OpenTelemetry attributes: semantic conventions lookup

• gen_ai.agent.descriptionstringDevelopment

  Free-form description of the GenAI agent provided by the application.

• gen_ai.agent.idstringDevelopment

  The unique and stable identifier of the GenAI hosted agent resource.

• gen_ai.agent.namestringDevelopment

  Human-readable name of the GenAI agent provided by the application.

• gen_ai.agent.versionstringDevelopment

  The version of the GenAI agent.

• gen_ai.conversation.compactedbooleanDevelopment

  Indicates whether the effective conversation context used for this operation is a compacted view of a prior conversation.

• gen_ai.conversation.idstringDevelopment

  The unique identifier for a conversation (session, thread), used to store and correlate messages within this conversation.

• gen_ai.data_source.idstringDevelopment

  The data source identifier.

• gen_ai.embeddings.dimension.countintDevelopment

  The number of dimensions the resulting output embeddings should have.

• gen_ai.evaluation.explanationstringDevelopment

  A free-form explanation for the assigned score provided by the evaluator.

• gen_ai.evaluation.namestringDevelopment

  The name of the evaluation metric used for the GenAI response.

• gen_ai.evaluation.score.labelstringDevelopment

  Human readable label for evaluation.

• gen_ai.evaluation.score.valuedoubleDevelopment

  The evaluation score returned by the evaluator.

• gen_ai.input.messagesanyDevelopment

  The chat history provided to the model as an input.

• gen_ai.main_agent.descriptionstringDevelopment

  The free-form description of the top-level Generative AI agent in the process.

• gen_ai.main_agent.idstringDevelopment

  The unique and stable identifier of the top-level Generative AI agent in the process

• gen_ai.main_agent.namestringDevelopment

  The human-readable name of the top-level Generative AI agent in the process.

• gen_ai.memory.query.textstringDevelopment

  The search query used to retrieve memories.

• gen_ai.memory.record.countintDevelopment

  The number of memory records relevant to the operation.

• gen_ai.memory.record.idstringDevelopment

  The unique identifier of the memory record.

• gen_ai.memory.recordsanyDevelopment

  The memory records stored or retrieved in a memory operation.

• gen_ai.memory.store.idstringDevelopment

  The unique identifier of the memory store.

• gen_ai.operation.namestringDevelopment

  The name of the operation being performed.

• gen_ai.output.messagesanyDevelopment

  Messages returned by the model where each message represents a specific model response (choice, candidate).

• gen_ai.output.typestringDevelopment

  Represents the content type requested by the client.

• gen_ai.prompt.namestringDevelopment

  The name of the prompt that uniquely identifies it.

• gen_ai.prompt.variable.<key>stringDevelopment

  The variables supplied to the prompt template, the <key> being the variable name, the value being the variable value.

• gen_ai.prompt.versionstringDevelopment

  The version of the prompt template used.

• gen_ai.provider.namestringDevelopment

  The Generative AI provider as identified by the client or server instrumentation.

• gen_ai.request.choice.countintDevelopment

  The target number of candidate completions to return.

• gen_ai.request.encoding_formatsstring[]Development

  The encoding formats requested in an embeddings operation, if specified.

• gen_ai.request.frequency_penaltydoubleDevelopment

  The frequency penalty setting for the GenAI request.

• gen_ai.request.max_tokensintDevelopment

  The maximum number of tokens the model generates for a request.

• gen_ai.request.modelstringDevelopment

  The name of the GenAI model a request is being made to.

• gen_ai.request.presence_penaltydoubleDevelopment

  The presence penalty setting for the GenAI request.

• gen_ai.request.previous_response.idstringDevelopment

  The unique identifier of a previous response or interaction used to provide context for the current operation.

• gen_ai.request.reasoning.levelstringDevelopment

  The reasoning or thinking effort level requested for a GenAI model.

• gen_ai.request.seedintDevelopment

  Requests with same seed value more likely to return same result.

