# gen_ai.* attributes: OpenTelemetry GenAI semantic conventions > Every gen_ai.* and mcp.* attribute in the OpenTelemetry GenAI semantic conventions: type, stability, the spans that set it, and renamed names. Source: https://hashspan.dev/learn/otel-attributes/gen-ai From semantic-conventions-genai at 547934a (schema 1.42.0-dev, no release yet). Synced 2026-10-18. ## Short answer The `gen_ai.*` attributes describe model calls, agents and tool calls: `gen_ai.operation.name`, `gen_ai.provider.name`, `gen_ai.request.model`, `gen_ai.usage.input_tokens`, `gen_ai.agent.name`, `gen_ai.tool.name` and more. Every one is Development. Since 2026 they are defined in the `semantic-conventions-genai` repository, together with the `mcp.*` attributes for the Model Context Protocol. ## What do the gen_ai.* and mcp.* attributes describe? An agent run is a tree of model calls and tool calls. The GenAI conventions name each one: `chat` for a model call, `execute_tool` for a tool, `invoke_agent` for the agent around them. The operation goes in `gen_ai.operation.name`, and the span name is built from it. Most keys fall into a few groups. `gen_ai.request.*` and `gen_ai.response.*` describe one model call, `gen_ai.usage.*` counts its tokens, `gen_ai.agent.*` and `gen_ai.tool.*` say who acted and with what. Message content (`gen_ai.input.messages`, `gen_ai.output.messages`) is opt-in. ## Which spans set them? | Span name | Kind | Convention | |---|---|---| | `{gen_ai.operation.name} {gen_ai.request.model}` | CLIENT | gen_ai.client.inference | | `{gen_ai.operation.name} {gen_ai.request.model}` | CLIENT | gen_ai.embeddings.client | | `{gen_ai.operation.name} {gen_ai.data_source.id}` | CLIENT | gen_ai.retrieval.client | | `{gen_ai.operation.name}` | CLIENT | gen_ai.fetch_response.client | | `{gen_ai.operation.name}` | CLIENT | gen_ai.memory.client | | `create_agent {gen_ai.agent.name}` | CLIENT | gen_ai.create_agent.client | | `invoke_agent {gen_ai.agent.name}` | CLIENT | gen_ai.invoke_agent.client | | `invoke_agent {gen_ai.agent.name}` | INTERNAL | gen_ai.invoke_agent.internal | | `execute_tool {gen_ai.tool.name}` | INTERNAL | gen_ai.execute_tool.internal | | `invoke_workflow {gen_ai.workflow.name}` | INTERNAL | gen_ai.invoke_workflow.internal | | `plan {gen_ai.agent.name}` | INTERNAL | gen_ai.plan.internal | | `{mcp.method.name}` | CLIENT | mcp.client | | `{mcp.method.name}` | SERVER | mcp.server | | `{gen_ai.operation.name} {gen_ai.request.model}` | CLIENT | openai.gen_ai.client.inference (refines gen_ai.client.inference) | | `{gen_ai.operation.name}` | CLIENT | openai.fetch_response.client (refines gen_ai.fetch_response.client) | | `{gen_ai.operation.name} {gen_ai.request.model}` | CLIENT | azure.ai.gen_ai.client.inference (refines gen_ai.client.inference) | | `{gen_ai.operation.name} {gen_ai.request.model}` | CLIENT | anthropic.gen_ai.client.inference (refines gen_ai.client.inference) | | `{gen_ai.operation.name} {gen_ai.request.model}` | CLIENT | aws.bedrock.gen_ai.client.inference (refines gen_ai.client.inference) | | `execute_tool {gen_ai.tool.name} {gen_ai.skill.name}` | INTERNAL | gen_ai.execute_tool.load_skill.internal (refines gen_ai.execute_tool.internal) | | `execute_tool {gen_ai.tool.name} {gen_ai.skill.name} {gen_ai.skill.resource.name}` | INTERNAL | gen_ai.execute_tool.read_skill_resource.internal (refines gen_ai.execute_tool.internal) | | `gen_ai.execute_tool.command.internal` | INTERNAL | gen_ai.execute_tool.command.internal (refines gen_ai.execute_tool.internal) | ## What does a real span record? Span `execute_tool pay_vendor` (INTERNAL): | Attribute | Value | |---|---| | `gen_ai.operation.name` | `execute_tool` | | `gen_ai.tool.name` | `pay_vendor` | | `gen_ai.tool.call.id` | `call_1` | | `gen_ai.tool.type` | `function` | | `gen_ai.tool.call.arguments` | `{"amountEth":"0.25"}` | From a real run on 2026-10-04: the AI SDK example agent in the hashspan repository, `ai` 7.0.127, `@ai-sdk/otel` 1.0.127, a scripted offline model, local Anvil chain. [The run in full](https://hashspan.dev/blog/opentelemetry-genai-semantic-conventions). The `chat` span before it carried `gen_ai.operation.name` chat, `gen_ai.request.model` scripted-model and `gen_ai.response.finish_reasons` ["tool-calls"]. The model was scripted, so its provider and token counts are not real ones. ## Why does the OpenTelemetry registry show gen_ai.* as deprecated? Because the names moved, not because they changed. In `semantic-conventions` v1.44.0 every `gen_ai.*` attribute is marked deprecated with the note "Moved to the OpenTelemetry GenAI semantic conventions repository", and the registry on opentelemetry.io shows that as Deprecated. The JavaScript package does the same: version 1.43.0 already marks `ATTR_GEN_AI_AGENT_ID` deprecated. The rows on this page come from the new repository, so they show the current status. The ones marked Deprecated here were really renamed or removed, such as `gen_ai.system`, now `gen_ai.provider.name`. One rename shows up in real traces. In the run above, AI SDK recorded `gen_ai.usage.cache_creation.input_tokens`. The GenAI repository has since renamed it to `gen_ai.usage.cache_write.input_tokens`, so a dashboard that groups by one name misses the other. ## All 79 `gen_ai.*` attributes ### `gen_ai.agent.description` - Type: string - Stability: Development - Free-form description of the GenAI agent provided by the application. - Examples: `Helps with math problems`, `Generates fiction stories` - Set on: - `create_agent {gen_ai.agent.name}` CLIENT: gen_ai.create_agent.client (conditionally required) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (conditionally required) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-agent-description - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.agent.description ### `gen_ai.agent.id` - Type: string - Stability: Development - The unique and stable identifier of the GenAI hosted agent resource. - Examples: `asst_5j66UpCpwteGg4YSxUnt7lPY`, `arn:aws:bedrock:us-east-1:123:agent/42`, `urn:agent:projects-123:projects:123:locations:us-east1:aiplatform:reasoningEngines:456` - Set on: - `create_agent {gen_ai.agent.name}` CLIENT: gen_ai.create_agent.client (conditionally required) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-agent-id - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.agent.id ### `gen_ai.agent.name` - Type: string - Stability: Development - Human-readable name of the GenAI agent provided by the application. - Examples: `Math Tutor`, `Fiction Writer` - Set on: - `create_agent {gen_ai.agent.name}` CLIENT: gen_ai.create_agent.client (conditionally required) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (conditionally required) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (conditionally required) - `execute_tool {gen_ai.tool.name}` INTERNAL: gen_ai.execute_tool.internal (conditionally required) - `plan {gen_ai.agent.name}` INTERNAL: gen_ai.plan.internal (conditionally required) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name}` INTERNAL: gen_ai.execute_tool.load_skill.internal (conditionally required) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name} {gen_ai.skill.resource.name}` INTERNAL: gen_ai.execute_tool.read_skill_resource.internal (conditionally required) - `gen_ai.execute_tool.command.internal` INTERNAL: gen_ai.execute_tool.command.internal (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-agent-name - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.agent.name ### `gen_ai.agent.version` - Type: string - Stability: Development - The version of the GenAI agent. - Examples: `1.0.0`, `2025-05-01` - Set on: - `create_agent {gen_ai.agent.name}` CLIENT: gen_ai.create_agent.client (conditionally required) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-agent-version - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.agent.version ### `gen_ai.conversation.compacted` - Type: boolean - Stability: Development - Indicates whether the effective conversation context used for this operation is a compacted view of a prior conversation. - Examples: `true` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-conversation-compacted - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.conversation.compacted ### `gen_ai.conversation.id` - Type: string - Stability: Development - The unique identifier for a conversation (session, thread), used to store and correlate messages within this conversation. - Examples: `conv_5j66UpCpwteGg4YSxUnt7lPY` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (conditionally required), openai.gen_ai.client.inference (conditionally required), azure.ai.gen_ai.client.inference (conditionally required), anthropic.gen_ai.client.inference (conditionally required), aws.bedrock.gen_ai.client.inference (conditionally required) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (conditionally required) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (conditionally required) - `execute_tool {gen_ai.tool.name}` INTERNAL: gen_ai.execute_tool.internal (conditionally required) - `invoke_workflow {gen_ai.workflow.name}` INTERNAL: gen_ai.invoke_workflow.internal (conditionally required) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name}` INTERNAL: gen_ai.execute_tool.load_skill.internal (conditionally required) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name} {gen_ai.skill.resource.name}` INTERNAL: gen_ai.execute_tool.read_skill_resource.internal (conditionally required) - `gen_ai.execute_tool.command.internal` INTERNAL: gen_ai.execute_tool.command.internal (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-conversation-id - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.conversation.id ### `gen_ai.data_source.id` - Type: string - Stability: Development - The data source identifier. - Examples: `H7STPQYOND` - Set on: - `{gen_ai.operation.name} {gen_ai.data_source.id}` CLIENT: gen_ai.retrieval.client (conditionally required) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (conditionally required) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-data-source-id - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.data_source.id ### `gen_ai.embeddings.dimension.count` - Type: int - Stability: Development - The number of dimensions the resulting output embeddings should have. - Examples: `512`, `1024` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.embeddings.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-embeddings-dimension-count - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.embeddings.dimension.count ### `gen_ai.evaluation.explanation` - Type: string - Stability: Development - A free-form explanation for the assigned score provided by the evaluator. - Examples: `The response is factually accurate but lacks sufficient detail to fully address the question.` - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-evaluation-explanation - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.evaluation.explanation ### `gen_ai.evaluation.name` - Type: string - Stability: Development - The name of the evaluation metric used for the GenAI response. - Examples: `Relevance`, `IntentResolution` - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-evaluation-name - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.evaluation.name ### `gen_ai.evaluation.score.label` - Type: string - Stability: Development - Human readable label for evaluation. - Examples: `relevant`, `not_relevant`, `correct` - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-evaluation-score-label - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.evaluation.score.label ### `gen_ai.evaluation.score.value` - Type: double - Stability: Development - The evaluation score returned by the evaluator. - Examples: `4` - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-evaluation-score-value - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.evaluation.score.value ### `gen_ai.input.messages` - Type: any - Stability: Development - The chat history provided to the model as an input. - Examples: `[ { "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" } ] } ] ` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (opt-in), openai.gen_ai.client.inference (opt-in), azure.ai.gen_ai.client.inference (opt-in), anthropic.gen_ai.client.inference (opt-in), aws.bedrock.gen_ai.client.inference (opt-in) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (opt-in) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (opt-in) - `invoke_workflow {gen_ai.workflow.name}` INTERNAL: gen_ai.invoke_workflow.internal (opt-in) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-input-messages - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.input.messages ### `gen_ai.main_agent.description` - Type: string - Stability: Development - The free-form description of the top-level Generative AI agent in the process. - Examples: `Helps with math problems`, `Generates fiction stories` - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-main-agent-description - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.main_agent.description ### `gen_ai.main_agent.id` - Type: string - Stability: Development - The unique and stable identifier of the top-level Generative AI agent in the process - Examples: `asst_5j66UpCpwteGg4YSxUnt7lPY`, `arn:aws:bedrock:us-east-1:123:agent/42`, `urn:agent:projects-123:projects:123:locations:us-east1:aiplatform:reasoningEngines:456` - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-main-agent-id - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.main_agent.id ### `gen_ai.main_agent.name` - Type: string - Stability: Development - The human-readable name of the top-level Generative AI agent in the process. - Examples: `Math Tutor`, `Fiction Writer` - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-main-agent-name - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.main_agent.name ### `gen_ai.memory.query.text` - Type: string - Stability: Development - The search query used to retrieve memories. - Examples: `user dietary preferences`, `past flight bookings` - Set on: - `{gen_ai.operation.name}` CLIENT: gen_ai.memory.client (opt-in) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-memory-query-text - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.memory.query.text ### `gen_ai.memory.record.count` - Type: int - Stability: Development - The number of memory records relevant to the operation. - Examples: `3` - Set on: - `{gen_ai.operation.name}` CLIENT: gen_ai.memory.