Get span summary
https://api.respan.ai/api/request-logs/summary/Returns aggregate span statistics for a time range. Send start_time, end_time, and environment as query parameters, and additional filters in the JSON body. Fields such as log_type are not read from query parameters. Empty or omitted filters may use pre-aggregated data; non-empty filters query individual spans using the List spans filter format.
Servers
https://api.respan.ai: Respan API Server
Authentication
RespanApiKey
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.
HTTP scheme: bearer; format: Respan API key.
Authorization: Bearer $RESPAN_API_KEYOr:
DashboardJwt
Use a dashboard JWT only for dashboard-authenticated endpoints. Respan API-key endpoints use the respanApiKey auth field instead.
HTTP scheme: bearer; format: Dashboard JWT.
Authorization: Bearer $RESPAN_DASHBOARD_JWTQuery parameters
start_time string OptionalFormat:
date-timeExample:
"2025-01-01T00:00:00Z"end_time string OptionalFormat:
date-timeExample:
"2025-01-31T23:59:59Z"environment string Optionalprod or test).Allowed:
"prod", "test"Example:
"prod"Request body
The request body is optional.
application/json
$ object Optional body
filters object Optional
{"<field>": {"operator": "<operator>", "value": [...]}}. A span must match every condition. To set two conditions on one field, such as a range, pass a list of conditions.Operators:
"" (equals, the default), not, in, not_in, lt, lte, gt, gte, contains, not_contains, icontains (ignores case), startswith, not_startswith, endswith, not_endswith, empty, not_empty. Put values in a list: "" and in match any of the listed values, and not and not_in match none of them. Other operators take one value; for empty and not_empty, send [""].Fields:
-
unique_id, trace_unique_id, span_unique_id, span_parent_id, span_name, span_workflow_name, thread_identifier, customer_identifier, customer_email, custom_identifier, group_identifier, evaluation_identifier, organization_key_id, prompt_id, prompt_name, prompt_version_number, model, provider_id, deployment_name, log_type, log_method, status, status_code, environment, error_class, error_code, error_message, error_fingerprint, cache_key, note- True or false:
stream, has_tool_calls, cache_bit, used_custom_credential, positive_feedback- Numbers:
cost, latency, time_to_first_token, tokens_per_second, routing_time, prompt_tokens, completion_tokens, total_request_tokens, prompt_cache_hit_tokens, prompt_cache_creation_tokens. The aliases total_cost, input_tokens, output_tokens and total_tokens also work, and so does trace_id for trace_unique_id.-
metadata__<key>: a custom metadata value. Values are strings, and spans without the key never match, even with not.-
scores__<evaluator_id>: an evaluator’s numeric score, with "", not, in, not_in, lt, lte, gt or gte.-
is_root_span ([true] or [false]), fault_domain (user, respan or provider), and behaviors (spans where the named behaviors fired, when span behaviors are on).Unsupported fields return a 400 error.