• gen_ai.request.stop_sequencesstring[]Development

  List of sequences that the model will use to stop generating further tokens.

• gen_ai.request.streambooleanDevelopment

  Indicates whether the GenAI request was made in streaming mode.

• gen_ai.request.stream_cursorstringDevelopment

  The cursor identifying the last streamed event already received, used to resume a streamed response from that position.

• gen_ai.request.temperaturedoubleDevelopment

  The temperature setting for the GenAI request.

• gen_ai.request.top_kintDevelopment

  The top-K sampling setting for the GenAI request: restricts token generation at each step to the K most likely next tokens.

• gen_ai.request.top_pdoubleDevelopment

  The top_p sampling setting for the GenAI request.

• gen_ai.response.finish_reasonsstring[]Development

  Array of reasons the model stopped generating tokens, corresponding to each generation received.

• gen_ai.response.idstringDevelopment

  The unique identifier for the completion.

• gen_ai.response.modelstringDevelopment

  The name of the model that generated the response.

• gen_ai.response.statusstringDevelopment

  The lifecycle status of a generated response, as reported by the provider when the response is fetched or polled.

• gen_ai.response.time_to_first_chunkdoubleDevelopment

  Time to first chunk in a streaming response, measured from request issuance, in seconds.

• gen_ai.retrieval.documentsanyDevelopment

  The documents retrieved.

• gen_ai.retrieval.query.textstringDevelopment

  The query text used for retrieval.

• gen_ai.retrieval.top_kintDevelopment

  The maximum number of documents the retriever was asked to return for the query (also known as k, limit, or max_num_results).

• gen_ai.skill.descriptionstringDevelopment

  The description of the Agent Skill.

• gen_ai.skill.namestringDevelopment

  The name of the Agent Skill.

• gen_ai.skill.resource.namestringDevelopment

  The skill-relative name of the resource (script, reference, or asset) being accessed or executed.

• gen_ai.skill.source.uristringDevelopment

  The source URI for loading the skill.

• gen_ai.system_instructionsanyDevelopment

  The system message or instructions provided to the GenAI model separately from the chat history.

• gen_ai.token.modalitystringDevelopment

  The modality of the tokens being counted.

• gen_ai.tool.call.argumentsanyDevelopment

  Parameters passed to the tool call.

• gen_ai.tool.call.idstringDevelopment

  The tool call identifier supplied by the model or provider.

• gen_ai.tool.call.resultanyDevelopment

  The result returned by the tool call (if any and if execution was successful).

• gen_ai.tool.definitionsanyDevelopment

  The list of tool definitions available to the GenAI agent or model.

• gen_ai.tool.descriptionstringDevelopment

  The tool description.

• gen_ai.tool.namestringDevelopment

  Name of the tool utilized by the agent.

• gen_ai.tool.typestringDevelopment

  Type of the tool utilized by the agent

• gen_ai.usage.audio.cache_read.input_tokensintDevelopment

  The number of audio input tokens served from a provider-managed cache.

• gen_ai.usage.audio.input_tokensintDevelopment

  The number of audio input tokens.

• gen_ai.usage.audio.output_tokensintDevelopment

  The number of audio output tokens.

• gen_ai.usage.cache_read.input_tokensintDevelopment

  The number of input tokens served from a provider-managed cache.

• gen_ai.usage.cache_write.input_tokensintDevelopment

  The number of input tokens written to a provider-managed cache.

• gen_ai.usage.image.cache_read.input_tokensintDevelopment

  The number of image input tokens served from a provider-managed cache.

• gen_ai.usage.image.input_tokensintDevelopment

  The number of image input tokens.

• gen_ai.usage.image.output_tokensintDevelopment

  The number of image output tokens.

• gen_ai.usage.input_tokensintDevelopment

  The number of tokens used in the GenAI input (prompt).

• gen_ai.usage.output_tokensintDevelopment

  The number of tokens used in the GenAI response (completion).

