Sign in

v48

latestOpenAPI 3.1.0raw.githubusercontent.com2026-05-275867561.6 MB
runs

Query runs

Alpha: The request and response contract may change; Returns a paginated list of runs for the given projects within min/max start_time. Supports filters, cursor pagination, and selects to select fields to return.

post/v2/runs/query

Headers

Acceptstring

application/json

Content-Typestring

application/json (required for JSON body)

Request body

ai_querystring

ai_query is a natural-language query to filter runs using AI.

cursorstring

cursor is the opaque string from a previous response's next_cursor.

filterstring

filter narrows results to runs matching this LangSmith filter expression, evaluated against each individual run. For example: and(eq(run_type, "llm"), gt(latency, 5)) or eq(status, "error"). See https://docs.langchain.com/langsmith/trace-query-syntax#filter-query-language for syntax.

has_errorboolean

has_error filters to runs that errored (true) or completed without error (false).

idsstring[]

ids optionally limits the request to these run UUIDs.

is_rootboolean

is_root returns only root runs (true) or only non-root runs (false).

max_start_timestring date-time

max_start_time is the upper bound for run start_time (RFC3339). Defaults to now.

min_start_timestring date-time

min_start_time is the lower bound for run start_time (RFC3339). Defaults to 1 day ago.

page_sizeinteger

page_size is the maximum number of runs to return in this response. Defaults to 100 when omitted; must be between 1 and 1000 inclusive when set.

project_idsstring[]

project_ids lists tracing project UUIDs to query. Required unless reference_dataset_id is set. Mutually exclusive with reference_dataset_id — set exactly one of them.

reference_dataset_idstring uuid

reference_dataset_id resolves session IDs server-side from the dataset. Required unless project_ids is set. Mutually exclusive with project_ids — set exactly one of them. When provided and min_start_time is omitted, the server derives it from the earliest session creation date.

reference_examplesstring[]

reference_examples optionally limits to runs linked to these dataset example UUIDs.

run_type'TOOL' | 'CHAIN' | 'LLM' | 'RETRIEVER' | 'EMBEDDING' | 'PROMPT' | 'PARSER'
selectsQueryRunSelectField[]

selects lists which properties to include on each returned run. If omitted, only id is returned. Properties not listed are omitted from each run object.

sort_order'ASC' | 'DESC'
trace_filterstring

trace_filter narrows results to runs whose root trace matches this LangSmith filter expression. Use this to filter by properties of the trace's root run — for example eq(status, "success") to include only traces that completed without error. See https://docs.langchain.com/langsmith/trace-query-syntax#filter-query-language for syntax.

trace_idstring uuid

trace_id optionally limits results to runs belonging to this trace UUID.

tree_filterstring

tree_filter narrows results to runs that belong to a trace containing at least one run matching this LangSmith filter expression anywhere in the run tree (not just the root). Use this to find runs inside traces that involved a specific tool, tag, or model — for example has(tags, "production") or eq(name, "my_tool"). See https://docs.langchain.com/langsmith/trace-query-syntax#filter-query-language for syntax.

Example request

{
  "ai_query": "runs that used tool calls",
  "cursor": "eyJsYXN0X2lkIjoiMDE4ZTRjN2UtYTlmYi03ZWYwLWE1YjYtNmVhM2E4MmU5MzI3In0=",
  "filter": "and(eq(run_type, \"llm\"), gt(latency, 5))",
  "ids": [
    "018e4c7e-a9fb-7ef0-a5b6-6ea3a82e9327",
    "f47ac10b-58cc-4372-a567-0e02b2c3d479"
  ],
  "is_root": true,
  "max_start_time": "2024-12-31T23:59:59Z",
  "min_start_time": "2024-01-01T00:00:00Z",
  "page_size": 100,
  "project_ids": [
    "018e4c7e-a9fb-7ef0-a5b6-6ea3a82e9327",
    "0190a1b2-c3d4-7ef0-a5b6-6ea3a82e9328"
  ],
  "reference_dataset_id": "018e4c7e-a9fb-7ef0-a5b6-6ea3a82e9327",
  "reference_examples": [
    "b2c3d4e5-f6a7-4b5c-9d0e-1f2a3b4c5d6e",
    "c3d4e5f6-a7b8-4c5d-0e1f-2a3b4c5d6e7f"
  ],
  "selects": [
    "ID",
    "NAME",
    "PROJECT_ID",
    "START_TIME",
    "RUN_TYPE",
    "STATUS"
  ],
  "trace_filter": "eq(status, \"success\")",
  "trace_id": "f47ac10b-58cc-4372-a567-0e02b2c3d479",
  "tree_filter": "has(tags, \"production\")"
}

Response

OK

next_cursorstring

next_cursor is the opaque cursor to pass as cursor on the next request. Omitted on the final page.

Example response

{
  "items": [
    {
      "app_path": "/app/chains/chat.py:invoke",
      "completion_cost": 0.0003,
      "completion_tokens": 150,
      "dotted_order": "20240115T103000000000Z018e4c7ea9fb7ef0a5b66ea3a82e9327.",
      "end_time": "2024-01-15T10:30:01.500Z",
      "error": "context deadline exceeded",
      "events": [
        {
          "name": "new_token",
          "time": "2024-01-15T10:30:00.312Z"
        }
      ],
      "first_token_time": "2024-01-15T10:30:00.312Z",
      "id": "018e4c7e-a9fb-7ef0-a5b6-6ea3a82e9327",
      "is_in_dataset": true,
      "is_root": true,
      "latency_seconds": 1.523,
      "name": "ChatOpenAI",
      "parent_run_ids": [
        "018e4c7e-a9fb-7ef0-a5b6-6ea3a82e9327",
        "a1b2c3d4-e5f6-4a5b-8c9d-0e1f2a3b4c5d"
      ],
      "price_model_id": "e5f6a7b8-c9d0-4e1f-2a3b-4c5d6e7f8a9b",
      "project_id": "018e4c7e-a9fb-7ef0-a5b6-6ea3a82e9327",
      "prompt_cost": 0.0002,
      "prompt_tokens": 200,
      "reference_dataset_id": "c3d4e5f6-a7b8-4c5d-0e1f-2a3b4c5d6e7f",
      "reference_example_id": "b2c3d4e5-f6a7-4b5c-9d0e-1f2a3b4c5d6e",
      "share_url": "https://smith.langchain.com/public/4f7a1b2c-8d9e-4a0b-9c1d-2e3f4a5b6c7d/r",
      "start_time": "2024-01-15T10:30:00.000Z",
      "tags": [
        "production",
        "gpt-4"
      ],
      "thread_id": "d4e5f6a7-b8c9-4d5e-1f2a-3b4c5d6e7f8a",
      "total_cost": 0.000525,
      "total_tokens": 350,
      "trace_id": "018e4c7e-a9fb-7ef0-a5b6-6ea3a82e9327"
    }
  ],
  "next_cursor": "eyJsYXN0X2lkIjoiMDE4ZTRjN2UtYTlmYi03ZWYwLWE1YjYtNmVhM2E4MmU5MzI3In0="
}