# Semantic conventions for Generative AI events **Status**: [Development][DocumentStatus] - [Event: `gen_ai.client.inference.operation.details`](#event-gen_aiclientinferenceoperationdetails) - [Event: `gen_ai.evaluation.result`](#event-gen_aievaluationresult) GenAI instrumentations MAY capture user inputs sent to the model and responses received from it as [events](https://github.com/open-telemetry/opentelemetry-specification/blob/v1.55.0/specification/logs/data-model.md#events). > [!Note] > Events are in-development and not yet available in some languages. Check [spec-compliance matrix](https://github.com/open-telemetry/opentelemetry-specification/blob/v1.55.0/spec-compliance-matrix.md#logs) to see the implementation status in corresponding language. ## Event: `gen_ai.client.inference.operation.details` **Status:**  The event name MUST be `gen_ai.client.inference.operation.details`. Describes the details of a GenAI completion request including chat history and parameters. This event could be used to store input and output details independently from traces. **Requirement level:** [Opt-In](https://github.com/open-telemetry/semantic-conventions/blob/main/docs/general/signal-requirement-level.md). **Attributes:** | Key | Stability | [Requirement Level](https://opentelemetry.io/docs/specs/semconv/general/attribute-requirement-level/) | Value Type | Description | Example Values | | --- | --- | --- | --- | --- | --- | | [`gen_ai.operation.name`](/docs/registry/attributes/gen-ai.md) |  | `Required` | string | The name of the operation being performed. [1] | `chat`; `generate_content`; `text_completion` | | [`gen_ai.provider.name`](/docs/registry/attributes/gen-ai.md) |  | `Required` | string | The Generative AI provider as identified by the client or server instrumentation. [2] | `openai`; `gcp.gen_ai`; `gcp.vertex_ai` | | [`error.type`](https://github.com/open-telemetry/semantic-conventions/blob/v1.43.0/docs/registry/attributes/error.md) |  | `Conditionally Required` If the operation ended in an error. | string | Describes a class of error the operation ended with. [3] | `timeout`; `java.net.UnknownHostException`; `server_certificate_invalid`; `500` | | [`gen_ai.conversation.id`](/docs/registry/attributes/gen-ai.md) |  | `Conditionally Required` When available. | string | The unique identifier for a conversation (session, thread), used to store and correlate messages within this conversation. [4] | `conv_5j66UpCpwteGg4YSxUnt7lPY` | | [`gen_ai.output.type`](/docs/registry/attributes/gen-ai.md) |  | `Conditionally Required` [5] | string | Represents the content type requested by the client. [6] | `text`; `json`; `image` | | [`gen_ai.prompt.name`](/docs/registry/attributes/gen-ai.md) |  | `Conditionally Required` when a named prompt template is used | string | The name of the prompt that uniquely identifies it. | `analyze-code` | | [`gen_ai.prompt.version`](/docs/registry/attributes/gen-ai.md) |  | `Conditionally Required` [7] | string | The version of the prompt template used. [8] | `1.0.0`; `2025-05-01`; `prod`; `v2` | | [`gen_ai.request.choice.count`](/docs/registry/attributes/gen-ai.md) |  | `Conditionally Required` If available, in the request, and !=1. | int | The target number of candidate completions to return. | `3` | | [`gen_ai.request.model`](/docs/registry/attributes/gen-ai.md) |  | `Conditionally Required` If available. | string | The name of the GenAI model a request is being made to. [9] | `gpt-4` | | [`gen_ai.request.seed`](/docs/registry/attributes/gen-ai.md) |  | `Conditionally Required` If applicable and if the request includes a seed. | int | Requests with same seed value more likely to return same result. | `100` | | [`gen_ai.request.stream`](/docs/registry/attributes/gen-ai.md) |  | `Conditionally Required` [10] | boolean | Indicates whether the GenAI request was made in streaming mode. | | | [`gen_ai.request.top_k`](/docs/registry/attributes/gen-ai.md) |  | `Conditionally Required` If applicable. | int | The top-K sampling setting for the GenAI request: restricts token generation at each step to the K most likely next tokens. [11] | `40` | | [`server.port`](https://github.com/open-telemetry/semantic-conventions/blob/v1.43.0/docs/registry/attributes/server.md) |  | `Conditionally Required` If `server.address` is set. | int | GenAI server port. [12] | `80`; `8080`; `443` | | [`gen_ai.conversation.compacted`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` when available | boolean | Indicates whether the effective conversation context used for this operation is a compacted view of a prior conversation. [13] | `true` | | [`gen_ai.request.frequency_penalty`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` | double | The frequency penalty setting for the GenAI request. | `0.1` | | [`gen_ai.request.max_tokens`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` | int | The maximum number of tokens the model generates for a request. | `100` | | [`gen_ai.request.presence_penalty`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` | double | The presence penalty setting for the GenAI request. | `0.1` | | [`gen_ai.request.previous_response.id`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` [14] | string | The unique identifier of a previous response or interaction used to provide context for the current operation. [15] | `resp_0123456789aBCdef`; `interaction-123` | | [`gen_ai.request.reasoning.level`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` When applicable. | string | The reasoning or thinking effort level requested for a GenAI model. [16] | `low`; `medium`; `high` | | [`gen_ai.request.stop_sequences`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` | string[] | List of sequences that the model will use to stop generating further tokens. | `["forest", "lived"]` | | [`gen_ai.request.temperature`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` | double | The temperature setting for the GenAI request. | `0.0` | | [`gen_ai.request.top_p`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` | double | The top_p sampling setting for the GenAI request. | `1.0` | | [`gen_ai.response.finish_reasons`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` | string[] | Array of reasons the model stopped generating tokens, corresponding to each generation received. | `["stop"]`; `["stop", "length"]` | | [`gen_ai.response.id`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` | string | The unique identifier for the completion. | `chatcmpl-123` | | [`gen_ai.response.model`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` | string | The name of the model that generated the response. [17] | `gpt-4-0613` | | [`gen_ai.response.time_to_first_chunk`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` If the request was a streaming request. | double | Time to first chunk in a streaming response, measured from request issuance, in seconds. The value is measured from when the client issues the generation request to when the first chunk is received in the response stream. | `0.5`; `1.2` | | [`gen_ai.usage.cache_creation.input_tokens`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` | int | The number of input tokens written to a provider-managed cache. [18] | `25` | | [`gen_ai.usage.cache_read.input_tokens`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` | int | The number of input tokens served from a provider-managed cache. [19] | `50` | | [`gen_ai.usage.input_tokens`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` | int | The number of tokens used in the GenAI input (prompt). [20] | `100` | | [`gen_ai.usage.output_tokens`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` | int | The number of tokens used in the GenAI response (completion). [21] | `180` | | [`gen_ai.usage.reasoning.output_tokens`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` When applicable. | int | The number of output tokens used for reasoning (e.g. chain-of-thought, extended thinking). [22] | `50` | | [`server.address`](https://github.com/open-telemetry/semantic-conventions/blob/v1.43.0/docs/registry/attributes/server.md) |  | `Recommended` | string | GenAI server address. [23] | `example.com`; `10.1.2.80`; `/tmp/my.sock` | | [`gen_ai.input.messages`](/docs/registry/attributes/gen-ai.md) |  | `Opt-In` | any | The chat history provided to the model as an input. [24] | [
  {
    "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",
        "response": "rainy, 57°F"
      }
    ]
  }
] | | [`gen_ai.output.messages`](/docs/registry/attributes/gen-ai.md) |  | `Opt-In` | any | Messages returned by the model where each message represents a specific model response (choice, candidate). [25] | [
  {
    "role": "assistant",
    "parts": [
      {
        "type": "text",
        "content": "The weather in Paris is currently rainy with a temperature of 57°F."
      }
    ],
    "finish_reason": "stop"
  }
] | | [`gen_ai.prompt.variable`](/docs/registry/attributes/gen-ai.md) |  | `Opt-In` | string | The variables supplied to the prompt template, the `` being the variable name, the value being the variable value. [26] | `Alice`; `French` | | [`gen_ai.system_instructions`](/docs/registry/attributes/gen-ai.md) |  | `Opt-In` | any | The system message or instructions provided to the GenAI model separately from the chat history. [27] | [
  {
    "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."