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-memory-record-count - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.memory.record.count ### `gen_ai.memory.record.id` - Type: string - Stability: Development - The unique identifier of the memory record. - Examples: `mem_5j66UpCpwteGg4YSxUnt7lPY` - Set on: - `{gen_ai.operation.name}` CLIENT: gen_ai.memory.client (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-memory-record-id - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.memory.record.id ### `gen_ai.memory.records` - Type: any - Stability: Development - The memory records stored or retrieved in a memory operation. - Examples: `[ { "content": "User prefers dark mode", "id": "mem_123", "score": 0.95 }, { "content": { "preference": "vegetarian meals", "confidence": 0.9 }, "metadata": { "source": "profile" } } ] ` - Set on: - `{gen_ai.operation.name}` CLIENT: gen_ai.memory.client (opt-in) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-memory-records - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.memory.records ### `gen_ai.memory.store.id` - Type: string - Stability: Development - The unique identifier of the memory store. - Examples: `ms_abc123`, `user-preferences-store` - Set on: - `{gen_ai.operation.name}` CLIENT: gen_ai.memory.client (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-memory-store-id - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.memory.store.id ### `gen_ai.operation.name` - Type: string - Stability: Development - The name of the operation being performed. - Values: `chat`, `generate_content`, `text_completion`, `embeddings`, `retrieval`, `fetch_response`, `create_agent`, `invoke_agent`, `execute_tool`, `invoke_workflow`, `plan`, `search_memory`, `create_memory`, `update_memory`, `upsert_memory`, `delete_memory`, `create_memory_store`, `delete_memory_store` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (required), gen_ai.embeddings.client (required), openai.gen_ai.client.inference (required), azure.ai.gen_ai.client.inference (required), anthropic.gen_ai.client.inference (required), aws.bedrock.gen_ai.client.inference (required) - `{gen_ai.operation.name} {gen_ai.data_source.id}` CLIENT: gen_ai.retrieval.client (required) - `{gen_ai.operation.name}` CLIENT: gen_ai.fetch_response.client (required), gen_ai.memory.client (required), openai.fetch_response.client (required) - `create_agent {gen_ai.agent.name}` CLIENT: gen_ai.create_agent.client (required) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (required) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (required) - `execute_tool {gen_ai.tool.name}` INTERNAL: gen_ai.execute_tool.internal (required) - `invoke_workflow {gen_ai.workflow.name}` INTERNAL: gen_ai.invoke_workflow.internal (required) - `plan {gen_ai.agent.name}` INTERNAL: gen_ai.plan.internal (required) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name}` INTERNAL: gen_ai.execute_tool.load_skill.internal (required) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name} {gen_ai.skill.resource.name}` INTERNAL: gen_ai.execute_tool.read_skill_resource.internal (required) - `gen_ai.execute_tool.command.internal` INTERNAL: gen_ai.execute_tool.command.internal (required) - `{mcp.method.name}` CLIENT: mcp.client (recommended) - `{mcp.method.name}` SERVER: mcp.server (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-operation-name - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.operation.name ### `gen_ai.output.messages` - Type: any - Stability: Development - Messages returned by the model where each message represents a specific model response (choice, candidate). - Examples: `[ { "role": "assistant", "parts": [ { "type": "text", "content": "The weather in Paris is currently rainy with a temperature of 57°F." } ] } ] ` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (opt-in), openai.gen_ai.client.inference (opt-in), azure.ai.gen_ai.client.inference (opt-in), anthropic.gen_ai.client.inference (opt-in), aws.bedrock.gen_ai.client.inference (opt-in) - `{gen_ai.operation.name}` CLIENT: gen_ai.fetch_response.client (opt-in), openai.fetch_response.client (opt-in) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (opt-in) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (opt-in) - `invoke_workflow {gen_ai.workflow.name}` INTERNAL: gen_ai.invoke_workflow.internal (opt-in) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-output-messages - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.output.messages ### `gen_ai.output.type` - Type: string - Stability: Development - Represents the content type requested by the client. - Values: `text`, `json`, `image`, `speech` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (conditionally required), openai.gen_ai.client.inference (conditionally required), azure.ai.gen_ai.client.inference (conditionally required), anthropic.gen_ai.client.inference (conditionally required), aws.bedrock.gen_ai.client.inference (conditionally required) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (conditionally required) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-output-type - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.output.type ### `gen_ai.prompt.name` - Type: string - Stability: Development - The name of the prompt that uniquely identifies it. - Examples: `analyze-code` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (conditionally required), openai.gen_ai.client.inference (conditionally required), azure.ai.gen_ai.client.inference (conditionally required), anthropic.gen_ai.client.inference (conditionally required), aws.bedrock.gen_ai.client.inference (conditionally required) - `{mcp.method.name}` CLIENT: mcp.client (conditionally required) - `{mcp.method.name}` SERVER: mcp.server (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-prompt-name - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.prompt.name ### `gen_ai.prompt.variable.