcp.gen_ai; gcp.vertex_aiDevelopment
gen_ai.request.choice.countintThe target number of candidate completions to return.3Development
gen_ai.request.encoding_formatsstring[]The encoding formats requested in an embeddings operation, if specified. [7]["base64"]; ["float", "binary"]Development
gen_ai.request.frequency_penaltydoubleThe frequency penalty setting for the GenAI request.0.1Development
gen_ai.request.max_tokensintThe maximum number of tokens the model generates for a request.100Development
gen_ai.request.modelstringThe name of the GenAI model a request is being made to.gpt-4Development
gen_ai.request.presence_penaltydoubleThe presence penalty setting for the GenAI request.0.1Development
gen_ai.request.seedintRequests with same seed value more likely to return same result.100Development
gen_ai.request.stop_sequencesstring[]List of sequences that the model will use to stop generating further tokens.["forest", "lived"]Development
gen_ai.request.temperaturedoubleThe temperature setting for the GenAI request.0.0Development
gen_ai.request.top_kdoubleThe top_k sampling setting for the GenAI request.1.0Development
gen_ai.request.top_pdoubleThe top_p sampling setting for the GenAI request.1.0Development
gen_ai.response.finish_reasonsstring[]Array of reasons the model stopped generating tokens, corresponding to each generation received.["stop"]; ["stop", "length"]Development
gen_ai.response.idstringThe unique identifier for the completion.chatcmpl-123Development
gen_ai.response.modelstringThe name of the model that generated the response.gpt-4-0613Development
gen_ai.system_instructionsanyThe system message or instructions provided to the GenAI model separately from the chat history. [8][
  {
    “type”: “text”,
    “content”: “You are an Agent that greet users, always use greetings tool to respond”
  }
]; [
  {
    “type”: “text”,
    “content”: “You are a language translator."
  },
  {
    “type”: “text”,
    “content”: “Your mission is to translate text in English to French."
  }
]
Development
gen_ai.token.typestringThe type of token being counted.input; outputDevelopment
gen_ai.tool.call.idstringThe tool call identifier.call_mszuSIzqtI65i1wAUOE8w5H4Development
gen_ai.tool.descriptionstringThe tool description.Multiply two numbersDevelopment
gen_ai.tool.namestringName of the tool utilized by the agent.FlightsDevelopment
gen_ai.tool.typestringType of the tool utilized by the agent [9]function; extension; datastoreDevelopment
gen_ai.usage.input_tokensintThe number of tokens used in the GenAI input (prompt).100Development
gen_ai.usage.output_tokensintThe number of tokens used in the GenAI response (completion).180Development

[1] gen_ai.data_source.id: Data sources are used by AI agents and RAG applications to store grounding data. A data source may be an external database, object store, document collection, website, or any other storage system used by the GenAI agent or application. The gen_ai.data_source.id SHOULD match the identifier used by the GenAI system rather than a name specific to the external storage, such as a database or object store. Semantic conventions referencing gen_ai.data_source.id MAY also leverage additional attributes, such as db.*, to further identify and describe the data source.

[2] gen_ai.input.messages: Instrumentations MUST follow Input messages JSON schema. When the attribute is recorded on events, it MUST be recorded in structured form. When recorded on spans, it MAY be recorded as a JSON string if structured format is not supported and SHOULD be recorded in structured form otherwise.

Messages MUST be provided in the order they were sent to the model. Instrumentations MAY provide a way for users to filter or truncate input messages.

[!Warning] This attribute is likely to contain sensitive information including user/PII data.

See Recording content on attributes section for more details.

[3] 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.

[4] gen_ai.output.messages: Instrumentations MUST follow Output messages JSON schema

Each message represents a single output choice/candidate generated by the model. Each message corresponds to exactly one generation (choice/candidate) and vice versa - one choice cannot be split across multiple messages or one message cannot contain parts from multiple choices.

When the attribute is recorded on events, it MUST be recorded in structured form. When recorded on spans, it MAY be recorded as a JSON string if structured format is not supported and SHOULD be recorded in structured form otherwise.

Instrumentations MAY provide a way for users to filter or truncate output messages.

[!Warning] This attribute is likely to contain sensitive information including user/PII data.

See Recording content on attributes section for more details.

[5] 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.

[6] gen_ai.provider.name: The attribute SHOULD be set based on the instrumentation’s best knowledge and may differ from the actual model provider.

Multiple providers, including Azure OpenAI, Gemini, and AI hosting platforms are accessible using the OpenAI REST API and corresponding client libraries, but may proxy or host models from different providers.

The gen_ai.request.model, gen_ai.response.model, and server.address attributes may help identify the actual system in use.

The gen_ai.provider.name attribute acts as a discriminator that identifies the GenAI telemetry format flavor specific to that provider within GenAI semantic conventions. It SHOULD be set consistently with provider-specific attributes and signals. For example, GenAI spans, metrics, and events related to AWS Bedrock should have the gen_ai.provider.name set to aws.bedrock and include applicable aws.bedrock.* attributes and are not expected to include openai.* attributes.

[7] 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.

[8] gen_ai.system_instructions: This attribute SHOULD be used when the corresponding provider or API allows to provide system instructions or messages separately from the chat history.

Instructions that are part of the chat history SHOULD be recorded in gen_ai.input.messages attribute instead.

Instrumentations MUST follow System instructions JSON schema.

When recorded on spans, it MAY be recorded as a JSON string if structured format is not supported and SHOULD be recorded in structured form otherwise.

Instrumentations MAY provide a way for users to filter or truncate system instructions.