• gen_ai.usage.reasoning.output_tokensintDevelopment

  The number of output tokens used for reasoning (e.g.

• gen_ai.usage.text.cache_read.input_tokensintDevelopment

  The number of text input tokens served from a provider-managed cache.

• gen_ai.usage.text.input_tokensintDevelopment

  The number of text input tokens.

• gen_ai.usage.text.output_tokensintDevelopment

  The number of text output tokens.

• gen_ai.workflow.namestringDevelopment

  Human-readable name of the GenAI workflow provided by the application.

• gen_ai.completionstringDeprecated

  Removed, no replacement at this time.

• gen_ai.openai.request.response_formatstringDeprecated

  Replaced by gen_ai.output.type.

• gen_ai.openai.request.seedintDeprecated

  Replaced by gen_ai.request.seed.

• gen_ai.openai.request.service_tierstringDeprecated

  Replaced by openai.request.service_tier.

• gen_ai.openai.response.service_tierstringDeprecated

  Replaced by openai.response.service_tier.

• gen_ai.openai.response.system_fingerprintstringDeprecated

  Replaced by openai.response.system_fingerprint.

• gen_ai.promptstringDeprecated

  Removed, no replacement at this time.

• gen_ai.systemstringDeprecated

  Replaced by gen_ai.provider.name.

• gen_ai.token.typestringDeprecated

  Replaced, with the gen_ai.client.token.usage histogram it served, by per-direction token histograms and gen_ai.token.modality (changelog).

• gen_ai.usage.cache_creation.input_tokensintDeprecated

  Renamed to gen_ai.usage.cache_write.input_tokens (changelog).

• gen_ai.usage.completion_tokensintDeprecated

  Replaced by gen_ai.usage.output_tokens.

• gen_ai.usage.prompt_tokensintDeprecated

  Replaced by gen_ai.usage.input_tokens.

• mcp.method.namestringDevelopment

  The name of the request or notification method.

• mcp.protocol.versionstringDevelopment

  The version of the Model Context Protocol used.

• mcp.resource.uristringDevelopment

  The value of the resource uri.

• mcp.session.idstringDevelopment

  Identifies MCP session.

• rpc.methodstringRelease candidate

  The fully-qualified logical name of the method from the RPC interface perspective.

• rpc.method_originalstringRelease candidate

  The original name of the method used by the client.

• rpc.request.metadata.<key>string[]Development

  RPC request metadata, <key> being the normalized RPC metadata key (lowercase), the value being the metadata values.

• rpc.response.metadata.<key>string[]Development

  RPC response metadata, <key> being the normalized RPC metadata key (lowercase), the value being the metadata values.

• rpc.response.status_codestringRelease candidate

  Status code of the RPC returned by the RPC server or generated by the client

• rpc.system.namestringRelease candidate

  The Remote Procedure Call (RPC) system.

• rpc.connect_rpc.error_codestringDeprecated

  Renamed to rpc.response.status_code.

• rpc.connect_rpc.request.metadata.<key>string[]Deprecated

  Renamed to rpc.request.metadata.<key>.

• rpc.connect_rpc.response.metadata.<key>string[]Deprecated

  Renamed to rpc.response.metadata.<key>.

• rpc.grpc.request.metadata.<key>string[]Deprecated

  Renamed to rpc.request.metadata.<key>.

• rpc.grpc.response.metadata.<key>string[]Deprecated

  Renamed to rpc.response.metadata.<key>.

• rpc.grpc.status_codestringDeprecated

  Replaced by rpc.response.status_code.

• rpc.jsonrpc.error_codeintDeprecated

  Replaced by rpc.response.status_code.

• rpc.jsonrpc.error_messagestringDeprecated

  Use the span status description when reporting JSON-RPC spans.

• rpc.jsonrpc.request_idstringDeprecated

  Renamed to jsonrpc.request.id.