` - Type: string - Stability: Development - The variables supplied to the prompt template, the `` being the variable name, the value being the variable value. - Examples: `Alice`, `French` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (opt-in), openai.gen_ai.client.inference (opt-in), azure.ai.gen_ai.client.inference (opt-in), anthropic.gen_ai.client.inference (opt-in), aws.bedrock.gen_ai.client.inference (opt-in) - `{mcp.method.name}` CLIENT: mcp.client (opt-in) - `{mcp.method.name}` SERVER: mcp.server (opt-in) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-prompt-variable - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.prompt.variable ### `gen_ai.prompt.version` - Type: string - Stability: Development - The version of the prompt template used. - Examples: `1.0.0`, `2025-05-01`, `prod` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (conditionally required), openai.gen_ai.client.inference (conditionally required), azure.ai.gen_ai.client.inference (conditionally required), anthropic.gen_ai.client.inference (conditionally required), aws.bedrock.gen_ai.client.inference (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-prompt-version - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.prompt.version ### `gen_ai.provider.name` - Type: string - Stability: Development - The Generative AI provider as identified by the client or server instrumentation. - Values: `openai`, `gcp.gen_ai`, `gcp.vertex_ai`, `gcp.gemini`, `anthropic`, `cohere`, `azure.ai.inference`, `azure.ai.openai`, `ibm.watsonx.ai`, `aws.bedrock`, `perplexity`, `x_ai`, `deepseek`, `groq`, `mistral`, `moonshot_ai` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (required), gen_ai.embeddings.client (required), openai.gen_ai.client.inference (required), azure.ai.gen_ai.client.inference (required), anthropic.gen_ai.client.inference (required), aws.bedrock.gen_ai.client.inference (required) - `{gen_ai.operation.name} {gen_ai.data_source.id}` CLIENT: gen_ai.retrieval.client (conditionally required) - `{gen_ai.operation.name}` CLIENT: gen_ai.fetch_response.client (required), gen_ai.memory.client (conditionally required), openai.fetch_response.client (required) - `create_agent {gen_ai.agent.name}` CLIENT: gen_ai.create_agent.client (required) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-provider-name - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.provider.name ### `gen_ai.request.choice.count` - Type: int - Stability: Development - The target number of candidate completions to return. - Examples: `3` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (conditionally required), openai.gen_ai.client.inference (conditionally required), azure.ai.gen_ai.client.inference (conditionally required), anthropic.gen_ai.client.inference (conditionally required), aws.bedrock.gen_ai.client.inference (conditionally required) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (conditionally required) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-request-choice-count - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.request.choice.count ### `gen_ai.request.encoding_formats` - Type: string[] - Stability: Development - The encoding formats requested in an embeddings operation, if specified. - Examples: `["base64"]`, `["float","binary"]` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.embeddings.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-request-encoding-formats - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.request.encoding_formats ### `gen_ai.request.frequency_penalty` - Type: double - Stability: Development - The frequency penalty setting for the GenAI request. - Examples: `0.1` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-request-frequency-penalty - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.request.frequency_penalty ### `gen_ai.request.max_tokens` - Type: int - Stability: Development - The maximum number of tokens the model generates for a request. - Examples: `100` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-request-max-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.request.max_tokens ### `gen_ai.request.model` - Type: string - Stability: Development - The name of the GenAI model a request is being made to. - Examples: `gpt-4` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (conditionally required), gen_ai.embeddings.client (conditionally required), openai.gen_ai.client.inference (required), azure.ai.gen_ai.client.inference (conditionally required), anthropic.gen_ai.client.inference (conditionally required), aws.bedrock.gen_ai.client.inference (conditionally required) - `{gen_ai.operation.name} {gen_ai.data_source.id}` CLIENT: gen_ai.retrieval.client (conditionally required) - `create_agent {gen_ai.agent.name}` CLIENT: gen_ai.create_agent.client (conditionally required) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-request-model - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.request.model ### `gen_ai.request.presence_penalty` - Type: double - Stability: Development - The presence penalty setting for the GenAI request. - Examples: `0.1` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-request-presence-penalty - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.request.presence_penalty ### `gen_ai.request.previous_response.id` - Type: string - Stability: Development - The unique identifier of a previous response or interaction used to provide context for the current operation. - Examples: `resp_0123456789aBCdef`, `interaction-123` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-request-previous-response-id - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.request.previous_response.id ### `gen_ai.request.reasoning.level` - Type: string - Stability: Development - The reasoning or thinking effort level requested for a GenAI model. - Examples: `low`, `medium`, `high` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-request-reasoning-level - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.request.reasoning.level ### `gen_ai.request.seed` - Type: int - Stability: Development - Requests with same seed value more likely to return same result. - Examples: `100` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (conditionally required), openai.gen_ai.client.inference (conditionally required), azure.ai.gen_ai.client.inference (conditionally required), anthropic.gen_ai.client.inference (conditionally required), aws.bedrock.gen_ai.client.inference (conditionally required) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (conditionally required) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-request-seed - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.request.seed ### `gen_ai.request.stop_sequences` - Type: string[] - Stability: Development - List of sequences that the model will use to stop generating further tokens. - Examples: `["forest","lived"]` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-request-stop-sequences - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.request.stop_sequences ### `gen_ai.request.stream` - Type: boolean - Stability: Development - Indicates whether the GenAI request was made in streaming mode. - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (conditionally required), openai.gen_ai.client.inference (conditionally required), azure.ai.gen_ai.client.inference (conditionally required), anthropic.gen_ai.client.inference (conditionally required), aws.bedrock.gen_ai.client.inference (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-request-stream - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.request.stream ### `gen_ai.request.stream_cursor` - Type: string - Stability: Development - The cursor identifying the last streamed event already received, used to resume a streamed response from that position. - Examples: `42`, `event-abc123` - Set on: - `{gen_ai.operation.name}` CLIENT: gen_ai.fetch_response.client (conditionally required), openai.fetch_response.client (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-request-stream-cursor - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.request.stream_cursor ### `gen_ai.request.temperature` - Type: double - Stability: Development - The temperature setting for the GenAI request. - Examples: `0` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-request-temperature - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.request.temperature ### `gen_ai.request.top_k` - Type: int - Stability: Development - The top-K sampling setting for the GenAI request: restricts token generation at each step to the K most likely next tokens. - Examples: `40` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (conditionally required), openai.gen_ai.client.inference (conditionally required), azure.ai.gen_ai.client.inference (conditionally required), anthropic.gen_ai.client.inference (conditionally required), aws.bedrock.gen_ai.client.inference (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-request-top-k - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.request.top_k ### `gen_ai.request.top_p` - Type: double - Stability: Development - The top_p sampling setting for the GenAI request. - Examples: `1` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-request-top-p - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.request.top_p ### `gen_ai.response.finish_reasons` - Type: string[] - Stability: Development - Array of reasons the model stopped generating tokens, corresponding to each generation received. - Examples: `["stop"]`, `["stop","length"]`, `["stop","length","error"]` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `{gen_ai.operation.name}` CLIENT: gen_ai.fetch_response.client (recommended), openai.fetch_response.client (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-response-finish-reasons - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.response.finish_reasons ### `gen_ai.response.id` - Type: string - Stability: Development - The unique identifier for the completion. - Examples: `chatcmpl-123` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `{gen_ai.operation.name}` CLIENT: gen_ai.fetch_response.client (required), openai.fetch_response.client (required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-response-id - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.response.id ### `gen_ai.response.model` - Type: string - Stability: Development - The name of the model that generated the response. - Examples: `gpt-4-0613` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), gen_ai.embeddings.client (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `{gen_ai.operation.name}` CLIENT: gen_ai.fetch_response.client (recommended), openai.fetch_response.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-response-model - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.response.model ### `gen_ai.response.status` - Type: string - Stability: Development - The lifecycle status of a generated response, as reported by the provider when the response is fetched or polled. - Values: `queued`, `in_progress`, `completed`, `incomplete`, `failed`, `cancelled` - Set on: - `{gen_ai.operation.name}` CLIENT: gen_ai.fetch_response.client (recommended), openai.fetch_response.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-response-status - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.response.status ### `gen_ai.response.time_to_first_chunk` - Type: double - Stability: Development - 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. - Examples: `0.5`, `1.2` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-response-time-to-first-chunk - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.response.time_to_first_chunk ### `gen_ai.retrieval.documents` - Type: any - Stability: Development - The documents retrieved. - Examples: `[ { "id": "doc_123", "score": 0.95 }, { "id": "doc_456", "score": 0.87 }, { "id": "doc_789", "score": 0.82 } ] ` - Set on: - `{gen_ai.operation.name} {gen_ai.data_source.id}` CLIENT: gen_ai.retrieval.client (opt-in) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-retrieval-documents - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.retrieval.documents ### `gen_ai.retrieval.query.text` - Type: string - Stability: Development - The query text used for retrieval. - Examples: `What is the capital of France?`, `weather in Paris` - Set on: - `{gen_ai.operation.name} {gen_ai.data_source.id}` CLIENT: gen_ai.retrieval.client (opt-in) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-retrieval-query-text - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.retrieval.query.text ### `gen_ai.retrieval.top_k` - Type: int - Stability: Development - The maximum number of documents the retriever was asked to return for the query (also known as `k`, `limit`, or `max_num_results`). - Examples: `5` - Set on: - `{gen_ai.operation.name} {gen_ai.data_source.id}` CLIENT: gen_ai.retrieval.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-retrieval-top-k - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.retrieval.top_k ### `gen_ai.skill.description` - Type: string - Stability: Development - The [description of the Agent Skill](https://agentskills.io/specification#skill-md-format). - Examples: `Review a changelist against the team's review policy.` - Set on: - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name}` INTERNAL: gen_ai.execute_tool.load_skill.internal (recommended) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name} {gen_ai.skill.resource.name}` INTERNAL: gen_ai.execute_tool.read_skill_resource.internal (recommended) - `gen_ai.execute_tool.command.internal` INTERNAL: gen_ai.execute_tool.command.internal (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-skill-description - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.skill.description ### `gen_ai.skill.name` - Type: string - Stability: Development - The name of the [Agent Skill](https://agentskills.io/specification#skill-md-format). - Examples: `code-review`, `pdf-processing` - Set on: - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name}` INTERNAL: gen_ai.execute_tool.load_skill.internal (conditionally required) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name} {gen_ai.skill.resource.name}` INTERNAL: gen_ai.execute_tool.read_skill_resource.internal (conditionally required) - `gen_ai.execute_tool.command.internal` INTERNAL: gen_ai.execute_tool.command.internal (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-skill-name - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.skill.name ### `gen_ai.skill.resource.name` - Type: string - Stability: Development - The skill-relative name of the resource (script, reference, or asset) being accessed or executed. - Examples: `references/review_policy.md`, `assets/report_template.html` - Set on: - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name} {gen_ai.skill.resource.name}` INTERNAL: gen_ai.execute_tool.read_skill_resource.internal (conditionally required) - `gen_ai.execute_tool.command.internal` INTERNAL: gen_ai.execute_tool.command.internal (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-skill-resource-name - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.skill.resource.name ### `gen_ai.skill.source.uri` - Type: string - Stability: Development - The source URI for loading the