Example:
json<br />{<br /> "customer_identifier": {"operator": "", "value": ["alex@acme.dev"]},<br /> "status_code": {"operator": "not", "value": [200]}<br />}<br />Reference:
#/components/schemas/FiltersExample:
{"customer_identifier":{"operator":"","value":["alex@acme.dev"]}}filters.status object Optional
Reference:
#/components/schemas/FilterValuefilters.status.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.status.value array<any> Required in parent
Example:
[0.01]filters.status.value[] any Array itemfilters.status_code object Optional
Reference:
#/components/schemas/FilterValuefilters.status_code.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.status_code.value array<any> Required in parent
Example:
[0.01]filters.status_code.value[] any Array itemfilters.unique_id object Optional
Reference:
#/components/schemas/FilterValuefilters.unique_id.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.unique_id.value array<any> Required in parent
Example:
[0.01]filters.unique_id.value[] any Array itemfilters.customer_identifier object Optional
Reference:
#/components/schemas/FilterValuefilters.customer_identifier.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.customer_identifier.value array<any> Required in parent
Example:
[0.01]filters.customer_identifier.value[] any Array itemfilters.thread_identifier object Optional
Reference:
#/components/schemas/FilterValuefilters.thread_identifier.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.thread_identifier.value array<any> Required in parent
Example:
[0.01]filters.thread_identifier.value[] any Array itemfilters.custom_identifier object Optional
Reference:
#/components/schemas/FilterValuefilters.custom_identifier.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.custom_identifier.value array<any> Required in parent
Example:
[0.01]filters.custom_identifier.value[] any Array itemfilters.group_identifier object Optional
Reference:
#/components/schemas/FilterValuefilters.group_identifier.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.group_identifier.value array<any> Required in parent
Example:
[0.01]filters.group_identifier.value[] any Array itemfilters.prompt_id object Optional
Reference:
#/components/schemas/FilterValuefilters.prompt_id.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.prompt_id.value array<any> Required in parent
Example:
[0.01]filters.prompt_id.value[] any Array itemfilters.trace_unique_id object Optional
Reference:
#/components/schemas/FilterValuefilters.trace_unique_id.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.trace_unique_id.value array<any> Required in parent
Example:
[0.01]filters.trace_unique_id.value[] any Array itemfilters.span_parent_id object Optional
Reference:
#/components/schemas/FilterValuefilters.span_parent_id.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.span_parent_id.value array<any> Required in parent
Example:
[0.01]filters.span_parent_id.value[] any Array itemfilters.is_root_span object Optional
Reference:
#/components/schemas/FilterValuefilters.is_root_span.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.is_root_span.value array<any> Required in parent
Example:
[0.01]filters.is_root_span.value[] any Array itemfilters.span_workflow_name object Optional
Reference:
#/components/schemas/FilterValuefilters.span_workflow_name.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.span_workflow_name.value array<any> Required in parent
Example:
[0.01]filters.span_workflow_name.value[] any Array itemfilters.span_name object Optional
Reference:
#/components/schemas/FilterValuefilters.span_name.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.span_name.value array<any> Required in parent
Example:
[0.01]filters.span_name.value[] any Array itemfilters.model object Optional
Reference:
#/components/schemas/FilterValuefilters.model.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.model.value array<any> Required in parent
Example:
[0.01]filters.model.value[] any Array itemfilters.log_type object Optional
Reference:
#/components/schemas/FilterValuefilters.log_type.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.log_type.value array<any> Required in parent
Example:
[0.01]filters.log_type.value[] any Array itemfilters.stream object Optional
Reference:
#/components/schemas/FilterValuefilters.stream.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.stream.value array<any> Required in parent
Example:
[0.01]filters.stream.value[] any Array itemfilters.has_tool_calls object Optional
Reference:
#/components/schemas/FilterValuefilters.has_tool_calls.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.has_tool_calls.value array<any> Required in parent
Example:
[0.01]filters.has_tool_calls.value[] any Array itemfilters.cache_bit object Optional
Reference:
#/components/schemas/FilterValuefilters.cache_bit.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.cache_bit.value array<any> Required in parent
