# Semantic Conventions for GenAI spans **Status**: [Experimental][DocumentStatus] - [Name](#name) - [GenAI attributes](#genai-attributes) - [Capturing inputs and outputs](#capturing-inputs-and-outputs) A request to an Generative AI is modeled as a span in a trace. **Span kind:** SHOULD be `CLIENT`. It MAY be set to `INTERNAL` on spans representing call to models running in the same process. It's RECOMMENDED to use `CLIENT` kind when GenAI system being instrumented usually runs in a different process than its client or when GenAI call happens over instrumented protocol such as HTTP. ## Name GenAI spans MUST follow the overall [guidelines for span names](https://github.com/open-telemetry/opentelemetry-specification/tree/v1.39.0/specification/trace/api.md#span). The **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. ## GenAI attributes These attributes track input data and metadata for a request to a GenAI model. Each attribute represents a concept that is common to most Generative AI clients. Many of these attributes only apply to specific GenAI operations. For example, GenAI embeddings requests don't use output tokens, so `gen_ai.usage.output_tokens` does not apply to embeddings operations. | Attribute | Type | Description | Examples | [Requirement Level](https://opentelemetry.io/docs/specs/semconv/general/attribute-requirement-level/) | Stability | |---|---|---|---|---|---| | [`gen_ai.operation.name`](/docs/attributes-registry/gen-ai.md) | string | The name of the operation being performed. [1] | `chat`; `text_completion`; `embeddings` | `Required` |  | | [`gen_ai.system`](/docs/attributes-registry/gen-ai.md) | string | The Generative AI product as identified by the client or server instrumentation. [2] | `openai` | `Required` |  | | [`error.type`](/docs/attributes-registry/error.md) | 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.request.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the GenAI model a request is being made to. [4] | `gpt-4` | `Conditionally Required` If available. |  | | [`server.port`](/docs/attributes-registry/server.md) | int | GenAI server port. [5] | `80`; `8080`; `443` | `Conditionally Required` If `server.address` is set. |  | | [`gen_ai.request.encoding_formats`](/docs/attributes-registry/gen-ai.md) | string[] | The encoding formats requested in an embeddings operation, if specified. [6] | `["base64"]`; `["float", "binary"]` | `Recommended` |  | | [`gen_ai.request.frequency_penalty`](/docs/attributes-registry/gen-ai.md) | double | The frequency penalty setting for the GenAI request. | `0.1` | `Recommended` |  | | [`gen_ai.request.max_tokens`](/docs/attributes-registry/gen-ai.md) | int | The maximum number of tokens the model generates for a request. | `100` | `Recommended` |  | | [`gen_ai.request.presence_penalty`](/docs/attributes-registry/gen-ai.md) | double | The presence penalty setting for the GenAI request. | `0.1` | `Recommended` |  | | [`gen_ai.request.stop_sequences`](/docs/attributes-registry/gen-ai.md) | string[] | List of sequences that the model will use to stop generating further tokens. | `["forest", "lived"]` | `Recommended` |  | | [`gen_ai.request.temperature`](/docs/attributes-registry/gen-ai.md) | double | The temperature setting for the GenAI request. | `0.0` | `Recommended` |  | | [`gen_ai.request.top_k`](/docs/attributes-registry/gen-ai.md) | double | The top_k sampling setting for the GenAI request. | `1.0` | `Recommended` |  | | [`gen_ai.request.top_p`](/docs/attributes-registry/gen-ai.md) | double | The top_p sampling setting for the GenAI request. | `1.0` | `Recommended` |  | | [`gen_ai.response.finish_reasons`](/docs/attributes-registry/gen-ai.md) | string[] | Array of reasons the model stopped generating tokens, corresponding to each generation received. | `["stop"]`; `["stop", "length"]` | `Recommended` |  | | [`gen_ai.response.id`](/docs/attributes-registry/gen-ai.md) | string | The unique identifier for the completion. | `chatcmpl-123` | `Recommended` |  | | [`gen_ai.response.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the model that generated the response. [7] | `gpt-4-0613` | `Recommended` |  | | [`gen_ai.usage.input_tokens`](/docs/attributes-registry/gen-ai.md) | int | The number of tokens used in the GenAI input (prompt). | `100` | `Recommended` |  | | [`gen_ai.usage.output_tokens`](/docs/attributes-registry/gen-ai.md) | int | The number of tokens used in the GenAI response (completion). | `180` | `Recommended` |  | | [`server.address`](/docs/attributes-registry/server.md) | string | GenAI server address. [8] | `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. For example, when using OpenAI client libraries to communicate with Mistral, the `gen_ai.system` is set to `openai` based on the instrumentation's best knowledge. 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.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. **[5] `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. **[6] `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. **[7] `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. **[8] `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](https://platform.openai.com/docs/api-reference/chat) |  | | `embeddings` | Embeddings operation such as [OpenAI Create embeddings API](https://platform.openai.com/docs/api-reference/embeddings/create) |  | | `text_completion` | Text completions operation such as [OpenAI Completions API (Legacy)](https://platform.openai.com/docs/api-reference/completions) |  | --- `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 |  | | `cohere` | Cohere |  | | `ibm.watsonx.ai` | IBM Watsonx AI |  | | `openai` | OpenAI |  | | `vertex_ai` | Vertex AI |  | ## 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](./gen-ai-events.md) for the details. [DocumentStatus]: https://opentelemetry.io/docs/specs/otel/document-status