> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://respan.ai/docs/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://respan.ai/docs/_mcp/server.

# Get LLM metric summary

POST https://api.respan.ai/api/dashboard/llm-metrics/summary/
Content-Type: application/json

Returns a single aggregated row of LLM metrics for the entire time range.

Reference: https://respan.ai/docs/apis/metrics/get-llm-metric-summary

## Authentication

- `Authorization` header (bearer token, required) — 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.
- `Authorization` header (bearer token, required) — Use a dashboard JWT only for dashboard-authenticated endpoints. Respan API-key endpoints use the respanApiKey auth field instead.

## Request

### Query parameters

- `summary_type` (enum, optional, default: all) — Preset time range. Use this or explicit `start_time` / `end_time`.
  - Allowed values: `daily`, `weekly`, `monthly`, `quarterly`, `yearly`, `last_24h`, `all`
- `date` (date, optional) — Base date used with `summary_type` presets.
- `start_time` (datetime, optional) — Optional explicit ISO start time.
- `end_time` (datetime, optional) — Optional explicit ISO end time.
- `time_tick` (enum, optional, default: hour) — Bucket granularity for time-series responses.
  - Allowed values: `minute`, `hour`, `day`
- `timezone_offset` (double, optional, default: 0) — Timezone offset, in hours, used when resolving preset ranges.
- `fetch_filters` (enum, optional, default: true) — Whether to include available filter options in the response.
  - Allowed values: `true`, `false`

### Body (application/json)

This endpoint expects a DashboardFiltersRequest.

- `filters` (Filters, optional) — Narrows the spans the metrics are computed from. 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. **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:** span columns, such as `model`, `provider_id`, `deployment_name`, `customer_identifier`, `custom_identifier`, `organization_key_id`, `prompt_id`, `log_type`, `status_code`, `environment`, `cost`, `latency`, `prompt_tokens`, `completion_tokens` and `total_request_tokens`, plus `metadata__<key>` (values are strings). Aliases such as `total_tokens` and `total_cost`, and `scores__<evaluator_id>`, don't work here. **Example:** ```json { "model": {"operator": "", "value": ["gpt-5.5"]}, "customer_identifier": {"operator": "", "value": ["alex@acme.dev"]} } ```

## Response

### 200

Successful response.

- `number_of_requests` (integer, optional)
- `total_cost` (double, optional)
- `total_prompt_tokens` (integer, optional)
- `total_completion_tokens` (integer, optional)
- `total_tokens` (integer, optional)
- `max_tpm` (integer, optional)
- `error_count` (integer, optional)
- `error_percentage` (double, optional, nullable)
- `average_prompt_tokens` (double, optional, nullable)
- `average_completion_tokens` (double, optional, nullable)
- `average_tokens` (double, optional, nullable)
- `average_cost` (double, optional, nullable)
- `average_latency` (double, optional, nullable)
- `average_tps` (double, optional, nullable)
- `average_ttft` (double, optional, nullable)
- `prompt_cache_hit_tokens` (integer, optional)
- `reasoning_tokens` (integer, optional)
- `cache_hit_percentage` (double, optional, nullable)
- `requests_per_second` (double, optional, nullable)
- `latency` (double, optional, nullable) — Legacy empty-bucket field.
- `time_to_first_token` (double, optional, nullable) — Legacy empty-bucket field.

## Errors

### 403 Forbidden Error

The API key is missing, invalid or expired.

- `detail` (string, required)

## Types

### Filters

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. **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 `[""]`. The fields you can filter on depend on the endpoint; `metadata__<key>` filters custom metadata where the endpoint supports it.