Example:
[0.01]filters.cache_bit.value[] any Array itemfilters.cache_key object Optional
Reference:
#/components/schemas/FilterValuefilters.cache_key.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.cache_key.value array<any> Required in parent
Example:
[0.01]filters.cache_key.value[] any Array itemfilters.prompt_tokens object Optional
Reference:
#/components/schemas/FilterValuefilters.prompt_tokens.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.prompt_tokens.value array<any> Required in parent
Example:
[0.01]filters.prompt_tokens.value[] any Array itemfilters.completion_tokens object Optional
Reference:
#/components/schemas/FilterValuefilters.completion_tokens.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.completion_tokens.value array<any> Required in parent
Example:
[0.01]filters.completion_tokens.value[] any Array itemfilters.total_tokens object Optional
Reference:
#/components/schemas/FilterValuefilters.total_tokens.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.total_tokens.value array<any> Required in parent
Example:
[0.01]filters.total_tokens.value[] any Array itemfilters.cost object Optional
Reference:
#/components/schemas/FilterValuefilters.cost.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.cost.value array<any> Required in parent
Example:
[0.01]filters.cost.value[] any Array itemfilters.latency object Optional
Reference:
#/components/schemas/FilterValuefilters.latency.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.latency.value array<any> Required in parent
Example:
[0.01]filters.latency.value[] any Array itemfilters.positive_feedback object Optional
Reference:
#/components/schemas/FilterValuefilters.positive_feedback.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.positive_feedback.value array<any> Required in parent
Example:
[0.01]filters.positive_feedback.value[] any Array itemfilters.<key> object Map value
Reference:
#/components/schemas/FilterValuefilters.<key>.operator string OptionalAllowed:
"", "not", "in", "not_in", "lt", "lte", "gt", "gte", "contains", "not_contains", "icontains", "startswith", "not_startswith", "endswith", "not_endswith", "empty", "not_empty"Default: “
Example:
"gte"filters.<key>.value array<any> Required in parent
Example:
[0.01]filters.<key>.value[] any Array itemOpenAPI request schema
{
"type": "object",
"properties": {
"filters": {
"$ref": "#/components/schemas/Filters",
"description": "Each key is a field to filter on, and each value is a condition: `{\"<field>\": {\"operator\": \"<operator>\", \"value\": [...]}}`. A span must match every condition. To set two conditions on one field, such as a range, pass a list of conditions.\n\n**Operators:** `\"\"` (equals, the default), `not`, `in`, `not_in`, `lt`, `lte`, `gt`, `gte`, `contains`, `not_contains`, `icontains` (ignores case), `startswith`, `not_startswith`, `endswith`, `not_endswith`, `empty`, `not_empty`. Put values in a list: `\"\"` and `in` match any of the listed values, and `not` and `not_in` match none of them. Other operators take one value; for `empty` and `not_empty`, send `[\"\"]`.\n\n**Fields:**\n- `unique_id`, `trace_unique_id`, `span_unique_id`, `span_parent_id`, `span_name`, `span_workflow_name`, `thread_identifier`, `customer_identifier`, `customer_email`, `custom_identifier`, `group_identifier`, `evaluation_identifier`, `organization_key_id`, `prompt_id`, `prompt_name`, `prompt_version_number`, `model`, `provider_id`, `deployment_name`, `log_type`, `log_method`, `status`, `status_code`, `environment`, `error_class`, `error_code`, `error_message`, `error_fingerprint`, `cache_key`, `note`\n- True or false: `stream`, `has_tool_calls`, `cache_bit`, `used_custom_credential`, `positive_feedback`\n- Numbers: `cost`, `latency`, `time_to_first_token`, `tokens_per_second`, `routing_time`, `prompt_tokens`, `completion_tokens`, `total_request_tokens`, `prompt_cache_hit_tokens`, `prompt_cache_creation_tokens`. The aliases `total_cost`, `input_tokens`, `output_tokens` and `total_tokens` also work, and so does `trace_id` for `trace_unique_id`.\n- `metadata__<key>`: a custom metadata value. Values are strings, and spans without the key never match, even with `not`.\n- `scores__<evaluator_id>`: an evaluator's numeric score, with `\"\"`, `not`, `in`, `not_in`, `lt`, `lte`, `gt` or `gte`.\n- `is_root_span` (`[true]` or `[false]`), `fault_domain` (`user`, `respan` or `provider`), and `behaviors` (spans where the named behaviors fired, when span behaviors are on).\n\nUnsupported fields return a 400 error.\n\n**Example:**\n\n```json\n{\n \"customer_identifier\": {\"operator\": \"\", \"value\": [\"alex@acme.dev\"]},\n \"status_code\": {\"operator\": \"not\", \"value\": [200]}\n}\n```"
}
}
}No additional filters
{
"filters": {}
}Filter by span/log type
{
"filters": {
"log_type": {
"operator": "",
"value": [
"chat"
]
}
}
}Responses
200
Summary statistics for matching spans.
