Span Attributes

string / object / array — Universal input to the model. Required. Format depends on the log type.

string / object / array — Model’s response. Required. Format depends on the log type.

array — (Legacy) Messages sent to the model. Use input instead.

object — (Legacy) Final assistant message. Use output instead.

object — Complete request payload sent to the provider. Tool calls and function definitions are auto-extracted.

object — Full response object from the provider.

string — Request start time in RFC3339 format (e.g. "2025-09-08T07:46:14.007279Z").

string — Request end time in RFC3339 format.

number — Total request latency in seconds.

number — Time to first token in seconds. Useful for measuring streaming responsiveness.

number — Output token throughput (tokens per second).

number — Total request cost in USD. Auto-calculated from model and token counts if omitted.

object — Token usage breakdown.

integer — Number of tokens served from cache.

integer — Number of tokens added to cache.

integer — Reasoning tokens used (subset of completion_tokens). Applies to models with chain-of-thought reasoning (e.g., o3, gpt-5).

number — Time spent on routing/preprocessing in seconds.

number — Custom price per 1M prompt tokens. Use for self-hosted or fine-tuned models.

number — Custom price per 1M completion tokens.

string — Unique identifier for the log. Auto-generated if not provided.

string — Model name (e.g. "gpt-4o", "claude-3-5-sonnet-20240620"). Required.

string — Type of log. Defaults to "chat". See Log types.

string — Provider identifier (e.g. "openai", "anthropic").

string — Runtime environment (e.g. "test", "prod"). Used to separate test and production data.

string (max 254 characters) — User or customer-level identifier. Auto-truncated if exceeded. See Customer identifier.

object — Extended customer info: customer_identifier, name, email.

object — Custom key-value pairs for tagging, analytics, and filtering. All values are coerced to strings.

object — Typed metadata that preserves native types (numbers, booleans, nested objects). Unlike metadata, values are not coerced to strings.

string — Indexed custom identifier for fast querying.

string — Conversation thread identifier. Logs with the same value are grouped into a thread.

string — Group identifier for related logs.

string — Prompt template identifier. Auto-set when using prompt management.

string — Prompt template name.

integer — Prompt version number.

string — Deployment name.

string — API key identifier used for the request.

string — Required. Groups all spans into a single trace. All spans sharing this ID form one trace.

string — Required. Unique identifier for this span within the trace.

string — Parent span ID. Creates the hierarchical tree structure. Omit or set to null for root spans.

string — Descriptive name for the operation (e.g. "openai.chat", "retrieval.search").

string — The nearest workflow this span belongs to. Used to label the root-level workflow in trace views.

string — Nested path within the workflow hierarchy.

string — Groups related traces together, even across different sessions or systems.

object — Additional Respan parameters passed via the tracing SDK.

integer — HTTP status code. Defaults to 200.

string — Semantic status: "success" or "error".

string — Error description if the request failed.

string / object — Non-fatal issues encountered during the request.

number — Randomness control (0–2).

integer — Maximum number of tokens to generate.

number — Nucleus sampling parameter (0–1).

number — Penalizes tokens based on frequency (0–2).

number — Penalizes tokens already present (0–2).

array — Sequences that halt generation.

integer — Number of completions to generate.

boolean — Whether the response was streamed.

object — Output format: text, json_schema, or json_object.

array — Available tool/function definitions.

string / object — Controls tool selection: "none", "auto", or specific tool.

boolean | null — User sentiment annotation. true = positive, false = negative, null = no annotation.

string — Annotation note text attached to the span.

object — Map of evaluator scores { evaluator_id: { evaluator_name, evaluator_slug, score_value } }. Sortable and filterable using the scores__ prefix pattern.

array — Tools/functions called by the model in the response.

boolean — Whether the span is pinned (exempt from retention TTL deletion). Pinned spans are preserved indefinitely. Default: false.

boolean — Whether the span content is blurred for privacy (based on plan’s log retention limits).

boolean — When true, omits input/output messages from the log (metrics still recorded).

boolean — When true, adds detailed metrics (tokens, cost, latency) to the response body.

object — Logging behavior controls.

string — Required. Groups all spans into a single trace. All spans sharing this ID form one trace view.

string — Required. Unique identifier for this span within the trace.

string — Parent span ID. Creates the hierarchical tree structure. Omit or set to null for root spans.

string — Descriptive name for the operation (e.g. "openai.chat", "retrieval.search", "generate_outline").

string — The workflow this span belongs to. Labels the root-level workflow in trace views.

string — Hierarchical path within the workflow (e.g. "content_pipeline.generate_outline"). Auto-set by the tracing SDK decorators.

string — Groups related traces together across sessions or systems.