Create chat completion
curl --request POST \
--url https://api.example.com/v1/chat/completions \
--header 'Authorization: <authorization>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "<string>",
"messages": [
{
"tool_calls": [
{
"id": "<string>",
"index": 123,
"type": "<string>",
"function": {
"name": "<string>",
"arguments": "<string>"
}
}
],
"tool_call_id": "<string>",
"reasoning_content": "<string>",
"content": {},
"name": "<string>",
"refusal": "<string>",
"annotations": [
{}
]
}
],
"stream_options": {
"include_usage": true
},
"top_p": 123,
"max_tokens": 123,
"max_completion_tokens": 123,
"frequency_penalty": 123,
"presence_penalty": 123,
"logit_bias": {
"key": 123
},
"top_logprobs": 123,
"response_format": {
"json_schema": {
"name": "<string>",
"description": "<string>",
"schema": {},
"strict": true
},
"type": "<string>"
},
"prompt_cache_key": "<string>",
"prompt_cache_retention": "<string>",
"safety_identifier": "<string>",
"tool_choice": {},
"parallel_tool_calls": true,
"service_tier": "<string>",
"reasoning_effort": "<string>",
"web_search_options": {},
"function_call": {},
"stream": true,
"temperature": 123,
"stop": {},
"n": 123,
"logprobs": true,
"seed": 123,
"user": "<string>",
"tools": [
{
"type": "<string>",
"function": {
"name": "<string>",
"description": "<string>",
"parameters": {},
"strict": true
}
}
],
"modalities": [
"<string>"
],
"audio": {},
"metadata": {
"key": "<string>"
},
"prediction": {},
"verbosity": "<string>",
"functions": [
{}
]
}
'import requests
url = "https://api.example.com/v1/chat/completions"
payload = {
"model": "<string>",
"messages": [
{
"tool_calls": [
{
"id": "<string>",
"index": 123,
"type": "<string>",
"function": {
"name": "<string>",
"arguments": "<string>"
}
}
],
"tool_call_id": "<string>",
"reasoning_content": "<string>",
"content": {},
"name": "<string>",
"refusal": "<string>",
"annotations": [{}]
}
],
"stream_options": { "include_usage": True },
"top_p": 123,
"max_tokens": 123,
"max_completion_tokens": 123,
"frequency_penalty": 123,
"presence_penalty": 123,
"logit_bias": { "key": 123 },
"top_logprobs": 123,
"response_format": {
"json_schema": {
"name": "<string>",
"description": "<string>",
"schema": {},
"strict": True
},
"type": "<string>"
},
"prompt_cache_key": "<string>",
"prompt_cache_retention": "<string>",
"safety_identifier": "<string>",
"tool_choice": {},
"parallel_tool_calls": True,
"service_tier": "<string>",
"reasoning_effort": "<string>",
"web_search_options": {},
"function_call": {},
"stream": True,
"temperature": 123,
"stop": {},
"n": 123,
"logprobs": True,
"seed": 123,
"user": "<string>",
"tools": [
{
"type": "<string>",
"function": {
"name": "<string>",
"description": "<string>",
"parameters": {},
"strict": True
}
}
],
"modalities": ["<string>"],
"audio": {},
"metadata": { "key": "<string>" },
"prediction": {},
"verbosity": "<string>",
"functions": [{}]
}
headers = {
"Authorization": "<authorization>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: '<authorization>', 'Content-Type': 'application/json'},
body: JSON.stringify({
model: '<string>',
messages: [
{
tool_calls: [
{
id: '<string>',
index: 123,
type: '<string>',
function: {name: '<string>', arguments: '<string>'}
}
],
tool_call_id: '<string>',
reasoning_content: '<string>',
content: {},
name: '<string>',
refusal: '<string>',
annotations: [{}]
}
],
stream_options: {include_usage: true},
top_p: 123,
max_tokens: 123,
max_completion_tokens: 123,
frequency_penalty: 123,
presence_penalty: 123,
logit_bias: {key: 123},
top_logprobs: 123,
response_format: {