application/json
$ object Body
{"number_of_requests":1,"total_cost":0,"total_tokens":0,"total_prompt_tokens":0,"total_completion_tokens":0,"avg_latency":0,"avg_tps":0,"avg_ttft":0,"scores":{}}number_of_requests integer Required in parentExample:
1024total_cost number Required in parentExample:
12.45total_tokens integer Required in parentExample:
150000total_prompt_tokens integer Required in parentExample:
80000total_completion_tokens integer Required in parentExample:
70000avg_latency number Required in parentExample:
1.35avg_tps number Required in parentExample:
45.2avg_ttft number Required in parentExample:
0.35scores object Required in parentAdditional properties are allowed
Example:
{}OpenAPI response schema
{
"type": "object",
"required": [
"number_of_requests",
"total_cost",
"total_tokens",
"total_prompt_tokens",
"total_completion_tokens",
"avg_latency",
"avg_tps",
"avg_ttft",
"scores"
],
"properties": {
"number_of_requests": {
"type": "integer",
"description": "Total number of matching spans/log rows.",
"example": 1024
},
"total_cost": {
"type": "number",
"description": "Total cost in USD for all matching spans/log rows.",
"example": 12.45
},
"total_tokens": {
"type": "integer",
"description": "Total tokens across all matching spans/log rows.",
"example": 150000
},
"total_prompt_tokens": {
"type": "integer",
"description": "Total prompt/input tokens.",
"example": 80000
},
"total_completion_tokens": {
"type": "integer",
"description": "Total completion/output tokens.",
"example": 70000
},
"avg_latency": {
"type": "number",
"description": "Average latency in seconds.",
"example": 1.35
},
"avg_tps": {
"type": "number",
"description": "Average tokens per second.",
"example": 45.2
},
"avg_ttft": {
"type": "number",
"description": "Average time to first token in seconds.",
"example": 0.35
},
"scores": {
"type": "object",
"additionalProperties": true,
"description": "Aggregated score summaries grouped by evaluator ID.",
"example": {}
}
},
"example": {
"number_of_requests": 1,
"total_cost": 0,
"total_tokens": 0,
"total_prompt_tokens": 0,
"total_completion_tokens": 0,
"avg_latency": 0,
"avg_tps": 0,
"avg_ttft": 0,
"scores": {}
}
}400
Bad Request
application/json
$ object Body
error string OptionalExample:
"Invalid request body"OpenAPI response schema
{
"type": "object",
"properties": {
"error": {
"type": "string",
"description": "Error message",
"example": "Invalid request body"
}
}
}403
The API key is missing, invalid or expired.
application/json
$ object Body
detail string Required in parentOpenAPI response schema
{
"type": "object",
"required": [
"detail"
],
"properties": {
"detail": {
"type": "string"
}
}
}Example
{
"detail": "Your API key is invalid or expired, please check your API key in the platform settings."
}413
The query exceeded the service’s memory or execution-time limit. Narrow the time range or add filters before retrying.
application/json
$ object Body
detail string Required in parentOpenAPI response schema
{
"type": "object",
"required": [
"detail"
],
"properties": {
"detail": {
"type": "string"
}
}
}Example
{
"detail": "This query is too large to run — it exceeded a per-query resource limit. Narrow the time range or add filters, then try again."
}429
Rate Limited
application/json
$ object Body
error string OptionalExample:
"Rate limit exceeded"OpenAPI response schema
{
"type": "object",
"properties": {
"error": {
"type": "string",
"description": "Error message",
"example": "Rate limit exceeded"
}
}
}500
Internal Server Error
application/json
$ object Body
error string OptionalExample:
"Internal server error"OpenAPI response schema
{
"type": "object",
"properties": {
"error": {
"type": "string",
"description": "Error message",
"example": "Internal server error"
}
}
}OpenAPI source
The operation and referenced components below retain the complete OpenAPI definitions, including constraints and examples.