  }
] | | [`gen_ai.tool.definitions`](/docs/registry/attributes/gen-ai.md) |  | `Opt-In` | any | The list of tool definitions available to the GenAI agent or model. [28] | [
  {
    "type": "function",
    "name": "get_current_weather",
    "description": "Get the current weather in a given location",
    "parameters": {
      "type": "object",
      "properties": {
        "location": {
          "type": "string",
          "description": "The city and state, e.g. San Francisco, CA"
        },
        "unit": {
          "type": "string",
          "enum": [
            "celsius",
            "fahrenheit"
          ]
        }
      },
      "required": [
        "location",
        "unit"
      ]
    }
  }
] | **[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.provider.name`:** Semantic conventions for individual GenAI operations SHOULD clarify which kinds of providers (e.g. inference, embeddings, retrieval, memory, hosted agent providers) apply when it is not clear from context. The attribute SHOULD be set based on the instrumentation's best knowledge and may differ from the actual upstream provider. For example, a client SDK may be configured against a proxy or hosting platform that transparently relays requests to a different provider. 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. **[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.conversation.id`:** Instrumentations SHOULD populate conversation id when they have an identifier for the conversation readily available for a given operation, for example: - when client framework being instrumented manages conversation history (see [LlamaIndex chat store](https://docs.llamaindex.ai/en/stable/module_guides/storing/chat_stores/)) - when instrumenting GenAI client libraries that maintain conversation on the backend side (see [AWS Bedrock agent sessions](https://docs.aws.amazon.com/bedrock/latest/userguide/agents-session-state.html), [OpenAI Assistant threads](https://platform.openai.com/docs/api-reference/threads)) When no identifier for the conversation is available, instrumentations SHOULD NOT populate conversation id. For example, a new UUID, a trace identifier, or a hash of request content SHOULD NOT be used as a fallback value. Application developers that manage conversation history MAY add conversation id to GenAI and other spans or logs using custom span or log record processors or hooks provided by instrumentation libraries. **[5] `gen_ai.output.type`:** When applicable and if the request includes an output format. **[6] `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. **[7] `gen_ai.prompt.version`:** when `gen_ai.prompt.name` is set and a version is available **[8] `gen_ai.prompt.version`:** The version string can follow any versioning scheme chosen by the application (e.g., SemVer, date-based, or platform-specific tags). When a prompt management system is in use, this SHOULD match the version identifier used by that system. **[9] `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. **[10] `gen_ai.request.stream`:** If and only if the request is streaming. If unset, the request is assumed to be non-streaming. **[11] `gen_ai.request.top_k`:** This is a decoding/sampling parameter (e.g., Anthropic `top_k`, Cohere `k`, Google `topK`), not an output-shaping parameter. In particular, OpenAI's `top_logprobs` controls how many per-token log-probabilities are returned in the response and does not change generation; it MUST NOT be reported as `gen_ai.request.top_k`. **[12] `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. **[13] `gen_ai.conversation.compacted`:** This attribute is a positive indicator of context compaction. Instrumentations SHOULD set it to `true` only when they can reliably determine that context compaction was applied. Instrumentations SHOULD NOT set it to `false`; they SHOULD leave it unset otherwise. **[14] `gen_ai.request.previous_response.id`:** When available and if the request references a previous response. **[15] `gen_ai.request.previous_response.id`:** Instrumentations SHOULD populate this attribute when the request references a previous response or interaction identifier to continue a conversation or pass prior context. For example, `previous_response_id` in [OpenAI Responses API](https://developers.openai.com/api/docs/guides/conversation-state#passing-context-from-the-previous-response) or `previous_interaction_id` in [Google GenAI Interactions API](https://ai.google.dev/gemini-api/docs/interactions-overview). **[16] `gen_ai.request.reasoning.level`:** The value SHOULD be the exact string value sent to the provider. Semantic conventions for individual providers SHOULD document which input