- `status` (FilterValue, optional) — A filter condition with an operator and value.
- `status_code` (FilterValue, optional) — A filter condition with an operator and value.
- `unique_id` (FilterValue, optional) — A filter condition with an operator and value.
- `customer_identifier` (FilterValue, optional) — A filter condition with an operator and value.
- `thread_identifier` (FilterValue, optional) — A filter condition with an operator and value.
- `custom_identifier` (FilterValue, optional) — A filter condition with an operator and value.
- `group_identifier` (FilterValue, optional) — A filter condition with an operator and value.
- `prompt_id` (FilterValue, optional) — A filter condition with an operator and value.
- `trace_unique_id` (FilterValue, optional) — A filter condition with an operator and value.
- `span_parent_id` (FilterValue, optional) — A filter condition with an operator and value.
- `is_root_span` (FilterValue, optional) — A filter condition with an operator and value.
- `span_workflow_name` (FilterValue, optional) — A filter condition with an operator and value.
- `span_name` (FilterValue, optional) — A filter condition with an operator and value.
- `model` (FilterValue, optional) — A filter condition with an operator and value.
- `log_type` (FilterValue, optional) — A filter condition with an operator and value.
- `stream` (FilterValue, optional) — A filter condition with an operator and value.
- `has_tool_calls` (FilterValue, optional) — Whether the span made tool calls.
- `cache_bit` (FilterValue, optional) — Whether the response was served from the Respan cache.
- `cache_key` (FilterValue, optional) — A filter condition with an operator and value.
- `prompt_tokens` (FilterValue, optional) — A filter condition with an operator and value.
- `completion_tokens` (FilterValue, optional) — A filter condition with an operator and value.
- `total_tokens` (FilterValue, optional) — A filter condition with an operator and value.
- `cost` (FilterValue, optional) — A filter condition with an operator and value.
- `latency` (FilterValue, optional) — A filter condition with an operator and value.
- `positive_feedback` (FilterValue, optional) — A filter condition with an operator and value.

### FilterValue

A filter condition with an operator and value.

- `value` (list of any, required) — Value(s) to filter by.
- `operator` (enum, optional, default: ) — Comparison operator. An empty string means equals.
  - Allowed values: ``, `not`, `in`, `not_in`, `lt`, `lte`, `gt`, `gte`, `contains`, `not_contains`, `icontains`, `startswith`, `not_startswith`, `endswith`, `not_endswith`, `empty`, `not_empty`

## Examples

**Request**

```json
{}
```

**Response**

```json
{
  "number_of_requests": 1,
  "total_cost": 1.1,
  "total_prompt_tokens": 1,
  "total_completion_tokens": 1,
  "total_tokens": 1,
  "max_tpm": 1,
  "error_count": 1,
  "error_percentage": 1.1,
  "average_prompt_tokens": 1.1,
  "average_completion_tokens": 1.1,
  "average_tokens": 1.1,
  "average_cost": 1.1,
  "average_latency": 1.1,
  "average_tps": 1.1,
  "average_ttft": 1.1,
  "prompt_cache_hit_tokens": 1,
  "reasoning_tokens": 1,
  "cache_hit_percentage": 1.1,
  "requests_per_second": 1.1,
  "latency": 1.1,
  "time_to_first_token": 1.1
}
```

**SDK Code**

```python
import requests

url = "https://api.respan.ai/api/dashboard/llm-metrics/summary/"

payload = {}
headers = {
    "Authorization": "Bearer <respanApiKey>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
```

```javascript
const url = 'https://api.respan.ai/api/dashboard/llm-metrics/summary/';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <respanApiKey>', 'Content-Type': 'application/json'},
  body: '{}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.respan.ai/api/dashboard/llm-metrics/summary/"

	payload := strings.NewReader("{}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <respanApiKey>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby
require 'uri'
require 'net/http'

url = URI("https://api.respan.ai/api/dashboard/llm-metrics/summary/")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <respanApiKey>'
request["Content-Type"] = 'application/json'
request.body = "{}"

response = http.request(request)
puts response.read_body
```

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.respan.ai/api/dashboard/llm-metrics/summary/")
  .header("Authorization", "Bearer <respanApiKey>")
  .header("Content-Type", "application/json")
  .body("{}")
  .asString();
```

```php
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.respan.ai/api/dashboard/llm-metrics/summary/', [
  'body' => '{}',
  'headers' => [
    'Authorization' => 'Bearer <respanApiKey>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp
using RestSharp;

var client = new RestClient("https://api.respan.ai/api/dashboard/llm-metrics/summary/");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <respanApiKey>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let headers = [
  "Authorization": "Bearer <respanApiKey>",
  "Content-Type": "application/json"
]
let parameters = [] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.respan.ai/api/dashboard/llm-metrics/summary/")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```