Retrieve an experiment trace

{
  "id": "trace_456",
  "trace_unique_id": "trace_456",
  "root_span_unique_id": "string",
  "environment": "prod",
  "customer_identifier": "string",
  "name": "Dataset Entry 1",
  "input": null,
  "output": null,
  "expected_output": null,
  "status": "success",
  "comparison_key": "string",
  "start_time": "2024-01-15T09:30:00Z",
  "end_time": "2024-01-15T09:30:00Z",
  "duration": 1.1,
  "span_count": 1,
  "llm_call_count": 1,
  "total_cost": 0.0012,
  "total_tokens": 1,
  "total_prompt_tokens": 1,
  "total_completion_tokens": 1,
  "error_count": 1,
  "scores": {},
  "span_tree": [
    {
      "id": "trace_456",
      "trace_unique_id": "trace_456",
      "root_span_unique_id": "string",
      "environment": "prod",
      "customer_identifier": "string",
      "name": "Dataset Entry 1",
      "input": null,
      "output": null,
      "expected_output": null,
      "status": "success",
      "comparison_key": "string",
      "start_time": "2024-01-15T09:30:00Z",
      "end_time": "2024-01-15T09:30:00Z",
      "duration": 1.1,
      "span_count": 1,
      "llm_call_count": 1,
      "total_cost": 0.0012,
      "total_tokens": 1,
      "total_prompt_tokens": 1,
      "total_completion_tokens": 1,
      "error_count": 1,
      "scores": {},
      "span_name": "workflow.completion",
      "log_type": "chat",
      "model": "string",
      "children": [
        {}
      ]
    }
  ]
}

Retrieve one experiment trace with its full span tree and enriched evaluator scores.

Authentication

AuthorizationBearer

Use your Respan API key for Respan API authentication. Enter only the Respan API key value; clients send Authorization: Bearer <RESPAN_API_KEY>. For /api/responses, provider credentials such as Perplexity, OpenAI, or Azure OpenAI go in Settings -> Providers or respan_params.credential_override in the request body, not in this authentication field.

AuthorizationBearer

Use a dashboard JWT only for dashboard-authenticated endpoints. Respan API-key endpoints use the respanApiKey auth field instead.

Path parameters

experiment_idstringRequired

Experiment ID returned as id in experiment responses.

log_idstringRequired

Trace ID returned as id in experiment trace list responses.

Response

Experiment trace details.

idstring

Trace ID. Use this value as log_id for trace detail and wait-workflow resume routes.

trace_unique_idstringOptional

Trace unique ID.

root_span_unique_idstring or nullOptional

environmentstring or nullOptional

customer_identifierstring or nullOptional

namestring or nullOptional

inputany or nullOptional

Trace input. May be a JSON value or serialized JSON string depending on storage.

outputany or nullOptional

Trace output. May be a JSON value or serialized JSON string depending on storage.

expected_outputany or nullOptional

Expected output from the dataset row, when available.

statusstring or nullOptional

comparison_keystring or nullOptional

Stable key for comparing the same input across experiments.

start_timedatetime or nullOptional

end_timedatetime or nullOptional

durationdouble or nullOptional

Trace duration in seconds.

span_countinteger or nullOptional

llm_call_countinteger or nullOptional

total_costdouble or nullOptional

total_tokensinteger or nullOptional

total_prompt_tokensinteger or nullOptional

total_completion_tokensinteger or nullOptional

error_countinteger or nullOptional

scoresmap from strings to objectsOptional

Scores keyed by evaluator ID or slug. Each value includes evaluator metadata and the score value field matching score_value_type.

span_treelist of objectsOptional

Hierarchical span tree for this trace.

Errors

401

Unauthorized Error

404

Not Found Error

413

Content Too Large Error