json_schema: {name: '<string>', description: '<string>', schema: {}, strict: true},
type: '<string>'
},
prompt_cache_key: '<string>',
prompt_cache_retention: '<string>',
safety_identifier: '<string>',
tool_choice: {},
parallel_tool_calls: true,
service_tier: '<string>',
reasoning_effort: '<string>',
web_search_options: {},
function_call: {},
stream: true,
temperature: 123,
stop: {},
n: 123,
logprobs: true,
seed: 123,
user: '<string>',
tools: [
{
type: '<string>',
function: {name: '<string>', description: '<string>', parameters: {}, strict: true}
}
],
modalities: ['<string>'],
audio: {},
metadata: {key: '<string>'},
prediction: {},
verbosity: '<string>',
functions: [{}]
})
};
fetch('https://api.example.com/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://api.example.com/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' => '<string>',
'messages' => [
[
'tool_calls' => [
[
'id' => '<string>',
'index' => 123,
'type' => '<string>',
'function' => [
'name' => '<string>',
'arguments' => '<string>'
]
]
],
'tool_call_id' => '<string>',
'reasoning_content' => '<string>',
'content' => [
],
'name' => '<string>',
'refusal' => '<string>',
'annotations' => [
[
]
]
]
],
'stream_options' => [
'include_usage' => true
],
'top_p' => 123,
'max_tokens' => 123,
'max_completion_tokens' => 123,
'frequency_penalty' => 123,
'presence_penalty' => 123,
'logit_bias' => [
'key' => 123
],
'top_logprobs' => 123,
'response_format' => [
'json_schema' => [
'name' => '<string>',
'description' => '<string>',
'schema' => [
],
'strict' => true
],
'type' => '<string>'
],
'prompt_cache_key' => '<string>',
'prompt_cache_retention' => '<string>',
'safety_identifier' => '<string>',
'tool_choice' => [
],
'parallel_tool_calls' => true,
'service_tier' => '<string>',
'reasoning_effort' => '<string>',
'web_search_options' => [
],
'function_call' => [
],
'stream' => true,
'temperature' => 123,
'stop' => [
],
'n' => 123,
'logprobs' => true,
'seed' => 123,
'user' => '<string>',
'tools' => [
[
'type' => '<string>',
'function' => [
'name' => '<string>',
'description' => '<string>',
'parameters' => [
],
'strict' => true
]
]
],
'modalities' => [
'<string>'
],
'audio' => [
],
'metadata' => [
'key' => '<string>'
],
'prediction' => [
],
'verbosity' => '<string>',
'functions' => [
[
]
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: <authorization>",
"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://api.example.com/v1/chat/completions"
payload := strings.NewReader("{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"tool_calls\": [\n {\n \"id\": \"<string>\",\n \"index\": 123,\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"arguments\": \"<string>\"\n }\n }\n ],\n \"tool_call_id\": \"<string>\",\n \"reasoning_content\": \"<string>\",\n \"content\": {},\n \"name\": \"<string>\",\n \"refusal\": \"<string>\",\n \"annotations\": [\n {}\n ]\n }\n ],\n \"stream_options\": {\n \"include_usage\": true\n },\n \"top_p\": 123,\n \"max_tokens\": 123,\n \"max_completion_tokens\": 123,\n \"frequency_penalty\": 123,\n \"presence_penalty\": 123,\n \"logit_bias\": {\n \"key\": 123\n },\n \"top_logprobs\": 123,\n \"response_format\": {\n \"json_schema\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"schema\": {},\n \"strict\": true\n },\n \"type\": \"<string>\"\n },\n \"prompt_cache_key\": \"<string>\",\n \"prompt_cache_retention\": \"<string>\",\n \"safety_identifier\": \"<string>\",\n \"tool_choice\": {},\n \"parallel_tool_calls\": true,\n \"service_tier\": \"<string>\",\n \"reasoning_effort\": \"<string>\",\n \"web_search_options\": {},\n \"function_call\": {},\n \"stream\": true,\n \"temperature\": 123,\n \"stop\": {},\n \"n\": 123,\n \"logprobs\": true,\n \"seed\": 123,\n \"user\": \"<string>\",\n \"tools\": [\n {\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"parameters\": {},\n \"strict\": true\n }\n }\n ],\n \"modalities\": [\n \"<string>\"\n ],\n \"audio\": {},\n \"metadata\": {\n \"key\": \"<string>\"\n },\n \"prediction\": {},\n \"verbosity\": \"<string>\",\n \"functions\": [\n {}\n ]\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "<authorization>")
