curl --request POST \
  --url https://direct.evolink.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "grok-4.7",
  "messages": [
    {
      "role": "user",
      "content": "Erkläre Prompt-Caching in einem Satz."
    }
  ],
  "reasoning_effort": "xhigh",
  "max_tokens": 2048,
  "prompt_cache_key": "grok-session-001"
}
'

import requests

url = "https://direct.evolink.ai/v1/chat/completions"

payload = {
    "model": "grok-4.7",
    "messages": [
        {
            "role": "user",
            "content": "Erkläre Prompt-Caching in einem Satz."
        }
    ],
    "reasoning_effort": "xhigh",
    "max_tokens": 2048,
    "prompt_cache_key": "grok-session-001"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'grok-4.7',
    messages: [{role: 'user', content: 'Erkläre Prompt-Caching in einem Satz.'}],
    reasoning_effort: 'xhigh',
    max_tokens: 2048,
    prompt_cache_key: 'grok-session-001'
  })
};

fetch('https://direct.evolink.ai/v1/chat/completions', 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://direct.evolink.ai/v1/chat/completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => 'grok-4.7',
    'messages' => [
        [
                'role' => 'user',
                'content' => 'Erkläre Prompt-Caching in einem Satz.'
        ]
    ],
    'reasoning_effort' => 'xhigh',
    'max_tokens' => 2048,
    'prompt_cache_key' => 'grok-session-001'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

	url := "https://direct.evolink.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"grok-4.7\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Erkläre Prompt-Caching in einem Satz.\"\n    }\n  ],\n  \"reasoning_effort\": \"xhigh\",\n  \"max_tokens\": 2048,\n  \"prompt_cache_key\": \"grok-session-001\"\n}")

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

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

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://direct.evolink.ai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"grok-4.7\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Erkläre Prompt-Caching in einem Satz.\"\n    }\n  ],\n  \"reasoning_effort\": \"xhigh\",\n  \"max_tokens\": 2048,\n  \"prompt_cache_key\": \"grok-session-001\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://direct.evolink.ai/v1/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"grok-4.7\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Erkläre Prompt-Caching in einem Satz.\"\n    }\n  ],\n  \"reasoning_effort\": \"xhigh\",\n  \"max_tokens\": 2048,\n  \"prompt_cache_key\": \"grok-session-001\"\n}"

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

{
  "id": "chatcmpl-20260812164515123456789AbCdEfGh",
  "model": "grok-4.7",
  "object": "chat.completion",
  "created": 1786538000,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Prompt caching reuses previously processed prompt prefixes so repeated context is billed at a lower rate.",
        "tool_calls": [
          {}
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 504,
    "completion_tokens": 2,
    "total_tokens": 526,
    "prompt_tokens_details": {
      "cached_tokens": 0
    }
  }
}

{
  "error": {
    "code": 400,
    "message": "Invalid request parameters",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": 401,
    "message": "Invalid or expired token",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": 402,
    "message": "Insufficient quota",
    "type": "insufficient_quota_error",
    "fallback_suggestion": "https://evolink.ai/dashboard/billing"
  }
}

{
  "error": {
    "code": 429,
    "message": "Rate limit exceeded",
    "type": "rate_limit_error",
    "fallback_suggestion": "retry after 60 seconds"
  }
}

{
  "error": {
    "code": 500,
    "message": "Internal server error",
    "type": "internal_server_error",
    "fallback_suggestion": "try again later"
  }
}

{
  "error": {
    "code": 503,
    "message": "Service temporarily unavailable",
    "type": "service_unavailable_error",
    "fallback_suggestion": "retry after 30 seconds"
  }
}