• rpc.jsonrpc.versionstringDeprecated

  Renamed to jsonrpc.protocol.version.

• rpc.message.compressed_sizeintDeprecated

  Deprecated, no replacement at this time.

• rpc.message.idintDeprecated

  Deprecated, no replacement at this time.

• rpc.message.typestringDeprecated

  Deprecated, no replacement at this time.

• rpc.message.uncompressed_sizeintDeprecated

  Deprecated, no replacement at this time.

• rpc.servicestringDeprecated

  Value should be included in rpc.method which is expected to be a fully-qualified name.

• rpc.systemstringDeprecated

  Renamed to rpc.system.name.

• jsonrpc.protocol.versionstringDevelopment

  Protocol version, as specified in the jsonrpc property of the request and its corresponding response.

• jsonrpc.request.idstringDevelopment

  A string representation of the id property of the request and its corresponding response.

• http.connection.statestringDevelopment

  State of the HTTP connection in the HTTP connection pool.

• http.request.body.sizeintDevelopment

  The size of the request payload body in bytes.

• http.request.header.<key>string[]Stable

  HTTP request headers, <key> being the normalized HTTP Header name (lowercase), the value being the header values.

• http.request.methodstringStable

  HTTP request method.

• http.request.method_originalstringStable

  Original HTTP method sent by the client in the request line.

• http.request.resend_countintStable

  The ordinal number of request resending attempt (for any reason, including redirects).

• http.request.sizeintDevelopment

  The total size of the request in bytes.

• http.response.body.sizeintDevelopment

  The size of the response payload body in bytes.

• http.response.header.<key>string[]Stable

  HTTP response headers, <key> being the normalized HTTP Header name (lowercase), the value being the header values.

• http.response.sizeintDevelopment

  The total size of the response in bytes.

• http.response.status_codeintStable

  HTTP response status code.

• http.routestringStable

  The matched route template for the request.

• http.client_ipstringDeprecated

  Renamed to client.address.

• http.flavorstringDeprecated

  Replaced by network.protocol.name.

• http.hoststringDeprecated

  Replaced by one of server.address, client.address or http.request.header.host, depending on the usage.

• http.methodstringDeprecated

  Renamed to http.request.method.

• http.request_content_lengthintDeprecated

  Replaced by http.request.header.content-length.

• http.request_content_length_uncompressedintDeprecated

  Renamed to http.request.body.size.

• http.response_content_lengthintDeprecated

  Replaced by http.response.header.content-length.

• http.response_content_length_uncompressedintDeprecated

  Renamed to http.response.body.size.

• http.schemestringDeprecated

  Renamed to url.scheme.

• http.server_namestringDeprecated

  Renamed to server.address.

• http.status_codeintDeprecated

  Renamed to http.response.status_code.

• http.targetstringDeprecated

  Replaced by url.path.

• http.urlstringDeprecated

  Renamed to url.full.

• http.user_agentstringDeprecated

  Renamed to user_agent.original.

• error.typestringStable

  Describes a class of error the operation ended with.

• error.messagestringDeprecated

  Use domain-specific error message attribute. For example, use feature_flag.error.message for feature flag errors.

• server.addressstringStable

  Server domain name if available without reverse DNS lookup.

• server.portintStable

  Server port number.

• client.addressstringStable

  Client address - domain name if available without reverse DNS lookup.

• client.portintStable

  Client port number.

• blockchain.system.namestringDevelopmenthashspan

  evm

• blockchain.chain.idintDevelopmenthashspan

  EIP-155 chain id, e.g.

• blockchain.operation.namestringDevelopmenthashspan

  send | confirm | payment

• blockchain.tx.hashstringDevelopmenthashspan

  0x-prefixed tx hash.