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://api.example.com/v1/chat/completions")
.header("Authorization", "<authorization>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"tool_calls\": [\n {\n \"id\": \"<string>\",\n \"index\": 123,\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"arguments\": \"<string>\"\n }\n }\n ],\n \"tool_call_id\": \"<string>\",\n \"reasoning_content\": \"<string>\",\n \"content\": {},\n \"name\": \"<string>\",\n \"refusal\": \"<string>\",\n \"annotations\": [\n {}\n ]\n }\n ],\n \"stream_options\": {\n \"include_usage\": true\n },\n \"top_p\": 123,\n \"max_tokens\": 123,\n \"max_completion_tokens\": 123,\n \"frequency_penalty\": 123,\n \"presence_penalty\": 123,\n \"logit_bias\": {\n \"key\": 123\n },\n \"top_logprobs\": 123,\n \"response_format\": {\n \"json_schema\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"schema\": {},\n \"strict\": true\n },\n \"type\": \"<string>\"\n },\n \"prompt_cache_key\": \"<string>\",\n \"prompt_cache_retention\": \"<string>\",\n \"safety_identifier\": \"<string>\",\n \"tool_choice\": {},\n \"parallel_tool_calls\": true,\n \"service_tier\": \"<string>\",\n \"reasoning_effort\": \"<string>\",\n \"web_search_options\": {},\n \"function_call\": {},\n \"stream\": true,\n \"temperature\": 123,\n \"stop\": {},\n \"n\": 123,\n \"logprobs\": true,\n \"seed\": 123,\n \"user\": \"<string>\",\n \"tools\": [\n {\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"parameters\": {},\n \"strict\": true\n }\n }\n ],\n \"modalities\": [\n \"<string>\"\n ],\n \"audio\": {},\n \"metadata\": {\n \"key\": \"<string>\"\n },\n \"prediction\": {},\n \"verbosity\": \"<string>\",\n \"functions\": [\n {}\n ]\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.example.com/v1/chat/completions")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = '<authorization>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"tool_calls\": [\n {\n \"id\": \"<string>\",\n \"index\": 123,\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"arguments\": \"<string>\"\n }\n }\n ],\n \"tool_call_id\": \"<string>\",\n \"reasoning_content\": \"<string>\",\n \"content\": {},\n \"name\": \"<string>\",\n \"refusal\": \"<string>\",\n \"annotations\": [\n {}\n ]\n }\n ],\n \"stream_options\": {\n \"include_usage\": true\n },\n \"top_p\": 123,\n \"max_tokens\": 123,\n \"max_completion_tokens\": 123,\n \"frequency_penalty\": 123,\n \"presence_penalty\": 123,\n \"logit_bias\": {\n \"key\": 123\n },\n \"top_logprobs\": 123,\n \"response_format\": {\n \"json_schema\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"schema\": {},\n \"strict\": true\n },\n \"type\": \"<string>\"\n },\n \"prompt_cache_key\": \"<string>\",\n \"prompt_cache_retention\": \"<string>\",\n \"safety_identifier\": \"<string>\",\n \"tool_choice\": {},\n \"parallel_tool_calls\": true,\n \"service_tier\": \"<string>\",\n \"reasoning_effort\": \"<string>\",\n \"web_search_options\": {},\n \"function_call\": {},\n \"stream\": true,\n \"temperature\": 123,\n \"stop\": {},\n \"n\": 123,\n \"logprobs\": true,\n \"seed\": 123,\n \"user\": \"<string>\",\n \"tools\": [\n {\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"parameters\": {},\n \"strict\": true\n }\n }\n ],\n \"modalities\": [\n \"<string>\"\n ],\n \"audio\": {},\n \"metadata\": {\n \"key\": \"<string>\"\n },\n \"prediction\": {},\n \"verbosity\": \"<string>\",\n \"functions\": [\n {}\n ]\n}"
