Time-to-first-token percentiles per model (streaming)

curl --request GET \
  --url https://api-sandbox.featherhq.com/v1/analytics/model-router/latency/ttft-by-model \
  --header 'x-api-key: <api-key>'

import requests

url = "https://api-sandbox.featherhq.com/v1/analytics/model-router/latency/ttft-by-model"

headers = {"x-api-key": "<api-key>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {'x-api-key': '<api-key>'}};

fetch('https://api-sandbox.featherhq.com/v1/analytics/model-router/latency/ttft-by-model', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api-sandbox.featherhq.com/v1/analytics/model-router/latency/ttft-by-model",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "x-api-key: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://api-sandbox.featherhq.com/v1/analytics/model-router/latency/ttft-by-model"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("x-api-key", "<api-key>")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.get("https://api-sandbox.featherhq.com/v1/analytics/model-router/latency/ttft-by-model")
  .header("x-api-key", "<api-key>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api-sandbox.featherhq.com/v1/analytics/model-router/latency/ttft-by-model")

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

request = Net::HTTP::Get.new(url)
request["x-api-key"] = '<api-key>'

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

[
  {
    "served_model": "<string>",
    "p50_ms": 123,
    "p95_ms": 123,
    "p99_ms": 123,
    "avg_ms": 123,
    "max_ms": 123,
    "invocations": 123,
    "provider": "<string>"
  }
]

{
  "error": "<string>",
  "message": "<string>",
  "retryable": true,
  "retry_after": 123
}

{
  "error": "<string>",
  "message": "<string>",
  "retryable": true,
  "retry_after": 123
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}