• blockchain.tx.fromstringDevelopmenthashspan

  sender address, subject to address mode

• blockchain.tx.tostringDevelopmenthashspan

  recipient / contract address, subject to address mode

• blockchain.tx.valuestringDevelopmenthashspan

  value in wei, decimal string

• blockchain.tx.nonceintDevelopmenthashspan

  sender nonce, when the sending call passes one (a nonce the wallet or viem picks is not known to the adapter)

• blockchain.tx.authorization.countintDevelopmenthashspan

  number of EIP-7702 authorizations a type 4 transaction carries

• blockchain.tx.authorization.addressesstring[]Developmenthashspan

  delegated contract address of each well-formed authorization, subject to address mode, at most 64.

• blockchain.tx.authorization.chain_idsint[]Developmenthashspan

  chain id of each well-formed authorization, in the order of the addresses, at most 64.

• blockchain.contract.function.namestringDevelopmenthashspan

  decoded function name when an ABI is known

• blockchain.contract.function.selectorstringDevelopmenthashspan

  4-byte selector, e.g.

• blockchain.contract.function.argumentsstringDevelopmenthashspan

  decoded call arguments as a JSON array, e.g.

• blockchain.tx.statusstringDevelopmenthashspan

  from chain data: success | reverted | replaced

• blockchain.block.numberintDevelopmenthashspan

  inclusion block.

• blockchain.tx.gas.usedintDevelopmenthashspan

  gas used

• blockchain.tx.effective_gas_pricestringDevelopmenthashspan

  price per gas in the chain's fee unit (see the fee table below), decimal string.

• blockchain.tx.l1_feestringDevelopmenthashspan

  L1 data fee on OP-stack chains, in the chain's fee unit.

• blockchain.tx.feestringDevelopmenthashspan

  gas.used × effective_gas_price + l1_fee, in the chain's fee unit: wei of the native currency, or the token fee_asset names (see the fee table below).

• blockchain.tx.operator_feestringDevelopmenthashspan

  OP Stack operator fee (Isthmus and later), wei, decimal string.

• blockchain.tx.fee_assetstringDevelopmenthashspan

  contract address of the token the fee was paid in, subject to address mode, as the chain reports it (a Celo fee currency, which for a 6-decimal token is its 18-decimal adapter contract.

• blockchain.tx.revert.reasonstringDevelopmenthashspan

  decoded revert reason when available, also of a reverted user operation: the Error(string) message, Panic(0x..), ErrorName(arg, ...) for custom errors with a known ABI, else the 4-byte error selector.

• blockchain.tx.replacement.hashstringDevelopmenthashspan

  on a replaced confirm span: hash of the mined transaction that replaced it

• blockchain.tx.replacement.reasonstringDevelopmenthashspan

  on a replaced confirm span: repriced | cancelled | replaced, as reported by the instrumented library.

• blockchain.tx.wait.confirmationsintDevelopmenthashspan

  on a transaction's confirm span: the confirmations (blocks, counting the receipt's own) that the wait which ended the span asked for, as the library applies them: a viem wait's or a CDP network-scoped wait's confirmations when it is a positive safe integer.

• blockchain.user_operation.hashstringDevelopmenthashspan

  0x-prefixed user operation hash (userOpHash), which identifies the operation with the chain id

• blockchain.user_operation.senderstringDevelopmenthashspan

  address of the smart account, subject to address mode

• blockchain.user_operation.entry_pointstringDevelopmenthashspan

  address of the EntryPoint contract, subject to address mode

• blockchain.user_operation.call_countintDevelopmenthashspan

  number of calls the operation makes, when the adapter knows them

• blockchain.user_operation.noncestringDevelopmenthashspan

  the operation's nonce, decimal string (a 192-bit key and a 64-bit sequence number)

• blockchain.user_operation.successbooleanDevelopmenthashspan

  whether the operation's calls succeeded.

• blockchain.user_operation.gas.usedintDevelopmenthashspan

  gas the operation used (actualGasUsed)

• blockchain.user_operation.gas.coststringDevelopmenthashspan

  what the operation paid (actualGasCost), wei, decimal string.

