Grok Chat Completions (All Models, Full Parameters)
curl --request POST \
--url https://direct.evolink.ai/v1/chat/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "grok-4.6",
"messages": [
{
"role": "system",
"content": "You are a concise assistant."
},
{
"role": "user",
"content": "Explain prompt caching in one sentence."
}
],
"stream": false,
"max_tokens": 1024,
"reasoning_effort": "high",
"temperature": 0.7,
"top_p": 0.95,
"tools": [
{
"type": "function",
"function": {}
}
]
}
'import requests
url = "https://direct.evolink.ai/v1/chat/completions"
payload = {
"model": "grok-4.6",
"messages": [
{
"role": "system",
"content": "You are a concise assistant."
},
{
"role": "user",
"content": "Explain prompt caching in one sentence."
}
],
"stream": False,
"max_tokens": 1024,
"reasoning_effort": "high",
"temperature": 0.7,
"top_p": 0.95,
"tools": [
{
"type": "function",
"function": {}
}
]
}
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-4.6',
messages: [
{role: 'system', content: 'You are a concise assistant.'},
{role: 'user', content: 'Explain prompt caching in one sentence.'}
],
stream: false,
max_tokens: 1024,
reasoning_effort: 'high',
temperature: 0.7,
top_p: 0.95,
tools: [{type: 'function', function: {}}]
})
};
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-4.6',
'messages' => [
[
'role' => 'system',
'content' => 'You are a concise assistant.'
],
[
'role' => 'user',
'content' => 'Explain prompt caching in one sentence.'
]
],
'stream' => false,
'max_tokens' => 1024,
'reasoning_effort' => 'high',
'temperature' => 0.7,
'top_p' => 0.95,
'tools' => [
[
'type' => 'function',
'function' => [
]
]
]
]),
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-4.6\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a concise assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Explain prompt caching in one sentence.\"\n }\n ],\n \"stream\": false,\n \"max_tokens\": 1024,\n \"reasoning_effort\": \"high\",\n \"temperature\": 0.7,\n \"top_p\": 0.95,\n \"tools\": [\n {\n \"type\": \"function\",\n \"function\": {}\n }\n ]\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-4.6\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a concise assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Explain prompt caching in one sentence.\"\n }\n ],\n \"stream\": false,\n \"max_tokens\": 1024,\n \"reasoning_effort\": \"high\",\n \"temperature\": 0.7,\n \"top_p\": 0.95,\n \"tools\": [\n {\n \"type\": \"function\",\n \"function\": {}\n }\n ]\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-4.6\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a concise assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Explain prompt caching in one sentence.\"\n }\n ],\n \"stream\": false,\n \"max_tokens\": 1024,\n \"reasoning_effort\": \"high\",\n \"temperature\": 0.7,\n \"top_p\": 0.95,\n \"tools\": [\n {\n \"type\": \"function\",\n \"function\": {}\n }\n ]\n}"
response = http.request(request)
puts response.read_body{
"id": "chatcmpl-20260812164515123456789AbCdEfGh",
"model": "grok-4.6",
"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"
}
}Chat Completions API
Grok All-Model API - Chat Completions Reference
- OpenAI-compatible Chat Completions endpoint for xAI Grok text models; pick the model via the
modelparameter (see the table on themodelparameter for all values) - 500K-token context window; prompts of 200K tokens or more are billed at 2x for all token types
- Prompt caching is automatic: cached prompt tokens are billed at the lower cached-input rate
- Synchronous and streaming (SSE) modes
- Regular
functiontool calling is supported; xAI server-side tools are available on the Responses API only
POST
/
v1
/
chat
/
completions
Grok Chat Completions (All Models, Full Parameters)
curl --request POST \
--url https://direct.evolink.ai/v1/chat/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "grok-4.6",
"messages": [
{
"role": "system",
"content": "You are a concise assistant."
},
{
"role": "user",
"content": "Explain prompt caching in one sentence."
}
],
"stream": false,
"max_tokens": 1024,
"reasoning_effort": "high",
"temperature": 0.7,
"top_p": 0.95,
"tools": [
{
"type": "function",
"function": {}
}
]
}
'import requests
url = "https://direct.evolink.ai/v1/chat/completions"
payload = {
"model": "grok-4.6",
"messages": [
{
"role": "system",
"content": "You are a concise assistant."
},
{
"role": "user",
"content": "Explain prompt caching in one sentence."