OpenAPI operation
{
"summary": "Get span summary",
"operationId": "getSpansSummary",
"tags": [
"Spans"
],
"description": "Returns aggregate span statistics for a time range. Send `start_time`, `end_time`, and `environment` as query parameters, and additional `filters` in the JSON body. Fields such as `log_type` are not read from query parameters. Empty or omitted `filters` may use pre-aggregated data; non-empty `filters` query individual spans using the List spans filter format.",
"parameters": [
{
"name": "start_time",
"in": "query",
"schema": {
"type": "string",
"format": "date-time"
},
"description": "Start of time range (ISO 8601).",
"example": "2025-01-01T00:00:00Z"
},
{
"name": "end_time",
"in": "query",
"schema": {
"type": "string",
"format": "date-time"
},
"description": "End of time range (ISO 8601).",
"example": "2025-01-31T23:59:59Z"
},
{
"name": "environment",
"in": "query",
"schema": {
"type": "string",
"enum": [
"prod",
"test"
]
},
"description": "Filter by environment (`prod` or `test`).",
"example": "prod"
}
],
"requestBody": {
"required": false,
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"filters": {
"$ref": "#/components/schemas/Filters",
"description": "Each key is a field to filter on, and each value is a condition: `{\"<field>\": {\"operator\": \"<operator>\", \"value\": [...]}}`. A span must match every condition. To set two conditions on one field, such as a range, pass a list of conditions.\n\n**Operators:** `\"\"` (equals, the default), `not`, `in`, `not_in`, `lt`, `lte`, `gt`, `gte`, `contains`, `not_contains`, `icontains` (ignores case), `startswith`, `not_startswith`, `endswith`, `not_endswith`, `empty`, `not_empty`. Put values in a list: `\"\"` and `in` match any of the listed values, and `not` and `not_in` match none of them. Other operators take one value; for `empty` and `not_empty`, send `[\"\"]`.\n\n**Fields:**\n- `unique_id`, `trace_unique_id`, `span_unique_id`, `span_parent_id`, `span_name`, `span_workflow_name`, `thread_identifier`, `customer_identifier`, `customer_email`, `custom_identifier`, `group_identifier`, `evaluation_identifier`, `organization_key_id`, `prompt_id`, `prompt_name`, `prompt_version_number`, `model`, `provider_id`, `deployment_name`, `log_type`, `log_method`, `status`, `status_code`, `environment`, `error_class`, `error_code`, `error_message`, `error_fingerprint`, `cache_key`, `note`\n- True or false: `stream`, `has_tool_calls`, `cache_bit`, `used_custom_credential`, `positive_feedback`\n- Numbers: `cost`, `latency`, `time_to_first_token`, `tokens_per_second`, `routing_time`, `prompt_tokens`, `completion_tokens`, `total_request_tokens`, `prompt_cache_hit_tokens`, `prompt_cache_creation_tokens`. The aliases `total_cost`, `input_tokens`, `output_tokens` and `total_tokens` also work, and so does `trace_id` for `trace_unique_id`.\n- `metadata__<key>`: a custom metadata value. Values are strings, and spans without the key never match, even with `not`.\n- `scores__<evaluator_id>`: an evaluator's numeric score, with `\"\"`, `not`, `in`, `not_in`, `lt`, `lte`, `gt` or `gte`.\n- `is_root_span` (`[true]` or `[false]`), `fault_domain` (`user`, `respan` or `provider`), and `behaviors` (spans where the named behaviors fired, when span behaviors are on).\n\nUnsupported fields return a 400 error.\n\n**Example:**\n\n```json\n{\n \"customer_identifier\": {\"operator\": \"\", \"value\": [\"alex@acme.dev\"]},\n \"status_code\": {\"operator\": \"not\", \"value\": [200]}\n}\n```"