response = http.request(request)
puts response.read_body{
"system_fingerprint": "<string>",
"service_tier": "<string>",
"id": "<string>",
"object": "<string>",
"created": 123,
"model": "<string>",
"choices": [
{
"finish_reason": "<string>",
"index": 123,
"message": {
"role": "SYSTEM",
"tool_calls": [
{
"id": "<string>",
"index": 123,
"type": "<string>",
"function": {
"name": "<string>",
"arguments": "<string>"
}
}
],
"tool_call_id": "<string>",
"reasoning_content": "<string>",
"content": {},
"name": "<string>",
"refusal": "<string>",
"annotations": [
{}
]
},
"logprobs": {
"content": [
{
"top_logprobs": [
{
"token": "<string>",
"logprob": 123,
"bytes": [
123
]
}
],
"token": "<string>",
"logprob": 123,
"bytes": [
123
]
}
],
"refusal": [
{
"top_logprobs": [
{
"token": "<string>",
"logprob": 123,
"bytes": [
123
]
}
],
"token": "<string>",
"logprob": 123,
"bytes": [
123
]
}
]
}
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123,
"prompt_tokens_details": {
"cached_tokens": 123,
"audio_tokens": 123
},
"completion_tokens_details": {
"reasoning_tokens": 123,
"audio_tokens": 123,
"accepted_prediction_tokens": 123,
"rejected_prediction_tokens": 123
},
"ephemeral_5m_input_tokens": 123,
"ephemeral_1h_input_tokens": 123,
"web_search_requests": 123
}
}Chat
OpenAI format
Create chat completions compatible with the OpenAI Chat Completions protocol, supporting streaming and non-streaming responses
POST
/
v1
/
chat
/
completions
Create chat completion
curl --request POST \
--url https://api.example.com/v1/chat/completions \
--header 'Authorization: <authorization>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "<string>",
"messages": [
{
"tool_calls": [
{
"id": "<string>",
"index": 123,
"type": "<string>",
"function": {
"name": "<string>",
"arguments": "<string>"
}
}
],
"tool_call_id": "<string>",
"reasoning_content": "<string>",
"content": {},
"name": "<string>",
"refusal": "<string>",
"annotations": [
{}
]
}
],
"stream_options": {
"include_usage": true
},
"top_p": 123,
"max_tokens": 123,
"max_completion_tokens": 123,
"frequency_penalty": 123,
"presence_penalty": 123,
"logit_bias": {
"key": 123
},
"top_logprobs": 123,
"response_format": {
"json_schema": {
"name": "<string>",
"description": "<string>",
"schema": {},
"strict": true
},
"type": "<string>"
},
"prompt_cache_key": "<string>",
"prompt_cache_retention": "<string>",
"safety_identifier": "<string>",
"tool_choice": {},
"parallel_tool_calls": true,
"service_tier": "<string>",
"reasoning_effort": "<string>",
"web_search_options": {},
"function_call": {},
"stream": true,
"temperature": 123,
"stop": {},
"n": 123,
"logprobs": true,
"seed": 123,
"user": "<string>",
"tools": [
{
"type": "<string>",
"function": {
"name": "<string>",
"description": "<string>",
"parameters": {},
"strict": true
}
}
],
"modalities": [
"<string>"
],
"audio": {},
"metadata": {
"key": "<string>"
},
"prediction": {},
"verbosity": "<string>",
"functions": [
{}
]
}
'import requests
url = "https://api.example.com/v1/chat/completions"
payload = {
"model": "<string>",
"messages": [
{
"tool_calls": [
{
"id": "<string>",
"index": 123,
"type": "<string>",
"function": {
"name": "<string>",
"arguments": "<string>"
}
}
],
