Query Single Thread Stats
Alpha: The request and response contract may change; Compute aggregate stats for a single thread (turn count, latency percentiles, token/cost sums, and detail breakdowns) within a project.
Path Parameters
Thread ID
Query Parameters
filter narrows which of the thread's traces are aggregated, using a LangSmith filter expression. For example: lt(start_time, "2025-01-01T00:00:00Z") or eq(trace_id, "0190a1b2-c3d4-7ef0-a5b6-6ea3a82e9328").
See https://docs.langchain.com/langsmith/trace-query-syntax#filter-query-language for syntax.
selects lists which aggregate stats to compute and return (repeatable query parameter). At least one value is required. Accepts any value of SingleThreadStatsSelectField.
TURNS, FIRST_START_TIME, LAST_START_TIME, LAST_END_TIME, LATENCY_P50, LATENCY_P99, PROMPT_TOKENS, PROMPT_COST, COMPLETION_TOKENS, COMPLETION_COST, TOTAL_TOKENS, TOTAL_COST, PROMPT_TOKEN_DETAILS, COMPLETION_TOKEN_DETAILS, PROMPT_COST_DETAILS, COMPLETION_COST_DETAILS, FEEDBACK_STATS session_id is the tracing project (session) UUID (required).
Response
aggregate stats for the thread
completion_cost is the sum of per-trace completion costs across the thread, in USD. Populated when COMPLETION_COST is selected.
completion_cost_details is the per-sub-category sum of completion cost details across the thread. Populated when COMPLETION_COST_DETAILS is selected.
completion_token_details is the per-sub-category sum of completion token details across the thread. Populated when COMPLETION_TOKEN_DETAILS is selected.
completion_tokens is the sum of per-trace completion token counts across the thread. Populated when COMPLETION_TOKENS is selected.
feedback_stats aggregates run-level feedback across the thread's traces, keyed by feedback key. Populated when FEEDBACK_STATS is selected.
first_start_time is the earliest trace start time in the thread (RFC3339). Populated when FIRST_START_TIME is selected.
last_end_time is the latest trace end time in the thread (RFC3339). Populated when LAST_END_TIME is selected.
last_start_time is the latest trace start time in the thread (RFC3339). Populated when LAST_START_TIME is selected.
latency_p50_seconds is the approximate p50 of trace latency across the thread, in seconds. Populated when LATENCY_P50 is selected.
latency_p99_seconds is the approximate p99 of trace latency across the thread, in seconds. Populated when LATENCY_P99 is selected.
prompt_cost is the sum of per-trace prompt costs across the thread, in USD. Populated when PROMPT_COST is selected.
prompt_cost_details is the per-sub-category sum of prompt cost details across the thread. Populated when PROMPT_COST_DETAILS is selected.
prompt_token_details is the per-sub-category sum of prompt token details across the thread. Populated when PROMPT_TOKEN_DETAILS is selected.
prompt_tokens is the sum of per-trace prompt token counts across the thread. Populated when PROMPT_TOKENS is selected.
total_cost is the sum of per-trace total costs across the thread, in USD. Populated when TOTAL_COST is selected.
total_tokens is the sum of per-trace total token counts across the thread. Populated when TOTAL_TOKENS is selected.
turns is the number of distinct traces (turns) in the thread. Populated when TURNS is selected.