[!Warning] This attribute may contain sensitive information.

See Recording content on attributes section for more details.

[9] gen_ai.tool.type: Extension: A tool executed on the agent-side to directly call external APIs, bridging the gap between the agent and real-world systems. Agent-side operations involve actions that are performed by the agent on the server or within the agent’s controlled environment. Function: A tool executed on the client-side, where the agent generates parameters for a predefined function, and the client executes the logic. Client-side operations are actions taken on the user’s end or within the client application. Datastore: A tool used by the agent to access and query structured or unstructured external data for retrieval-augmented tasks or knowledge updates.


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.

ValueDescriptionStability
chatChat completion operation such as OpenAI Chat APIDevelopment
create_agentCreate GenAI agentDevelopment
embeddingsEmbeddings operation such as OpenAI Create embeddings APIDevelopment
execute_toolExecute a toolDevelopment
generate_contentMultimodal content generation operation such as Gemini Generate ContentDevelopment
invoke_agentInvoke GenAI agentDevelopment
text_completionText completions operation such as OpenAI Completions API (Legacy)Development

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.

ValueDescriptionStability
imageImageDevelopment
jsonJSON object with known or unknown schemaDevelopment
speechSpeechDevelopment
textPlain textDevelopment

gen_ai.provider.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.

ValueDescriptionStability
anthropicAnthropicDevelopment
aws.bedrockAWS BedrockDevelopment
azure.ai.inferenceAzure AI InferenceDevelopment
azure.ai.openaiAzure OpenAIDevelopment
cohereCohereDevelopment
deepseekDeepSeekDevelopment
gcp.geminiGemini [10]Development
gcp.gen_aiAny Google generative AI endpoint [11]Development
gcp.vertex_aiVertex AI [12]Development
groqGroqDevelopment
ibm.watsonx.aiIBM Watsonx AIDevelopment
mistral_aiMistral AIDevelopment
openaiOpenAIDevelopment
perplexityPerplexityDevelopment
x_aixAIDevelopment

[10]: Used when accessing the ‘generativelanguage.googleapis.com’ endpoint. Also known as the AI Studio API.

[11]: May be used when specific backend is unknown.

[12]: Used when accessing the ‘aiplatform.googleapis.com’ endpoint.


gen_ai.token.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.

ValueDescriptionStability
inputInput tokens (prompt, input, etc.)Development
outputOutput tokens (completion, response, etc.)Development

Deprecated GenAI Attributes

Describes deprecated gen_ai attributes.

AttributeTypeDescriptionExamplesStability
gen_ai.completionstringDeprecated, use Event API to report completions contents.[{'role': 'assistant', 'content': 'The capital of France is Paris.'}]Deprecated
Removed, no replacement at this time.
gen_ai.promptstringDeprecated, use Event API to report prompt contents.[{'role': 'user', 'content': 'What is the capital of France?'}]Deprecated
Removed, no replacement at this time.
gen_ai.systemstringDeprecated, use gen_ai.provider.name instead.openai; gcp.gen_ai; gcp.vertex_aiDeprecated
Replaced by gen_ai.provider.name.
gen_ai.usage.completion_tokensintDeprecated, use gen_ai.usage.output_tokens instead.42Deprecated
Replaced by gen_ai.usage.output_tokens.
gen_ai.usage.prompt_tokensintDeprecated, use gen_ai.usage.input_tokens instead.42Deprecated
Replaced by gen_ai.usage.input_tokens.

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.

ValueDescriptionStability
anthropicAnthropicDevelopment
aws.bedrockAWS BedrockDevelopment
az.ai.inferenceAzure AI InferenceDevelopment
az.ai.openaiAzure OpenAIDevelopment
azure.ai.inferenceAzure AI InferenceDevelopment
azure.ai.openaiAzure OpenAIDevelopment
cohereCohereDevelopment
deepseekDeepSeekDevelopment
gcp.geminiGemini [13]Development
gcp.gen_aiAny Google generative AI endpoint [14]Development
gcp.vertex_aiVertex AI [15]Development
groqGroqDevelopment
ibm.watsonx.aiIBM Watsonx AIDevelopment
mistral_aiMistral AIDevelopment
openaiOpenAIDevelopment
perplexityPerplexityDevelopment

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

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

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

Deprecated OpenAI GenAI Attributes

Describes deprecated gen_ai.openai attributes.

AttributeTypeDescriptionExamplesStability
gen_ai.openai.request.response_formatstringDeprecated, use gen_ai.output.type.text; json_object; json_schemaDeprecated
Replaced by gen_ai.output.type.
gen_ai.openai.request.seedintDeprecated, use gen_ai.request.seed.100Deprecated
Replaced by gen_ai.request.seed.
gen_ai.openai.request.service_tierstringDeprecated, use openai.request.service_tier.auto; defaultDeprecated
Replaced by openai.request.service_tier.
gen_ai.openai.response.service_tierstringDeprecated, use openai.response.service_tier.scale; defaultDeprecated
Replaced by openai.response.service_tier.
gen_ai.openai.response.system_fingerprintstringDeprecated, use openai.response.system_fingerprint.fp_44709d6fcbDeprecated
Replaced by openai.response.system_fingerprint.

gen_ai.openai.request.response_format 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.

ValueDescriptionStability
json_objectJSON object response formatDevelopment
json_schemaJSON schema response formatDevelopment
textText response formatDevelopment

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.

ValueDescriptionStability
autoThe system will utilize scale tier credits until they are exhausted.Development
defaultThe system will utilize the default scale tier.Development