parameter maps to this attribute. **[17] `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. **[18] `gen_ai.usage.cache_creation.input_tokens`:** The value SHOULD be included in `gen_ai.usage.input_tokens`. **[19] `gen_ai.usage.cache_read.input_tokens`:** The value SHOULD be included in `gen_ai.usage.input_tokens`. **[20] `gen_ai.usage.input_tokens`:** This value SHOULD include all types of input tokens, including cached tokens. Instrumentations SHOULD make a best effort to populate this value, using a total provided by the provider when available or, depending on the provider API, by summing different token types parsed from the provider output. When the provider reports both billed token counts and model-consumed token counts (for example, Cohere exposes both `usage.billed_units` and `usage.tokens`), instrumentations SHOULD report the billed count so the value matches the units the customer is charged for. **[21] `gen_ai.usage.output_tokens`:** When the provider reports both billed token counts and model-consumed token counts (for example, Cohere exposes both `usage.billed_units` and `usage.tokens`), instrumentations SHOULD report the billed count so the value matches the units the customer is charged for. **[22] `gen_ai.usage.reasoning.output_tokens`:** The value SHOULD be included in `gen_ai.usage.output_tokens`. **[23] `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. **[24] `gen_ai.input.messages`:** 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](/docs/gen-ai/gen-ai-spans.md#recording-content-on-attributes) section for more details. Instrumentations MUST follow [JSON schema](/model/gen-ai/gen-ai-input-messages.json). 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. **[25] `gen_ai.output.messages`:** 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. 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](/docs/gen-ai/gen-ai-spans.md#recording-content-on-attributes) section for more details. Instrumentations MUST follow [JSON schema](/model/gen-ai/gen-ai-output-messages.json). 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. **[26] `gen_ai.prompt.variable`:** Prompt templates are parameterized with variables that are filled in at runtime. This attribute records the variable values passed to the template. The attribute name defines the variable name, and the attribute value is the variable value serialized as a string. Examples: - A variable `user_name` with value `Alice` SHOULD be recorded as the `gen_ai.prompt.variable.user_name` attribute with value `"Alice"`. - A variable `language` with value `French` SHOULD be recorded as the `gen_ai.prompt.variable.language` attribute with value `"French"`. > [!Warning] > This attribute may contain sensitive information. **[27] `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 MAY provide a way for users to filter or truncate system instructions. > [!Warning] > This attribute may contain sensitive information. See [Recording content on attributes](/docs/gen-ai/gen-ai-spans.md#recording-content-on-attributes) section for more details. Instrumentations MUST follow [JSON schema](/model/gen-ai/gen-ai-system-instructions.json). 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. **[28] `gen_ai.tool.definitions`:** Since this attribute could be large, it's NOT RECOMMENDED to populate non-required properties by default. Instrumentations MAY provide a way to enable populating optional properties. Instrumentations MUST follow [JSON schema](/model/gen-ai/gen-ai-tool-definitions.json). 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. --- `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](https://platform.openai.com/docs/api-reference/chat) |  | | `create_agent` | Create GenAI agent |  | | `create_memory` | Create new memory records |  | | `create_memory_store` | Create or initialize a memory store |  | | `delete_memory` | Delete memory records |  | | `delete_memory_store` | Delete or deprovision a memory store |  | | `embeddings` | Embeddings operation such as [OpenAI Create embeddings API](https://platform.openai.com/docs/api-reference/embeddings/create) |  | | `execute_tool` | Execute a tool |  | | `generate_content` | Multimodal content generation operation such as [Gemini Generate Content](https://ai.google.dev/api/generate-content) |  | | `invoke_agent` | Invoke GenAI agent |  | | `invoke_workflow` | Invoke GenAI workflow |  | | `plan` | Agent planning or task decomposition phase |  | | `retrieval` | Retrieval operation such as [OpenAI Search Vector Store API](https://platform.openai.com/docs/api-reference/vector-stores/search) |  | | `search_memory` | Search/query memories from a memory store |  | | `text_completion` | Text completions operation such as [OpenAI Completions API (Legacy)](https://platform.openai.com/docs/api-reference/completions) |  | | `update_memory` | Update existing memory records |  | | `upsert_memory` | Create or update memory records without the caller choosing which |  | --- `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.