--- title: Gen AI OpenTelemetry metrics reference description: Reference for OpenTelemetry metrics emitted by AI Gateway for generative AI, MCP, and A2A traffic. url: "/ai-gateway/ai-otel-metrics/" canonical_url: "/ai-gateway/ai-otel-metrics/" content_type: reference min_version: ai-gateway: '2.0' products: - AI Gateway tags: - ai - monitoring - metrics - tracing canonical: true works_on: - konnect --- # Gen AI OpenTelemetry metrics reference AI Gateway can export OpenTelemetry (OTLP) metrics for generative AI, MCP, and A2A traffic through an [OpenTelemetry AI Policy](/ai-gateway/policies/opentelemetry/). These metrics are aggregated time-series data points (counters, histograms) pushed to a configured OTLP metrics endpoint on a regular interval. They are separate from the per-request [Gen AI span attributes](/ai-gateway/llm-open-telemetry/) emitted on traces. You can use these metrics to: * Track LLM request latency and upstream provider processing time * Monitor token consumption across AI Model Providers, AI Models, and AI Consumers * Measure time-to-first-token (TTFT) and inter-token latency (TPOT) for streaming responses * Calculate AI request costs * Observe MCP tool-call latency, error rates, and ACL decisions * Monitor A2A agent request volume, duration, and task state transitions ## Prerequisites Metrics are natively supported by the OpenTelemetry Policy. To send metrics, set the following [`config.metrics`](/ai-gateway/policies/opentelemetry/reference/#schema--config-metrics) parameters: ### `config.metrics.enable_ai_metrics`: `true` Source: [OpenTelemetry](/ai-gateway/policies/opentelemetry/reference/) Description: Enable all AI metrics ### `config.metrics.endpoint` Source: [OpenTelemetry](/ai-gateway/policies/opentelemetry/reference/) Description: Set to a valid OTLP-compatible metrics endpoint Some metrics have additional requirements: * `gen_ai.server.request.duration` and `mcp.client.operation.duration` require `config.metrics.enable_latency_metrics` set to `true` in the [OpenTelemetry AI Policy](/ai-gateway/policies/opentelemetry/reference/). * The `error.type` attribute on duration metrics requires `config.metrics.enable_request_metrics` set to `true` in the [OpenTelemetry AI Policy](/ai-gateway/policies/opentelemetry/reference/). ## Gen AI metrics (OTLP semantic conventions) These metrics follow the [OpenTelemetry Gen AI semantic conventions](https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-metrics/). They capture request duration, upstream latency, token usage, and streaming performance. ### Metric reference #### gen_ai.client.operation.duration Total time Kong spends processing a Gen AI operation, such as an LLM request. Requires `enable_request_metrics` to populate the `error.type` attribute. - **Instrument unit**: `s` - **Instrument type**: `Histogram` - **Attributes**: ##### `gen_ai.provider.name` Attribute description: Name of the Gen AI provider. ##### `gen_ai.request.model` Attribute description: Model name targeted by the request. ##### `gen_ai.response.model` Attribute description: Model name reported by the provider in the response. ##### `gen_ai.operation.name` Attribute description: Operation requested, such as `chat` or `embeddings`. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.auth.consumer.name` Attribute description: Name of the authenticated AI Consumer. ##### `kong.gen_ai.request.mode` Attribute description: Request mode: `oneshot`, `stream`, or `realtime`. ##### `error.type` Attribute description: Type of error that occurred. #### gen_ai.server.request.duration Time the LLM provider spends processing the request. Requires `enable_latency_metrics` set to `true`. Requires `enable_request_metrics` to populate the `error.type` attribute. - **Instrument unit**: `s` - **Instrument type**: `Histogram` - **Attributes**: ##### `gen_ai.provider.name` Attribute description: Name of the Gen AI provider. ##### `gen_ai.request.model` Attribute description: Model name targeted by the request. ##### `gen_ai.response.model` Attribute description: Model name reported by the provider in the response. ##### `gen_ai.operation.name` Attribute description: Operation requested, such as `chat` or `embeddings`. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.auth.consumer.name` Attribute description: Name of the authenticated AI Consumer. ##### `kong.gen_ai.request.mode` Attribute description: Request mode: `oneshot`, `stream`, or `realtime`. ##### `error.type` Attribute description: Type of error that occurred. #### gen_ai.client.token.usage Number of tokens consumed by the Gen AI operation. - **Instrument unit**: `{token}` - **Instrument type**: `Sum` - **Attributes**: ##### `gen_ai.provider.name` Attribute description: Name of the Gen AI provider. ##### `gen_ai.request.model` Attribute description: Model name targeted by the request. ##### `gen_ai.response.model` Attribute description: Model name reported by the provider in the response. ##### `gen_ai.token.type` Attribute description: Token category: `input`, `output`, or `total`. ##### `gen_ai.operation.name` Attribute description: Operation requested, such as `chat` or `embeddings`. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.auth.consumer.name` Attribute description: Name of the authenticated AI Consumer. ##### `kong.gen_ai.request.mode` Attribute description: Request mode: `oneshot`, `stream`, or `realtime`. #### gen_ai.server.time_to_first_token Time from when the model server receives the request until the first output token is generated. - **Instrument unit**: `s` - **Instrument type**: `Histogram` - **Attributes**: ##### `gen_ai.provider.name` Attribute description: Name of the Gen AI provider. ##### `gen_ai.request.model` Attribute description: Model name targeted by the request. ##### `gen_ai.response.model` Attribute description: Model name reported by the provider in the response. ##### `gen_ai.operation.name` Attribute description: Operation requested, such as `chat` or `embeddings`. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.auth.consumer.name` Attribute description: Name of the authenticated AI Consumer. ##### `kong.gen_ai.request.mode` Attribute description: Request mode: `oneshot`, `stream`, or `realtime`. #### gen_ai.server.time_per_output_token Time between successive output tokens generated by the model server after the first token. - **Instrument unit**: `s` - **Instrument type**: `Histogram` - **Attributes**: ##### `gen_ai.provider.name` Attribute description: Name of the Gen AI provider. ##### `gen_ai.request.model` Attribute description: Model name targeted by the request. ##### `gen_ai.response.model` Attribute description: Model name reported by the provider in the response. ##### `gen_ai.operation.name` Attribute description: Operation requested, such as `chat` or `embeddings`. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.auth.consumer.name` Attribute description: Name of the authenticated AI Consumer. ##### `kong.gen_ai.request.mode` Attribute description: Request mode: `oneshot`, `stream`, or `realtime`. ## Kong Gen AI metrics These metrics use the `kong.gen_ai.*` namespace and capture Kong-specific AI observability data, including cost tracking, cache and RAG latency, and AWS Guardrails processing time. To populate `kong.gen_ai.llm.cost`, define `targets[].config.input_cost` and `targets[].config.output_cost` in your [AI Model configuration](/ai-gateway/entities/ai-model/#targets). #### kong.gen_ai.llm.cost Cost of AI requests. - **Instrument unit**: `{cost}` - **Instrument type**: `Sum` - **Attributes**: ##### `gen_ai.provider.name` Attribute description: Name of the Gen AI provider. ##### `gen_ai.request.model` Attribute description: Model name targeted by the request. ##### `gen_ai.response.model` Attribute description: Model name reported by the provider in the response. ##### `gen_ai.operation.name` Attribute description: Operation requested, such as `chat` or `embeddings`. ##### `kong.gen_ai.cache.status` Attribute description: Cache status: `hit` or empty if not cached. ##### `kong.gen_ai.vector_db` Attribute description: Vector database used for caching, such as `redis`. ##### `kong.gen_ai.embeddings.provider` Attribute description: Embeddings provider used for caching. ##### `kong.gen_ai.embeddings.model` Attribute description: Embeddings model used for caching. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.auth.consumer.name` Attribute description: Name of the authenticated AI Consumer. ##### `kong.gen_ai.request.mode` Attribute description: Request mode: `oneshot`, `stream`, or `realtime`. #### kong.gen_ai.cache.fetch.latency Time to fetch a response from the semantic cache. - **Instrument unit**: `s` - **Instrument type**: `Histogram` - **Attributes**: ##### `gen_ai.provider.name` Attribute description: Name of the Gen AI provider. ##### `gen_ai.request.model` Attribute description: Model name targeted by the request. ##### `gen_ai.response.model` Attribute description: Model name reported by the provider in the response. ##### `gen_ai.operation.name` Attribute description: Operation requested, such as `chat` or `embeddings`. ##### `kong.gen_ai.cache.status` Attribute description: Cache status: `hit` or empty if not cached. ##### `kong.gen_ai.vector_db` Attribute description: Vector database used for caching, such as `redis`. ##### `kong.gen_ai.embeddings.provider` Attribute description: Embeddings provider used for caching. ##### `kong.gen_ai.embeddings.model` Attribute description: Embeddings model used for caching. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.auth.consumer.name` Attribute description: Name of the authenticated AI Consumer. ##### `kong.gen_ai.request.mode` Attribute description: Request mode: `oneshot`, `stream`, or `realtime`. #### kong.gen_ai.cache.embeddings.latency Time to generate embeddings during cache operations. - **Instrument unit**: `s` - **Instrument type**: `Histogram` - **Attributes**: ##### `gen_ai.provider.name` Attribute description: Name of the Gen AI provider. ##### `gen_ai.request.model` Attribute description: Model name targeted by the request. ##### `gen_ai.response.model` Attribute description: Model name reported by the provider in the response. ##### `gen_ai.operation.name` Attribute description: Operation requested, such as `chat` or `embeddings`. ##### `kong.gen_ai.cache.status` Attribute description: Cache status: `hit` or empty if not cached. ##### `kong.gen_ai.vector_db` Attribute description: Vector database used for caching, such as `redis`. ##### `kong.gen_ai.embeddings.provider` Attribute description: Embeddings provider used for caching. ##### `kong.gen_ai.embeddings.model` Attribute description: Embeddings model used for caching. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.auth.consumer.name` Attribute description: Name of the authenticated AI Consumer. ##### `kong.gen_ai.request.mode` Attribute description: Request mode: `oneshot`, `stream`, or `realtime`. #### kong.gen_ai.rag.fetch.latency Time to fetch data from a RAG source. - **Instrument unit**: `s` - **Instrument type**: `Histogram` - **Attributes**: ##### `gen_ai.provider.name` Attribute description: Name of the Gen AI provider. ##### `gen_ai.request.model` Attribute description: Model name targeted by the request. ##### `gen_ai.response.model` Attribute description: Model name reported by the provider in the response. ##### `gen_ai.operation.name` Attribute description: Operation requested, such as `chat` or `embeddings`. ##### `kong.gen_ai.cache.status` Attribute description: Cache status: `hit` or empty if not cached. ##### `kong.gen_ai.vector_db` Attribute description: Vector database used for caching, such as `redis`. ##### `kong.gen_ai.embeddings.provider` Attribute description: Embeddings provider used for caching. ##### `kong.gen_ai.embeddings.model` Attribute description: Embeddings model used for caching. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.auth.consumer.name` Attribute description: Name of the authenticated AI Consumer. ##### `kong.gen_ai.request.mode` Attribute description: Request mode: `oneshot`, `stream`, or `realtime`. #### kong.gen_ai.rag.embeddings.latency Time to generate embeddings for RAG operations. - **Instrument unit**: `s` - **Instrument type**: `Histogram` - **Attributes**: ##### `gen_ai.provider.name` Attribute description: Name of the Gen AI provider. ##### `gen_ai.request.model` Attribute description: Model name targeted by the request. ##### `gen_ai.response.model` Attribute description: Model name reported by the provider in the response. ##### `gen_ai.operation.name` Attribute description: Operation requested, such as `chat` or `embeddings`. ##### `kong.gen_ai.cache.status` Attribute description: Cache status: `hit` or empty if not cached. ##### `kong.gen_ai.vector_db` Attribute description: Vector database used for caching, such as `redis`. ##### `kong.gen_ai.embeddings.provider` Attribute description: Embeddings provider used for caching. ##### `kong.gen_ai.embeddings.model` Attribute description: Embeddings model used for caching. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.auth.consumer.name` Attribute description: Name of the authenticated AI Consumer. ##### `kong.gen_ai.request.mode` Attribute description: Request mode: `oneshot`, `stream`, or `realtime`. #### kong.gen_ai.aws.guardrails.latency Time for AWS Guardrails to process a request. - **Instrument unit**: `s` - **Instrument type**: `Histogram` - **Attributes**: ##### `kong.gen_ai.aws.guardrails.id` Attribute description: ID of the AWS Guardrails configuration. ##### `kong.gen_ai.aws.guardrails.version` Attribute description: Version of the AWS Guardrails configuration. ##### `kong.gen_ai.aws.guardrails.mode` Attribute description: Mode of the AWS Guardrails evaluation. ##### `kong.gen_ai.aws.guardrails.region` Attribute description: AWS region of the Guardrails service. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.auth.consumer.name` Attribute description: Name of the authenticated AI Consumer. #### kong.gen_ai.mcp.response.size Size of the MCP response body in bytes. - **Instrument unit**: `By` - **Instrument type**: `Histogram` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `mcp.method.name` Attribute description: MCP method name, such as `tools/call`. ##### `gen_ai.tool.name` Attribute description: Name of the MCP tool invoked. #### kong.gen_ai.mcp.request.error.count Number of MCP request errors. - **Instrument unit**: `{error}` - **Instrument type**: `Sum` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `mcp.method.name` Attribute description: MCP method name, such as `tools/call`. ##### `gen_ai.tool.name` Attribute description: Name of the MCP tool invoked. ##### `error.type` Attribute description: Type of error that occurred. #### kong.gen_ai.mcp.acl.allowed Number of MCP requests allowed by ACL rules. - **Instrument unit**: `{request}` - **Instrument type**: `Sum` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.mcp.primitive` Attribute description: MCP primitive type, such as `tool`. ##### `kong.gen_ai.mcp.primitive_name` Attribute description: Name of the MCP primitive. #### kong.gen_ai.mcp.acl.denied Number of MCP requests denied by ACL rules. - **Instrument unit**: `{request}` - **Instrument type**: `Sum` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.mcp.primitive` Attribute description: MCP primitive type, such as `tool`. ##### `kong.gen_ai.mcp.primitive_name` Attribute description: Name of the MCP primitive. #### kong.gen_ai.a2a.request.count Total number of A2A requests. - **Instrument unit**: `{request}` - **Instrument type**: `Sum` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.a2a.method` Attribute description: A2A method name. ##### `kong.gen_ai.a2a.binding` Attribute description: A2A binding type. #### kong.gen_ai.a2a.request.duration Duration of an A2A request in seconds. - **Instrument unit**: `s` - **Instrument type**: `Histogram` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.a2a.method` Attribute description: A2A method name. ##### `kong.gen_ai.a2a.binding` Attribute description: A2A binding type. #### kong.gen_ai.a2a.response.size Size of the A2A response body in bytes. - **Instrument unit**: `By` - **Instrument type**: `Histogram` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.a2a.method` Attribute description: A2A method name. ##### `kong.gen_ai.a2a.binding` Attribute description: A2A binding type. #### kong.gen_ai.a2a.ttfb Time to first byte for A2A streaming responses in seconds. - **Instrument unit**: `s` - **Instrument type**: `Histogram` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.a2a.method` Attribute description: A2A method name. ##### `kong.gen_ai.a2a.binding` Attribute description: A2A binding type. #### kong.gen_ai.a2a.request.error.count Number of A2A request errors. - **Instrument unit**: `{error}` - **Instrument type**: `Sum` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.a2a.method` Attribute description: A2A method name. ##### `kong.gen_ai.a2a.binding` Attribute description: A2A binding type. ##### `kong.gen_ai.a2a.error.type` Attribute description: Type of the A2A error. #### kong.gen_ai.a2a.task.state.count Number of A2A task state transitions. - **Instrument unit**: `{state}` - **Instrument type**: `Sum` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.a2a.task.state` Attribute description: Task state, such as `completed`, `failed`, or `in_progress`. ## MCP metrics These metrics provide observability into MCP (Model Context Protocol) server interactions, including latency, response sizes, errors, and ACL decisions. #### kong.gen_ai.mcp.response.size Size of the MCP response body in bytes. - **Instrument unit**: `By` - **Instrument type**: `Histogram` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `mcp.method.name` Attribute description: MCP method name, such as `tools/call`. ##### `gen_ai.tool.name` Attribute description: Name of the MCP tool invoked. #### kong.gen_ai.mcp.request.error.count Number of MCP request errors. - **Instrument unit**: `{error}` - **Instrument type**: `Sum` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `mcp.method.name` Attribute description: MCP method name, such as `tools/call`. ##### `gen_ai.tool.name` Attribute description: Name of the MCP tool invoked. ##### `error.type` Attribute description: Type of error that occurred. #### mcp.client.operation.duration Duration of the MCP request as observed by the sender. Only available when the MCP entity is in