skill. - Examples: `https://skills.example.com/code-review`, `gs://example-skills/code-review`, `file:///opt/skills/code-review` - Set on: - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name}` INTERNAL: gen_ai.execute_tool.load_skill.internal (recommended) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name} {gen_ai.skill.resource.name}` INTERNAL: gen_ai.execute_tool.read_skill_resource.internal (recommended) - `gen_ai.execute_tool.command.internal` INTERNAL: gen_ai.execute_tool.command.internal (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-skill-source-uri - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.skill.source.uri ### `gen_ai.system_instructions` - Type: any - Stability: Development - The system message or instructions provided to the GenAI model separately from the chat history. - Examples: `[ { "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." } ] ` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (opt-in), openai.gen_ai.client.inference (opt-in), azure.ai.gen_ai.client.inference (opt-in), anthropic.gen_ai.client.inference (opt-in), aws.bedrock.gen_ai.client.inference (opt-in) - `{gen_ai.operation.name}` CLIENT: gen_ai.fetch_response.client (opt-in), openai.fetch_response.client (opt-in) - `create_agent {gen_ai.agent.name}` CLIENT: gen_ai.create_agent.client (opt-in) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (opt-in) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (opt-in) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-system-instructions - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.system_instructions ### `gen_ai.token.modality` - Type: string - Stability: Development - The modality of the tokens being counted. - Values: `text`, `image`, `audio`, `unknown` - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-token-modality - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.token.modality ### `gen_ai.tool.call.arguments` - Type: any - Stability: Development - Parameters passed to the tool call. - Examples: `{ "location": "San Francisco?", "date": "2025-10-01" } ` - Set on: - `execute_tool {gen_ai.tool.name}` INTERNAL: gen_ai.execute_tool.internal (opt-in) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name}` INTERNAL: gen_ai.execute_tool.load_skill.internal (opt-in) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name} {gen_ai.skill.resource.name}` INTERNAL: gen_ai.execute_tool.read_skill_resource.internal (opt-in) - `gen_ai.execute_tool.command.internal` INTERNAL: gen_ai.execute_tool.command.internal (opt-in) - `{mcp.method.name}` CLIENT: mcp.client (opt-in) - `{mcp.method.name}` SERVER: mcp.server (opt-in) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-tool-call-arguments - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.tool.call.arguments ### `gen_ai.tool.call.id` - Type: string - Stability: Development - The tool call identifier supplied by the model or provider. - Examples: `call_mszuSIzqtI65i1wAUOE8w5H4` - Set on: - `execute_tool {gen_ai.tool.name}` INTERNAL: gen_ai.execute_tool.internal (conditionally required) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name}` INTERNAL: gen_ai.execute_tool.load_skill.internal (conditionally required) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name} {gen_ai.skill.resource.name}` INTERNAL: gen_ai.execute_tool.read_skill_resource.internal (conditionally required) - `gen_ai.execute_tool.command.internal` INTERNAL: gen_ai.execute_tool.command.internal (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-tool-call-id - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.tool.call.id ### `gen_ai.tool.call.result` - Type: any - Stability: Development - The result returned by the tool call (if any and if execution was successful). - Examples: `{ "temperature_range": { "high": 75, "low": 60 }, "conditions": "sunny" } ` - Set on: - `execute_tool {gen_ai.tool.name}` INTERNAL: gen_ai.execute_tool.internal (opt-in) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name}` INTERNAL: gen_ai.execute_tool.load_skill.internal (opt-in) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name} {gen_ai.skill.resource.name}` INTERNAL: gen_ai.execute_tool.read_skill_resource.internal (opt-in) - `gen_ai.execute_tool.command.internal` INTERNAL: gen_ai.execute_tool.command.internal (opt-in) - `{mcp.method.name}` CLIENT: mcp.client (opt-in) - `{mcp.method.name}` SERVER: mcp.server (opt-in) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-tool-call-result - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.tool.call.result ### `gen_ai.tool.definitions` - Type: any - Stability: Development - The list of tool definitions available to the GenAI agent or model. - Examples: `[ { "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" ] } } ] ` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (opt-in), openai.gen_ai.client.inference (opt-in), azure.ai.gen_ai.client.inference (opt-in), anthropic.gen_ai.client.inference (opt-in), aws.bedrock.gen_ai.client.inference (opt-in) - `{gen_ai.operation.name}` CLIENT: gen_ai.fetch_response.client (opt-in), openai.fetch_response.client (opt-in) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (opt-in) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (opt-in) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-tool-definitions - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.tool.definitions ### `gen_ai.tool.description` - Type: string - Stability: Development - The tool description. - Examples: `Multiply two numbers` - Set on: - `execute_tool {gen_ai.tool.name}` INTERNAL: gen_ai.execute_tool.internal (recommended) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name}` INTERNAL: gen_ai.execute_tool.load_skill.internal (recommended) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name} {gen_ai.skill.resource.name}` INTERNAL: gen_ai.execute_tool.read_skill_resource.internal (recommended) - `gen_ai.execute_tool.command.internal` INTERNAL: gen_ai.execute_tool.command.internal (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-tool-description - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.tool.description ### `gen_ai.tool.name` - Type: string - Stability: Development - Name of the tool utilized by the agent. - Examples: `Flights` - Set on: - `execute_tool {gen_ai.tool.name}` INTERNAL: gen_ai.execute_tool.internal (required) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name}` INTERNAL: gen_ai.execute_tool.load_skill.internal (required) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name} {gen_ai.skill.resource.name}` INTERNAL: gen_ai.execute_tool.read_skill_resource.internal (required) - `gen_ai.execute_tool.command.internal` INTERNAL: gen_ai.execute_tool.command.internal (required) - `{mcp.method.name}` CLIENT: mcp.client (conditionally required) - `{mcp.method.name}` SERVER: mcp.server (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-tool-name - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.tool.name ### `gen_ai.tool.type` - Type: string - Stability: Development - Type of the tool utilized by the agent - Examples: `function`, `extension`, `datastore` - Set on: - `execute_tool {gen_ai.tool.name}` INTERNAL: gen_ai.execute_tool.internal (recommended) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name}` INTERNAL: gen_ai.execute_tool.load_skill.internal (recommended) - `execute_tool {gen_ai.tool.name} {gen_ai.skill.name} {gen_ai.skill.resource.name}` INTERNAL: gen_ai.execute_tool.read_skill_resource.internal (recommended) - `gen_ai.execute_tool.command.internal` INTERNAL: gen_ai.execute_tool.command.internal (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-tool-type - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.tool.type ### `gen_ai.usage.audio.cache_read.input_tokens` - Type: int - Stability: Development - The number of audio input tokens served from a provider-managed cache. - Examples: `60` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-usage-audio-cache-read-input-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.audio.cache_read.input_tokens ### `gen_ai.usage.audio.input_tokens` - Type: int - Stability: Development - The number of audio input tokens. - Examples: `120` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-usage-audio-input-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.audio.input_tokens ### `gen_ai.usage.audio.output_tokens` - Type: int - Stability: Development - The number of audio output tokens. - Examples: `240` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-usage-audio-output-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.audio.output_tokens ### `gen_ai.usage.cache_read.input_tokens` - Type: int - Stability: Development - The number of input tokens served from a provider-managed cache. - Examples: `50` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-usage-cache-read-input-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.cache_read.input_tokens ### `gen_ai.usage.cache_write.input_tokens` - Type: int - Stability: Development - The number of input tokens written to a provider-managed cache. - Examples: `25` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-usage-cache-write-input-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.cache_write.input_tokens ### `gen_ai.usage.image.cache_read.input_tokens` - Type: int - Stability: Development - The number of image input tokens served from a provider-managed cache. - Examples: `128` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-usage-image-cache-read-input-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.image.cache_read.input_tokens ### `gen_ai.usage.image.input_tokens` - Type: int - Stability: Development - The number of image input tokens. - Examples: `258` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-usage-image-input-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.image.input_tokens ### `gen_ai.usage.image.output_tokens` - Type: int - Stability: Development - The number of image output tokens. - Examples: `1290` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-usage-image-output-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.image.output_tokens ### `gen_ai.usage.input_tokens` - Type: int - Stability: Development - The number of tokens used in the GenAI input (prompt). - Examples: `100` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), gen_ai.embeddings.client (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-usage-input-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.input_tokens ### `gen_ai.usage.output_tokens` - Type: int - Stability: Development - The number of tokens used in the GenAI response (completion). - Examples: `180` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - `invoke_agent {gen_ai.agent.name}` INTERNAL: gen_ai.invoke_agent.internal (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-usage-output-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.output_tokens ### `gen_ai.usage.reasoning.output_tokens` - Type: int - Stability: Development - The number of output tokens used for reasoning (e.g. chain-of-thought, extended thinking). - Examples: `50` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-usage-reasoning-output-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.reasoning.output_tokens ### `gen_ai.usage.text.cache_read.input_tokens` - Type: int - Stability: Development - The number of text input tokens served from a provider-managed cache. - Examples: `40` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-usage-text-cache-read-input-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.text.cache_read.input_tokens ### `gen_ai.usage.text.input_tokens` - Type: int - Stability: Development - The number of text input tokens. - Examples: `100` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-usage-text-input-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.text.input_tokens ### `gen_ai.usage.text.output_tokens` - Type: int - Stability: Development - The number of text output tokens. - Examples: `180` - Set on: - `{gen_ai.operation.name} {gen_ai.request.model}` CLIENT: gen_ai.client.inference (recommended), openai.gen_ai.client.inference (recommended), azure.ai.gen_ai.client.inference (recommended), anthropic.gen_ai.client.inference (recommended), aws.bedrock.gen_ai.client.inference (recommended) - `invoke_agent {gen_ai.agent.name}` CLIENT: gen_ai.invoke_agent.client (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-usage-text-output-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.text.output_tokens ### `gen_ai.workflow.name` - Type: string - Stability: Development - Human-readable name of the GenAI workflow provided by the application. - Examples: `multi_agent_rag`, `customer_support_pipeline` - Set on: - `invoke_workflow {gen_ai.workflow.name}` INTERNAL: gen_ai.invoke_workflow.internal (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/gen-ai.md#gen-ai-workflow-name - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.workflow.name ## All 4 `mcp.*` attributes ### `mcp.method.name` - Type: string - Stability: Development - The name of the request or notification method. - Values: `notifications/cancelled`, `initialize`, `notifications/initialized`, `notifications/progress`, `ping`, `resources/list`, `resources/templates/list`, `resources/read`, `notifications/resources/list_changed`, `resources/subscribe`, `resources/unsubscribe`, `notifications/resources/updated`, `prompts/list`, `prompts/get`, `notifications/prompts/list_changed`, `tools/list`, `tools/call`, `notifications/tools/list_changed`, `logging/setLevel`, `notifications/message`, `sampling/createMessage`, `completion/complete`, `roots/list`, `notifications/roots/list_changed`, `elicitation/create` - Set on: - `{mcp.method.name}` CLIENT: mcp.client (required) - `{mcp.method.name}` SERVER: mcp.server (required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/mcp.md#mcp-method-name - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#mcp.method.name ### `mcp.protocol.version` - Type: string - Stability: Development - The [version](https://modelcontextprotocol.io/specification/versioning) of the Model Context Protocol used. - Examples: `2025-06-18` - Set on: - `{mcp.method.name}` CLIENT: mcp.client (recommended) - `{mcp.method.name}` SERVER: mcp.server (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/mcp.md#mcp-protocol-version - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#mcp.protocol.version ### `mcp.resource.uri` - Type: string - Stability: Development - The value of the resource uri. - Examples: `postgres://database/customers/schema`, `file:///home/user/documents/report.pdf` - Set on: - `{mcp.method.name}` CLIENT: mcp.client (conditionally required) - `{mcp.method.name}` SERVER: mcp.server (conditionally required) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/mcp.md#mcp-resource-uri - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#mcp.resource.uri ### `mcp.session.id` - Type: string - Stability: Development - Identifies [MCP session](https://modelcontextprotocol.io/specification/2025-06-18/basic/transports#session-management). - Examples: `191c4850af6c49e08843a3f6c80e5046` - Set on: - `{mcp.method.name}` CLIENT: mcp.client (recommended) - `{mcp.method.name}` SERVER: mcp.server (recommended) - Official definition: https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/docs/registry/attributes/mcp.md#mcp-session-id - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#mcp.session.id ## Which names were renamed or removed? ### `gen_ai.completion` - Type: string - Stability: Deprecated - Removed, no replacement at this time. - Examples: `[{'role': 'assistant', 'content': 'The capital of France is Paris.'}]` - Official definition: https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/#gen-ai-completion - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.completion ### `gen_ai.openai.request.response_format` - Type: string - Stability: Deprecated - Replaced by `gen_ai.output.type`. - Values: `text`, `json_object`, `json_schema` - Official definition: https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/#gen-ai-openai-request-response-format - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.openai.request.response_format ### `gen_ai.openai.request.seed` - Type: int - Stability: Deprecated - Replaced by `gen_ai.request.seed`. - Examples: `100` - Official definition: https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/#gen-ai-openai-request-seed - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.openai.request.seed ### `gen_ai.openai.request.service_tier` - Type: string - Stability: Deprecated - Replaced by `openai.request.service_tier`. - Values: `auto`, `default` - Official definition: https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/#gen-ai-openai-request-service-tier - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.openai.request.service_tier ### `gen_ai.openai.response.service_tier` - Type: string - Stability: Deprecated - Replaced by `openai.response.service_tier`. - Examples: `scale`, `default` - Official definition: https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/#gen-ai-openai-response-service-tier - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.openai.response.service_tier ### `gen_ai.openai.response.system_fingerprint` - Type: string - Stability: Deprecated - Replaced by `openai.response.system_fingerprint`. - Examples: `fp_44709d6fcb` - Official definition: https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/#gen-ai-openai-response-system-fingerprint - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.openai.response.system_fingerprint ### `gen_ai.prompt` - Type: string - Stability: Deprecated - Removed, no replacement at this time. - Examples: `[{'role': 'user', 'content': 'What is the capital of France?'}]` - Official definition: https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/#gen-ai-prompt - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.prompt ### `gen_ai.system` - Type: string - Stability: Deprecated - Replaced by `gen_ai.provider.name`. - Values: `openai`, `gcp.gen_ai`, `gcp.vertex_ai`, `gcp.gemini`, `vertex_ai`, `gemini`, `anthropic`, `cohere`, `az.ai.inference`, `az.ai.openai`, `azure.ai.inference`, `azure.ai.openai`, `ibm.watsonx.ai`, `aws.bedrock`, `perplexity`, `xai`, `deepseek`, `groq`, `mistral_ai` - Official definition: https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/#gen-ai-system - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.system ### `gen_ai.token.type` - Type: string - Stability: Deprecated - Replaced, with the `gen_ai.client.token.usage` histogram it served, by per-direction token histograms and `gen_ai.token.modality` ([changelog](https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/changelog.d/374.breaking.md)). - Values: `input`, `output`, `output` - Official definition: https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/#gen-ai-token-type - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.token.type ### `gen_ai.usage.cache_creation.input_tokens` - Type: int - Stability: Deprecated - Renamed to `gen_ai.usage.cache_write.input_tokens` ([changelog](https://github.com/open-telemetry/semantic-conventions-genai/blob/547934afa90a34298441caf80c43b27255c3a292/changelog.d/440.breaking.md)). - Examples: `25` - Official definition: https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/#gen-ai-usage-cache-creation-input-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.cache_creation.input_tokens ### `gen_ai.usage.completion_tokens` - Type: int - Stability: Deprecated - Replaced by `gen_ai.usage.output_tokens`. - Examples: `42` - Official definition: https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/#gen-ai-usage-completion-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.completion_tokens ### `gen_ai.usage.prompt_tokens` - Type: int - Stability: Deprecated - Replaced by `gen_ai.usage.input_tokens`. - Examples: `42` - Official definition: https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/#gen-ai-usage-prompt-tokens - Link: https://hashspan.dev/learn/otel-attributes/gen-ai#gen_ai.usage.prompt_tokens ## FAQ ### Are the gen_ai attributes stable? No. Every gen_ai.* and mcp.* attribute is Development, so names can still be renamed or removed. Pin the version of the instrumentation you use, and check renames before you upgrade. ### Where are the GenAI semantic conventions defined now? In the open-telemetry/semantic-conventions-genai repository, which also holds the MCP conventions. The main semantic-conventions repository keeps only deprecated entries that point there. ### Why does opentelemetry.io mark gen_ai.agent.id as deprecated? The registry there is built from the main repository, where every gen_ai.* name is marked deprecated with the note "Moved to the GenAI repository". The name gen_ai.agent.id itself did not change. ## Read next - [GenAI semantic conventions on a real agent run](https://hashspan.dev/blog/opentelemetry-genai-semantic-conventions) - [Semantic conventions: shared names for spans and attributes](https://hashspan.dev/learn/otel-semantic-conventions) - [Trace an AI SDK agent and its transactions](https://hashspan.dev/docs/recipes/ai-sdk) - [Search every attribute](https://hashspan.dev/learn/otel-attributes.md) Attribute names, types, stability and descriptions are from the OpenTelemetry semantic conventions, © OpenTelemetry Authors, Apache-2.0.