}
}
},
"examples": {
"empty": {
"summary": "No additional filters",
"value": {
"filters": {}
}
},
"log_type": {
"summary": "Filter by span/log type",
"value": {
"filters": {
"log_type": {
"operator": "",
"value": [
"chat"
]
}
}
}
}
}
}
}
},
"responses": {
"200": {
"description": "Summary statistics for matching spans.",
"content": {
"application/json": {
"schema": {
"type": "object",
"required": [
"number_of_requests",
"total_cost",
"total_tokens",
"total_prompt_tokens",
"total_completion_tokens",
"avg_latency",
"avg_tps",
"avg_ttft",
"scores"
],
"properties": {
"number_of_requests": {
"type": "integer",
"description": "Total number of matching spans/log rows.",
"example": 1024
},
"total_cost": {
"type": "number",
"description": "Total cost in USD for all matching spans/log rows.",
"example": 12.45
},
"total_tokens": {
"type": "integer",
"description": "Total tokens across all matching spans/log rows.",
"example": 150000
},
"total_prompt_tokens": {
"type": "integer",
"description": "Total prompt/input tokens.",
"example": 80000
},
"total_completion_tokens": {
"type": "integer",
"description": "Total completion/output tokens.",
"example": 70000
},
"avg_latency": {
"type": "number",
"description": "Average latency in seconds.",
"example": 1.35
},
"avg_tps": {
"type": "number",
"description": "Average tokens per second.",
"example": 45.2
},
"avg_ttft": {
"type": "number",
"description": "Average time to first token in seconds.",
"example": 0.35
},
"scores": {
"type": "object",
"additionalProperties": true,
"description": "Aggregated score summaries grouped by evaluator ID.",
"example": {}
}
},
"example": {
"number_of_requests": 1,
"total_cost": 0,
"total_tokens": 0,
"total_prompt_tokens": 0,
"total_completion_tokens": 0,
"avg_latency": 0,
"avg_tps": 0,
"avg_ttft": 0,
"scores": {}
}
}
}
}
},
"400": {
"description": "Bad Request",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"description": "Error message",
"example": "Invalid request body"
}
}
}
}
}
},
"403": {
"$ref": "#/components/responses/InvalidApiKey"
},
"413": {
"description": "The query exceeded the service's memory or execution-time limit. Narrow the time range or add filters before retrying.",
"content": {
"application/json": {
"schema": {
"type": "object",
"required": [
"detail"
],
"properties": {
"detail": {
"type": "string"
}
}
},
"example": {
"detail": "This query is too large to run — it exceeded a per-query resource limit. Narrow the time range or add filters, then try again."
}
}
}
},
"429": {
"description": "Rate Limited",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"description": "Error message",
"example": "Rate limit exceeded"
}
}
}
}
}
},
"500": {
"description": "Internal Server Error",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"error": {
"type": "string",
"description": "Error message",
"example": "Internal server error"
}
}
}
}
}
}
},
"security": [
{
"RespanApiKey": []
},
{
"DashboardJwt": []
}
]
}OpenAPI path metadata
{}Referenced OpenAPI components
{
"responses": {
"InvalidApiKey": {
"description": "The API key is missing, invalid or expired.",
"content": {
"application/json": {
"schema": {
"type": "object",
"required": [
"detail"
],
"properties": {
"detail": {
"type": "string"
}
}
},
"example": {
"detail": "Your API key is invalid or expired, please check your API key in the platform settings."