"tool_call_id": "<string>",
"reasoning_content": "<string>",
"content": {},
"name": "<string>",
"refusal": "<string>",
"annotations": [{}]
}
],
"stream_options": { "include_usage": True },
"top_p": 123,
"max_tokens": 123,
"max_completion_tokens": 123,
"frequency_penalty": 123,
"presence_penalty": 123,
"logit_bias": { "key": 123 },
"top_logprobs": 123,
"response_format": {
"json_schema": {
"name": "<string>",
"description": "<string>",
"schema": {},
"strict": True
},
"type": "<string>"
},
"prompt_cache_key": "<string>",
"prompt_cache_retention": "<string>",
"safety_identifier": "<string>",
"tool_choice": {},
"parallel_tool_calls": True,
"service_tier": "<string>",
"reasoning_effort": "<string>",
"web_search_options": {},
"function_call": {},
"stream": True,
"temperature": 123,
"stop": {},
"n": 123,
"logprobs": True,
"seed": 123,
"user": "<string>",
"tools": [
{
"type": "<string>",
"function": {
"name": "<string>",
"description": "<string>",
"parameters": {},
"strict": True
}
}
],
"modalities": ["<string>"],
"audio": {},
"metadata": { "key": "<string>" },
"prediction": {},
"verbosity": "<string>",
"functions": [{}]
}
headers = {
"Authorization": "<authorization>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: '<authorization>', 'Content-Type': 'application/json'},
body: JSON.stringify({
model: '<string>',
messages: [
{
tool_calls: [
{
id: '<string>',
index: 123,
type: '<string>',
function: {name: '<string>', arguments: '<string>'}
}
],
tool_call_id: '<string>',
reasoning_content: '<string>',
content: {},
name: '<string>',
refusal: '<string>',
annotations: [{}]
}
],
stream_options: {include_usage: true},
top_p: 123,
max_tokens: 123,
max_completion_tokens: 123,
frequency_penalty: 123,
presence_penalty: 123,
logit_bias: {key: 123},
top_logprobs: 123,
response_format: {
json_schema: {name: '<string>', description: '<string>', schema: {}, strict: true},
type: '<string>'
},
prompt_cache_key: '<string>',
prompt_cache_retention: '<string>',
safety_identifier: '<string>',
tool_choice: {},
parallel_tool_calls: true,
service_tier: '<string>',
reasoning_effort: '<string>',
web_search_options: {},
function_call: {},
stream: true,
temperature: 123,
stop: {},
n: 123,
logprobs: true,
seed: 123,
user: '<string>',
tools: [
{
type: '<string>',
function: {name: '<string>', description: '<string>', parameters: {}, strict: true}
}
],
modalities: ['<string>'],
audio: {},
metadata: {key: '<string>'},
prediction: {},
verbosity: '<string>',
functions: [{}]
})
};
fetch('https://api.example.com/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://api.example.com/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' => '<string>',
'messages' => [
[
'tool_calls' => [
[
'id' => '<string>',
'index' => 123,
'type' => '<string>',
'function' => [
'name' => '<string>',
'arguments' => '<string>'
]
]
],
'tool_call_id' => '<string>',
'reasoning_content' => '<string>',
'content' => [
],
'name' => '<string>',
'refusal' => '<string>',
'annotations' => [
[
]
]
]
],
'stream_options' => [
'include_usage' => true
],
'top_p' => 123,
'max_tokens' => 123,
'max_completion_tokens' => 123,
'frequency_penalty' => 123,
'presence_penalty' => 123,
'logit_bias' => [
'key' => 123
],
'top_logprobs' => 123,
'response_format' => [
'json_schema' => [
'name' => '<string>',
'description' => '<string>',
'schema' => [
],
'strict' => true
],
'type' => '<string>'
],
'prompt_cache_key' => '<string>',
'prompt_cache_retention' => '<string>',
'safety_identifier' => '<string>',
'tool_choice' => [
],
'parallel_tool_calls' => true,
'service_tier' => '<string>',