passthrough-listener mode. Requires `enable_latency_metrics` set to `true`. - **Instrument unit**: `s` - **Instrument type**: `Histogram` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `mcp.method.name` Attribute description: MCP method name, such as `tools/call`. ##### `gen_ai.tool.name` Attribute description: Name of the MCP tool invoked. ##### `error.type` Attribute description: Type of error that occurred. ##### `gen_ai.operation.name` Attribute description: Operation requested, such as `chat` or `embeddings`. #### mcp.server.operation.duration Duration of the MCP request as observed by the receiver. - **Instrument unit**: `s` - **Instrument type**: `Histogram` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `mcp.method.name` Attribute description: MCP method name, such as `tools/call`. ##### `gen_ai.tool.name` Attribute description: Name of the MCP tool invoked. ##### `error.type` Attribute description: Type of error that occurred. ##### `gen_ai.operation.name` Attribute description: Operation requested, such as `chat` or `embeddings`. #### kong.gen_ai.mcp.acl.allowed Number of MCP requests allowed by ACL rules. - **Instrument unit**: `{request}` - **Instrument type**: `Sum` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.mcp.primitive` Attribute description: MCP primitive type, such as `tool`. ##### `kong.gen_ai.mcp.primitive_name` Attribute description: Name of the MCP primitive. #### kong.gen_ai.mcp.acl.denied Number of MCP requests denied by ACL rules. - **Instrument unit**: `{request}` - **Instrument type**: `Sum` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.mcp.primitive` Attribute description: MCP primitive type, such as `tool`. ##### `kong.gen_ai.mcp.primitive_name` Attribute description: Name of the MCP primitive. ## A2A metrics These metrics provide observability into [A2A (Agent-to-Agent)](/ai-gateway/entities/ai-agent/) traffic, including request volume, latency, response sizes, and task state transitions. #### kong.gen_ai.a2a.request.count Total number of A2A requests. - **Instrument unit**: `{request}` - **Instrument type**: `Sum` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.a2a.method` Attribute description: A2A method name. ##### `kong.gen_ai.a2a.binding` Attribute description: A2A binding type. #### kong.gen_ai.a2a.request.duration Duration of an A2A request in seconds. - **Instrument unit**: `s` - **Instrument type**: `Histogram` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.a2a.method` Attribute description: A2A method name. ##### `kong.gen_ai.a2a.binding` Attribute description: A2A binding type. #### kong.gen_ai.a2a.response.size Size of the A2A response body in bytes. - **Instrument unit**: `By` - **Instrument type**: `Histogram` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.a2a.method` Attribute description: A2A method name. ##### `kong.gen_ai.a2a.binding` Attribute description: A2A binding type. #### kong.gen_ai.a2a.ttfb Time to first byte for A2A streaming responses in seconds. - **Instrument unit**: `s` - **Instrument type**: `Histogram` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.a2a.method` Attribute description: A2A method name. ##### `kong.gen_ai.a2a.binding` Attribute description: A2A binding type. #### kong.gen_ai.a2a.request.error.count Number of A2A request errors. - **Instrument unit**: `{error}` - **Instrument type**: `Sum` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.a2a.method` Attribute description: A2A method name. ##### `kong.gen_ai.a2a.binding` Attribute description: A2A binding type. ##### `kong.gen_ai.a2a.error.type` Attribute description: Type of the A2A error. #### kong.gen_ai.a2a.task.state.count Number of A2A task state transitions. - **Instrument unit**: `{state}` - **Instrument type**: `Sum` - **Attributes**: ##### `kong.service.name` Attribute description: Name of the Gateway Service. ##### `kong.route.name` Attribute description: Name of the Route. ##### `kong.workspace.name` Attribute description: Name of the Workspace. ##### `kong.gen_ai.a2a.task.state` Attribute description: Task state, such as `completed`, `failed`, or `in_progress`. ## Related Resources - [Gen AI OpenTelemetry span attributes](/ai-gateway/llm-open-telemetry/) - [Monitor AI LLM metrics (Prometheus)](/ai-gateway/monitor-ai-llm-metrics/) - [AI Gateway](/ai-gateway/) - [OpenTelemetry Policy](/ai-gateway/policies/opentelemetry/) - [Kong Gateway OpenTelemetry metrics reference](/gateway/otel-metrics/) - [Kong Gateway tracing guide](/gateway/tracing/) - [AI Gateway audit log reference](/ai-gateway/ai-audit-log-reference/) - [Model cost management](/ai-gateway/model-cost-management/)