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. | Value | Description | Stability | | --- | --- | --- | | `anthropic` | [Anthropic](https://www.anthropic.com/) |  | | `aws.bedrock` | [AWS Bedrock](https://aws.amazon.com/bedrock) |  | | `azure.ai.inference` | Azure AI Inference |  | | `azure.ai.openai` | [Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-services/openai/overview) |  | | `cohere` | [Cohere](https://cohere.com/) |  | | `deepseek` | [DeepSeek](https://www.deepseek.com/) |  | | `gcp.gemini` | [Gemini](https://cloud.google.com/products/gemini) [29] |  | | `gcp.gen_ai` | Any Google generative AI endpoint [30] |  | | `gcp.vertex_ai` | [Vertex AI](https://cloud.google.com/vertex-ai) [31] |  | | `groq` | [Groq](https://groq.com/) |  | | `ibm.watsonx.ai` | [IBM Watsonx AI](https://www.ibm.com/products/watsonx-ai) |  | | `mistral_ai` | [Mistral AI](https://mistral.ai/) |  | | `moonshot_ai` | [Moonshot AI](https://www.moonshot.ai/) |  | | `openai` | [OpenAI](https://openai.com/) |  | | `perplexity` | [Perplexity](https://www.perplexity.ai/) |  | | `x_ai` | [xAI](https://x.ai/) |  | **[29]:** Used when accessing the 'generativelanguage.googleapis.com' endpoint. Also known as the AI Studio API. **[30]:** May be used when specific backend is unknown. **[31]:** Used when accessing the 'aiplatform.googleapis.com' endpoint. ## Event: `gen_ai.evaluation.result` **Status:**  The event name MUST be `gen_ai.evaluation.result`. This event captures the result of evaluating GenAI output for quality, accuracy, or other characteristics. This event SHOULD be parented to GenAI operation span being evaluated when possible or set `gen_ai.response.id` when span id is not available. **Requirement level:** [Recommended](https://github.com/open-telemetry/semantic-conventions/blob/main/docs/general/signal-requirement-level.md). **Attributes:** | Key | Stability | [Requirement Level](https://opentelemetry.io/docs/specs/semconv/general/attribute-requirement-level/) | Value Type | Description | Example Values | | --- | --- | --- | --- | --- | --- | | [`gen_ai.evaluation.name`](/docs/registry/attributes/gen-ai.md) |  | `Required` | string | The name of the evaluation metric used for the GenAI response. | `Relevance`; `IntentResolution` | | [`error.type`](https://github.com/open-telemetry/semantic-conventions/blob/v1.43.0/docs/registry/attributes/error.md) |  | `Conditionally Required` If the operation ended in an error. | string | Describes a class of error the operation ended with. [1] | `timeout`; `java.net.UnknownHostException`; `server_certificate_invalid`; `500` | | [`gen_ai.evaluation.score.label`](/docs/registry/attributes/gen-ai.md) |  | `Conditionally Required` If applicable. | string | Human readable label for evaluation. [2] | `relevant`; `not_relevant`; `correct`; `incorrect`; `pass`; `fail` | | [`gen_ai.evaluation.score.value`](/docs/registry/attributes/gen-ai.md) |  | `Conditionally Required` If applicable. | double | The evaluation score returned by the evaluator. | `4.0` | | [`gen_ai.evaluation.explanation`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` | string | A free-form explanation for the assigned score provided by the evaluator. | `The response is factually accurate but lacks sufficient detail to fully address the question.` | | [`gen_ai.response.id`](/docs/registry/attributes/gen-ai.md) |  | `Recommended` When available. | string | The unique identifier for the completion. [3] | `chatcmpl-123` | **[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. **[2] `gen_ai.evaluation.score.label`:** This attribute provides a human-readable interpretation of the evaluation score produced by an evaluator. For example, a score value of 1 could mean "relevant" in one evaluation system and "not relevant" in another, depending on the scoring range and evaluator. The label SHOULD have low cardinality. Possible values depend on the evaluation metric and evaluator used; implementations SHOULD document the possible values. **[3] `gen_ai.response.id`:** The unique identifier assigned to the specific completion being evaluated. This attribute helps correlate the evaluation event with the corresponding operation when span id is not 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. |  | [DocumentStatus]: https://opentelemetry.io/docs/specs/otel/document-status