• blockchain.user_operation.paymasterstringDevelopmenthashspan

  address of the paymaster that paid for the operation, subject to address mode.

• blockchain.call_batch.idstringDevelopmenthashspan

  the batch id the wallet returned for EIP-5792 wallet_sendCalls (0x-prefixed hex, at most 8194 characters), truncated after 256 characters.

• blockchain.call_batch.senderstringDevelopmenthashspan

  address of the account the calls are sent from, subject to address mode

• blockchain.call_batch.call_countintDevelopmenthashspan

  number of calls in the batch

• blockchain.call_batch.statusstringDevelopmenthashspan

  the batch's outcome from chain data: success | reverted | partially_reverted.

• blockchain.call_batch.status_codeintDevelopmenthashspan

  the EIP-5792 status code the wallet reported, e.g.

• blockchain.call_batch.atomicbooleanDevelopmenthashspan

  whether the wallet ran the calls atomically

• blockchain.call_batch.transaction_hashesstring[]Developmenthashspan

  hashes of the transactions whose receipts the wallet reported for the batch, de-duplicated, at most 64

• blockchain.operation.subjectstringDevelopmenthashspan

  on metrics of user operations: user_operation.

• blockchain.fee.payerstringDevelopmenthashspan

  on blockchain.client.fee samples whose fee the sender of the traced transaction or operation did not pay: facilitator for a payment's settlement transaction that another party sent (x402), paymaster for a user operation a paymaster paid for, sponsor for a transaction whose receipt names another account as its fee payer (a Tempo feePayer).

• blockchain.fee.denominationstringDevelopmenthashspan

  on blockchain.client.fee samples whose fee was paid in a token rather than the chain's native currency: token, a constant, never an address or a value read from the chain.

• blockchain.payment.protocolstringDevelopmenthashspan

  x402 | mpp.

• blockchain.payment.payerstringDevelopmenthashspan

  address that pays, subject to address mode.

• blockchain.payment.recipientstringDevelopmenthashspan

  address that is paid, subject to address mode

• blockchain.payment.assetstringDevelopmenthashspan

  contract address of the token paid with, subject to address mode

• blockchain.payment.amountstringDevelopmenthashspan

  amount in the asset's smallest unit, decimal string.

• blockchain.payment.settled_amountstringDevelopmenthashspan

  amount the settling party reports it settled, decimal string, e.g.

• blockchain.payment.verifiedbooleanDevelopmenthashspan

  whether the settlement transaction carries this payment (its receipt and, for Permit2, its input.

• blockchain.payment.statusstringDevelopmenthashspan

  settled | pending | failed

• x402.schemestringDevelopmenthashspan

  x402 payment scheme, e.g.

• x402.resourcestringDevelopmenthashspan

  the resource paid for, per the tracker's paymentResource mode: origin (default) records scheme, host and port only, path the URL without query string, fragment or user info, off nothing.

• mpp.methodstringDevelopmenthashspan

  MPP payment method, e.g.

• mpp.intentstringDevelopmenthashspan

  MPP intent, e.g.

• mpp.modestringDevelopmenthashspan

  how an MPP charge is settled: push (the payer broadcasts) | pull (the server broadcasts what the payer signed)

• mpp.challenge.idstringDevelopmenthashspan

  id of the MPP challenge paid, chosen by the server: 1 to 128 characters of A-Z a-z 0-9 - .

• mpp.resourcestringDevelopmenthashspan

  the resource paid for, as x402.resource records it

No attribute matches. Try a shorter part of the name, set Stability to All to include renamed names, or suggest a namespace.

OpenTelemetry attribute names, types, stability and descriptions: © OpenTelemetry Authors, Apache-2.0, from open-telemetry/semantic-conventions (semantic-conventions v1.44.0 (e10a930)) and open-telemetry/semantic-conventions-genai.

Something wrong or out of date? Report a problem with this page.