}
],
"stream": False,
"max_tokens": 1024,
"reasoning_effort": "high",
"temperature": 0.7,
"top_p": 0.95,
"tools": [
{
"type": "function",
"function": {}
}
]
}
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-4.6',
messages: [
{role: 'system', content: 'You are a concise assistant.'},
{role: 'user', content: 'Explain prompt caching in one sentence.'}
],
stream: false,
max_tokens: 1024,
reasoning_effort: 'high',
temperature: 0.7,
top_p: 0.95,
tools: [{type: 'function', function: {}}]
})
};
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-4.6',
'messages' => [
[
'role' => 'system',
'content' => 'You are a concise assistant.'
],
[
'role' => 'user',
'content' => 'Explain prompt caching in one sentence.'
]
],
'stream' => false,
'max_tokens' => 1024,
'reasoning_effort' => 'high',
'temperature' => 0.7,
'top_p' => 0.95,
'tools' => [
[
'type' => 'function',
'function' => [
]
]
]
]),
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-4.6\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a concise assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Explain prompt caching in one sentence.\"\n }\n ],\n \"stream\": false,\n \"max_tokens\": 1024,\n \"reasoning_effort\": \"high\",\n \"temperature\": 0.7,\n \"top_p\": 0.95,\n \"tools\": [\n {\n \"type\": \"function\",\n \"function\": {}\n }\n ]\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-4.6\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a concise assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Explain prompt caching in one sentence.\"\n }\n ],\n \"stream\": false,\n \"max_tokens\": 1024,\n \"reasoning_effort\": \"high\",\n \"temperature\": 0.7,\n \"top_p\": 0.95,\n \"tools\": [\n {\n \"type\": \"function\",\n \"function\": {}\n }\n ]\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-4.6\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a concise assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Explain prompt caching in one sentence.\"\n }\n ],\n \"stream\": false,\n \"max_tokens\": 1024,\n \"reasoning_effort\": \"high\",\n \"temperature\": 0.7,\n \"top_p\": 0.95,\n \"tools\": [\n {\n \"type\": \"function\",\n \"function\": {}\n }\n ]\n}"
response = http.request(request)
puts response.read_body{
"id": "chatcmpl-20260812164515123456789AbCdEfGh",
"model": "grok-4.6",
"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"
}
}BaseURL: The default BaseURL is
https://direct.evolink.ai, which has better support for text models and long-lived connections. https://api.evolink.ai is the primary endpoint for multimodal services and serves as a fallback address for text models.Server-side tools (web search, X search, code execution, attachment search, collections search) are only available on the Responses API. The Chat Completions endpoint supports regular
function tool calling only.Authorizations
##All APIs require Bearer Token authentication##
Get API Key:
Visit API Key Management Page to get your API Key
Add to request header:
Authorization: Bearer YOUR_API_KEY
Body
application/json
Model to call:
| Model ID | Positioning |
|---|---|
grok-4.6 | xAI reasoning + tool-use model, 500K context window; adds the xhigh reasoning level; knowledge cutoff 2026-02-01 |
grok-4.5 | xAI reasoning + tool-use model, 500K context window; reasoning levels up to high (xhigh is accepted but downgraded to high) |
Available options:
grok-4.6, grok-4.5 Example:
"grok-4.6"
List of chat messages. Supports system, user, and assistant roles.
Minimum array length:
1Show child attributes
Show child attributes
Example:
[
{
"role": "system",
"content": "You are a concise assistant."
},
{
"role": "user",
"content": "Explain prompt caching in one sentence."
}
]
Whether to return a streaming response (SSE, chat.completion.chunk events). Default false.
Example:
false
Maximum number of tokens to generate.
Example:
1024
Reasoning depth: low / medium / high (default) / xhigh. Reasoning cannot be disabled. xhigh is supported by grok-4.6 only — grok-4.5 accepts the value but downgrades it to high. Reasoning tokens are billed as output tokens.
Available options:
low, medium, high, xhigh Sampling temperature (0-2). Higher values produce more random output.
Example:
0.7
Nucleus sampling parameter (0-1).
Example:
0.95
Regular OpenAI function tool definitions (client-side function calling, no extra per-call fee). xAI server-side tools are only available on the Responses API.
Show child attributes
Show child attributes
Controls function selection: "auto" / "none" / "required", or an object pinning a specific function.
Available options:
auto, none, required Response
Chat completion generated successfully (JSON object, or an SSE stream of chat.completion.chunk events when stream=true)
Unique identifier for the chat completion
Example:
"chatcmpl-20260812164515123456789AbCdEfGh"
Model name actually used
Example:
"grok-4.6"
Response type
Available options:
chat.completion Example:
"chat.completion"
Creation timestamp
Example:
1786538000
List of chat completion choices
Show child attributes
Show child attributes
Token usage statistics. Prompts of 200K tokens or more are billed at 2x for all token types (input, cached input, output).
Show child attributes
Show child attributes