'reasoning_effort' => '<string>',
'web_search_options' => [
],
'function_call' => [
],
'stream' => true,
'temperature' => 123,
'stop' => [
],
'n' => 123,
'logprobs' => true,
'seed' => 123,
'user' => '<string>',
'tools' => [
[
'type' => '<string>',
'function' => [
'name' => '<string>',
'description' => '<string>',
'parameters' => [
],
'strict' => true
]
]
],
'modalities' => [
'<string>'
],
'audio' => [
],
'metadata' => [
'key' => '<string>'
],
'prediction' => [
],
'verbosity' => '<string>',
'functions' => [
[
]
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: <authorization>",
"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://api.example.com/v1/chat/completions"
payload := strings.NewReader("{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"tool_calls\": [\n {\n \"id\": \"<string>\",\n \"index\": 123,\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"arguments\": \"<string>\"\n }\n }\n ],\n \"tool_call_id\": \"<string>\",\n \"reasoning_content\": \"<string>\",\n \"content\": {},\n \"name\": \"<string>\",\n \"refusal\": \"<string>\",\n \"annotations\": [\n {}\n ]\n }\n ],\n \"stream_options\": {\n \"include_usage\": true\n },\n \"top_p\": 123,\n \"max_tokens\": 123,\n \"max_completion_tokens\": 123,\n \"frequency_penalty\": 123,\n \"presence_penalty\": 123,\n \"logit_bias\": {\n \"key\": 123\n },\n \"top_logprobs\": 123,\n \"response_format\": {\n \"json_schema\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"schema\": {},\n \"strict\": true\n },\n \"type\": \"<string>\"\n },\n \"prompt_cache_key\": \"<string>\",\n \"prompt_cache_retention\": \"<string>\",\n \"safety_identifier\": \"<string>\",\n \"tool_choice\": {},\n \"parallel_tool_calls\": true,\n \"service_tier\": \"<string>\",\n \"reasoning_effort\": \"<string>\",\n \"web_search_options\": {},\n \"function_call\": {},\n \"stream\": true,\n \"temperature\": 123,\n \"stop\": {},\n \"n\": 123,\n \"logprobs\": true,\n \"seed\": 123,\n \"user\": \"<string>\",\n \"tools\": [\n {\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"parameters\": {},\n \"strict\": true\n }\n }\n ],\n \"modalities\": [\n \"<string>\"\n ],\n \"audio\": {},\n \"metadata\": {\n \"key\": \"<string>\"\n },\n \"prediction\": {},\n \"verbosity\": \"<string>\",\n \"functions\": [\n {}\n ]\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "<authorization>")
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://api.example.com/v1/chat/completions")
.header("Authorization", "<authorization>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"tool_calls\": [\n {\n \"id\": \"<string>\",\n \"index\": 123,\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"arguments\": \"<string>\"\n }\n }\n ],\n \"tool_call_id\": \"<string>\",\n \"reasoning_content\": \"<string>\",\n \"content\": {},\n \"name\": \"<string>\",\n \"refusal\": \"<string>\",\n \"annotations\": [\n {}\n ]\n }\n ],\n \"stream_options\": {\n \"include_usage\": true\n },\n \"top_p\": 123,\n \"max_tokens\": 123,\n \"max_completion_tokens\": 123,\n \"frequency_penalty\": 123,\n \"presence_penalty\": 123,\n \"logit_bias\": {\n \"key\": 123\n },\n \"top_logprobs\": 123,\n \"response_format\": {\n \"json_schema\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"schema\": {},\n \"strict\": true\n },\n \"type\": \"<string>\"\n },\n \"prompt_cache_key\": \"<string>\",\n \"prompt_cache_retention\": \"<string>\",\n \"safety_identifier\": \"<string>\",\n \"tool_choice\": {},\n \"parallel_tool_calls\": true,\n \"service_tier\": \"<string>\",\n \"reasoning_effort\": \"<string>\",\n \"web_search_options\": {},\n \"function_call\": {},\n \"stream\": true,\n \"temperature\": 123,\n \"stop\": {},\n \"n\": 123,\n \"logprobs\": true,\n \"seed\": 123,\n \"user\": \"<string>\",\n \"tools\": [\n {\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"parameters\": {},\n \"strict\": true\n }\n }\n ],\n \"modalities\": [\n \"<string>\"\n ],\n \"audio\": {},\n \"metadata\": {\n \"key\": \"<string>\"\n },\n \"prediction\": {},\n \"verbosity\": \"<string>\",\n \"functions\": [\n {}\n ]\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.example.com/v1/chat/completions")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = '<authorization>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"tool_calls\": [\n {\n \"id\": \"<string>\",\n \"index\": 123,\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"arguments\": \"<string>\"\n }\n }\n ],\n \"tool_call_id\": \"<string>\",\n \"reasoning_content\": \"<string>\",\n \"content\": {},\n \"name\": \"<string>\",\n \"refusal\": \"<string>\",\n \"annotations\": [\n {}\n ]\n }\n ],\n \"stream_options\": {\n \"include_usage\": true\n },\n \"top_p\": 123,\n \"max_tokens\": 123,\n \"max_completion_tokens\": 123,\n \"frequency_penalty\": 123,\n \"presence_penalty\": 123,\n \"logit_bias\": {\n \"key\": 123\n },\n \"top_logprobs\": 123,\n \"response_format\": {\n \"json_schema\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"schema\": {},\n \"strict\": true\n },\n \"type\": \"<string>\"\n },\n \"prompt_cache_key\": \"<string>\",\n \"prompt_cache_retention\": \"<string>\",\n \"safety_identifier\": \"<string>\",\n \"tool_choice\": {},\n \"parallel_tool_calls\": true,\n \"service_tier\": \"<string>\",\n \"reasoning_effort\": \"<string>\",\n \"web_search_options\": {},\n \"function_call\": {},\n \"stream\": true,\n \"temperature\": 123,\n \"stop\": {},\n \"n\": 123,\n \"logprobs\": true,\n \"seed\": 123,\n \"user\": \"<string>\",\n \"tools\": [\n {\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"parameters\": {},\n \"strict\": true\n }\n }\n ],\n \"modalities\": [\n \"<string>\"\n ],\n \"audio\": {},\n \"metadata\": {\n \"key\": \"<string>\"\n },\n \"prediction\": {},\n \"verbosity\": \"<string>\",\n \"functions\": [\n {}\n ]\n}"
response = http.request(request)
puts response.read_body{
"system_fingerprint": "<string>",
"service_tier": "<string>",
"id": "<string>",
"object": "<string>",
"created": 123,
"model": "<string>",
"choices": [
{
"finish_reason": "<string>",
"index": 123,
"message": {
"role": "SYSTEM",
"tool_calls": [
{
"id": "<string>",
"index": 123,
"type": "<string>",
"function": {
"name": "<string>",
"arguments": "<string>"
}
}
],
"tool_call_id": "<string>",
"reasoning_content": "<string>",
"content": {},
"name": "<string>",
"refusal": "<string>",
"annotations": [
{}
]
},
"logprobs": {
"content": [
{
"top_logprobs": [
{
"token": "<string>",
"logprob": 123,
"bytes": [
123
]
}
],
"token": "<string>",
"logprob": 123,
"bytes": [
123
]
}
],
"refusal": [
{
"top_logprobs": [
{
"token": "<string>",
"logprob": 123,
"bytes": [
123
]
}
],
"token": "<string>",
"logprob": 123,
"bytes": [
123
]
}
]
}
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123,
"prompt_tokens_details": {
"cached_tokens": 123,
"audio_tokens": 123
},
"completion_tokens_details": {
"reasoning_tokens": 123,
"audio_tokens": 123,
"accepted_prediction_tokens": 123,
"rejected_prediction_tokens": 123
},
"ephemeral_5m_input_tokens": 123,
"ephemeral_1h_input_tokens": 123,
"web_search_requests": 123
}
}This endpoint is compatible with the OpenAI Chat Completions protocol for creating chat completion requests.