}
}
}
}
},
"schemas": {
"FilterValue": {
"type": "object",
"description": "A filter condition with an operator and value.",
"required": [
"value"
],
"properties": {
"operator": {
"type": "string",
"description": "Comparison operator. An empty string means equals.",
"enum": [
"",
"not",
"in",
"not_in",
"lt",
"lte",
"gt",
"gte",
"contains",
"not_contains",
"icontains",
"startswith",
"not_startswith",
"endswith",
"not_endswith",
"empty",
"not_empty"
],
"default": "",
"example": "gte"
},
"value": {
"type": "array",
"description": "Value(s) to filter by.",
"items": {},
"example": [
0.01
]
}
}
},
"Filters": {
"type": "object",
"description": "Each key is a field to filter on, and each value is a condition: `{\"<field>\": {\"operator\": \"<operator>\", \"value\": [...]}}`. A result must match every condition. To set two conditions on one field, such as a range, pass a list of conditions.\n\n**Operators:** `\"\"` (equals, the default), `not`, `in`, `not_in`, `lt`, `lte`, `gt`, `gte`, `contains`, `not_contains`, `icontains` (ignores case), `startswith`, `not_startswith`, `endswith`, `not_endswith`, `empty`, `not_empty`. Put values in a list: `\"\"` and `in` match any of the listed values, and `not` and `not_in` match none of them. Other operators take one value; for `empty` and `not_empty`, send `[\"\"]`.\n\nThe fields you can filter on depend on the endpoint; `metadata__<key>` filters custom metadata where the endpoint supports it.",
"properties": {
"status": {
"$ref": "#/components/schemas/FilterValue"
},
"status_code": {
"$ref": "#/components/schemas/FilterValue"
},
"unique_id": {
"$ref": "#/components/schemas/FilterValue"
},
"customer_identifier": {
"$ref": "#/components/schemas/FilterValue"
},
"thread_identifier": {
"$ref": "#/components/schemas/FilterValue"
},
"custom_identifier": {
"$ref": "#/components/schemas/FilterValue"
},
"group_identifier": {
"$ref": "#/components/schemas/FilterValue"
},
"prompt_id": {
"$ref": "#/components/schemas/FilterValue"
},
"trace_unique_id": {
"$ref": "#/components/schemas/FilterValue"
},
"span_parent_id": {
"$ref": "#/components/schemas/FilterValue"
},
"is_root_span": {
"$ref": "#/components/schemas/FilterValue"
},
"span_workflow_name": {
"$ref": "#/components/schemas/FilterValue"
},
"span_name": {
"$ref": "#/components/schemas/FilterValue"
},
"model": {
"$ref": "#/components/schemas/FilterValue"
},
"log_type": {
"$ref": "#/components/schemas/FilterValue"
},
"stream": {
"$ref": "#/components/schemas/FilterValue"
},
"has_tool_calls": {
"$ref": "#/components/schemas/FilterValue",
"description": "Whether the span made tool calls."
},
"cache_bit": {
"$ref": "#/components/schemas/FilterValue",
"description": "Whether the response was served from the Respan cache."
},
"cache_key": {
"$ref": "#/components/schemas/FilterValue"
},
"prompt_tokens": {
"$ref": "#/components/schemas/FilterValue"
},
"completion_tokens": {
"$ref": "#/components/schemas/FilterValue"
},
"total_tokens": {
"$ref": "#/components/schemas/FilterValue"
},
"cost": {
"$ref": "#/components/schemas/FilterValue"
},
"latency": {
"$ref": "#/components/schemas/FilterValue"
},
"positive_feedback": {
"$ref": "#/components/schemas/FilterValue"
}
},
"example": {
"customer_identifier": {
"operator": "",
"value": [
"alex@acme.dev"
]
}
},
"additionalProperties": {
"$ref": "#/components/schemas/FilterValue"
}
}
},
"securitySchemes": {
"DashboardJwt": {
"type": "http",
"scheme": "bearer",
"bearerFormat": "Dashboard JWT",
"description": "Use a dashboard JWT only for dashboard-authenticated endpoints. Respan API-key endpoints use the respanApiKey auth field instead.",
"x-fern-bearer": {
"name": "dashboardJwt",
"env": "RESPAN_DASHBOARD_JWT"
}
},
"RespanApiKey": {
"type": "http",
"scheme": "bearer",
"bearerFormat": "Respan API key",
"description": "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.",
"x-fern-bearer": {
"name": "respanApiKey",
"env": "RESPAN_API_KEY"
}
}
}
}