Features
- Supports both streaming (SSE) and non-streaming response modes
- Supports multimodal input (text, images, etc.)
- Supports function calling and tool calling
- Supports structured output (JSON Schema)
- Supports reasoning effort configuration
- Supports web search options
Use cases
Suitable for scenarios requiring interaction with OpenAI-compatible models, including:- Single-turn or multi-turn conversations
- Function calling and tool orchestration
- Structured JSON output
- Real-time streaming responses
Authentication
Include theAuthorization header in the format Bearer YOUR_API_KEY.
Never expose API keys in client-side code. Use a server-side proxy to forward requests.
Quick example
import requests
url = "https://api.haitoken.ai/v1/chat/completions"
headers = {
"Authorization": "Bearer YOUR_API_KEY",
"Content-Type": "application/json"
}
data = {
"model": "gpt-4o",
"messages": [
{"role": "user", "content": "Hello, please introduce yourself"}
]
}
response = requests.post(url, json=data, headers=headers)
print(response.json())
const response = await fetch('https://api.haitoken.ai/v1/chat/completions', {
method: 'POST',
headers: {
'Authorization': 'Bearer YOUR_API_KEY',
'Content-Type': 'application/json'
},
body: JSON.stringify({
model: 'gpt-4o',
messages: [
{ role: 'user', content: 'Hello, please introduce yourself' }
]
})
});
const data = await response.json();
console.log(data);
curl -X POST 'https://api.haitoken.ai/v1/chat/completions' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "gpt-4o",
"messages": [
{"role": "user", "content": "Hello, please introduce yourself"}
]
}'
Headers
Example:
"Bearer YOUR_API_KEY"
Example:
"application/json"
Body
application/json
Model ID, e.g. gpt-4o, deepseek-chat, etc.
List of messages
Show child attributes
Show child attributes
Streaming response options (only used when stream=true)
Show child attributes
Show child attributes
Nucleus sampling, between 0 and 1
Maximum number of tokens to generate (deprecated, use max_completion_tokens instead)
Maximum number of tokens to generate (including visible output tokens and reasoning tokens)
Frequency penalty, -2.0 to 2.0
Presence penalty, -2.0 to 2.0
Map to modify the likelihood of specified tokens appearing
Show child attributes
Show child attributes
Maximum number of most likely tokens to return at each token position (0-20)
Response format, supports "text", "json_object", "json_schema"
Show child attributes
Show child attributes
Stable identifier for cache optimization
Cache retention policy: "in_memory" or "24h"
Safety identifier for detecting violating users
Controls which tool the model calls, can be a string ("none"/"auto"/"required") or an object
Whether to enable parallel tool calls
Service tier: "auto", "default", "flex", "scale", "priority"
Reasoning effort level: "none", "minimal", "low", "medium", "high", "xhigh"
Web search options
Deprecated: function call control
Whether to enable streaming output
Sampling temperature, between 0 and 2, higher values produce more random output
Stop sequences
Number of chat completion choices to generate for each input message
Whether to return log probabilities of output tokens
Seed value for deterministic sampling
User identifier (deprecated, use prompt_cache_key instead)
List of tools the model can call
Show child attributes
Show child attributes
Output type list: ["text"] or ["text", "audio"]
Audio output parameters
Metadata, up to 16 key-value pairs
Show child attributes
Show child attributes
Predicted output content
Response verbosity: "low", "medium", "high"
Deprecated: list of function definitions
Response
200 - application/json
OpenAI Chat Completions API response object
System fingerprint, representing backend configuration
Actual service tier used
Unique identifier for the chat completion
Object type, always "chat.completion"
Creation time (Unix timestamp)
Model ID used
List of chat completion choices
Show child attributes
Show child attributes
Usage statistics
Show child attributes
Show child attributes