Chat Completions
curl --request POST \
--url https://{gatewayBaseURL}/chat/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "<string>",
"messages": [
{
"role": "system",
"content": "<string>",
"name": "<string>"
}
],
"tools": [
{
"type": "<string>",
"function": {
"name": "<string>",
"description": "<string>",
"parameters": {}
}
}
],
"tool_choice": "none",
"temperature": 123,
"top_p": 123,
"top_k": 123,
"n": 123,
"stream": true,
"logprobs": true,
"stop": "<string>",
"max_tokens": 123,
"presence_penalty": 123,
"frequency_penalty": 123,
"logit_bias": {},
"user": "<string>",
"prompt_version_fqn": "<string>",
"prompt_variables": {}
}
'import requests
url = "https://{gatewayBaseURL}/chat/completions"
payload = {
"model": "<string>",
"messages": [
{
"role": "system",
"content": "<string>",
"name": "<string>"
}
],
"tools": [
{
"type": "<string>",
"function": {
"name": "<string>",
"description": "<string>",
"parameters": {}
}
}
],
"tool_choice": "none",
"temperature": 123,
"top_p": 123,
"top_k": 123,
"n": 123,
"stream": True,
"logprobs": True,
"stop": "<string>",
"max_tokens": 123,
"presence_penalty": 123,
"frequency_penalty": 123,
"logit_bias": {},
"user": "<string>",
"prompt_version_fqn": "<string>",
"prompt_variables": {}
}
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: '<string>',
messages: [{role: 'system', content: '<string>', name: '<string>'}],
tools: [
{
type: '<string>',
function: {name: '<string>', description: '<string>', parameters: {}}
}
],
tool_choice: 'none',
temperature: 123,
top_p: 123,
top_k: 123,
n: 123,
stream: true,
logprobs: true,
stop: '<string>',
max_tokens: 123,
presence_penalty: 123,
frequency_penalty: 123,
logit_bias: {},
user: '<string>',
prompt_version_fqn: '<string>',
prompt_variables: {}
})
};
fetch('https://{gatewayBaseURL}/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://{gatewayBaseURL}/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' => [
[
'role' => 'system',
'content' => '<string>',
'name' => '<string>'
]
],
'tools' => [
[
'type' => '<string>',
'function' => [
'name' => '<string>',
'description' => '<string>',
'parameters' => [
]
]
]
],
'tool_choice' => 'none',
'temperature' => 123,
'top_p' => 123,
'top_k' => 123,
'n' => 123,
'stream' => true,
'logprobs' => true,
'stop' => '<string>',
'max_tokens' => 123,
'presence_penalty' => 123,
'frequency_penalty' => 123,
'logit_bias' => [
],
'user' => '<string>',
'prompt_version_fqn' => '<string>',
'prompt_variables' => [
]
]),
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://{gatewayBaseURL}/chat/completions"
payload := strings.NewReader("{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"<string>\",\n \"name\": \"<string>\"\n }\n ],\n \"tools\": [\n {\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"parameters\": {}\n }\n }\n ],\n \"tool_choice\": \"none\",\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"n\": 123,\n \"stream\": true,\n \"logprobs\": true,\n \"stop\": \"<string>\",\n \"max_tokens\": 123,\n \"presence_penalty\": 123,\n \"frequency_penalty\": 123,\n \"logit_bias\": {},\n \"user\": \"<string>\",\n \"prompt_version_fqn\": \"<string>\",\n \"prompt_variables\": {}\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://{gatewayBaseURL}/chat/completions")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"<string>\",\n \"name\": \"<string>\"\n }\n ],\n \"tools\": [\n {\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"parameters\": {}\n }\n }\n ],\n \"tool_choice\": \"none\",\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"n\": 123,\n \"stream\": true,\n \"logprobs\": true,\n \"stop\": \"<string>\",\n \"max_tokens\": 123,\n \"presence_penalty\": 123,\n \"frequency_penalty\": 123,\n \"logit_bias\": {},\n \"user\": \"<string>\",\n \"prompt_version_fqn\": \"<string>\",\n \"prompt_variables\": {}\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://{gatewayBaseURL}/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\": \"<string>\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"<string>\",\n \"name\": \"<string>\"\n }\n ],\n \"tools\": [\n {\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"parameters\": {}\n }\n }\n ],\n \"tool_choice\": \"none\",\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"n\": 123,\n \"stream\": true,\n \"logprobs\": true,\n \"stop\": \"<string>\",\n \"max_tokens\": 123,\n \"presence_penalty\": 123,\n \"frequency_penalty\": 123,\n \"logit_bias\": {},\n \"user\": \"<string>\",\n \"prompt_version_fqn\": \"<string>\",\n \"prompt_variables\": {}\n}"
response = http.request(request)
puts response.read_body{
"id": "<string>",
"object": "<string>",
"created": 123,
"model": "<string>",
"choices": [
{
"index": 123,
"message": {
"role": "<string>",
"content": "<string>",
"refusal": "<string>"
},
"finish_reason": "<string>",
"logprobs": "<unknown>"
}
],
"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
}
},
"service_tier": "<string>",
"system_fingerprint": "<string>"
}Chat
Chat Completions
Generate chat-based completions using the specified model.
POST
/
chat
/
completions
Chat Completions
curl --request POST \
--url https://{gatewayBaseURL}/chat/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "<string>",
"messages": [
{
"role": "system",
"content": "<string>",
"name": "<string>"
}
],
"tools": [
{
"type": "<string>",
"function": {
"name": "<string>",
"description": "<string>",
"parameters": {}
}
}
],
"tool_choice": "none",
"temperature": 123,
"top_p": 123,
"top_k": 123,
"n": 123,
"stream": true,
"logprobs": true,
"stop": "<string>",
"max_tokens": 123,
"presence_penalty": 123,
"frequency_penalty": 123,
"logit_bias": {},
"user": "<string>",
"prompt_version_fqn": "<string>",
"prompt_variables": {}
}
'import requests
url = "https://{gatewayBaseURL}/chat/completions"
payload = {
"model": "<string>",
"messages": [
{
"role": "system",
"content": "<string>",
"name": "<string>"
}
],
"tools": [
{
"type": "<string>",
"function": {
"name": "<string>",
"description": "<string>",
"parameters": {}
}
}
],
"tool_choice": "none",
"temperature": 123,
"top_p": 123,
"top_k": 123,
"n": 123,
"stream": True,
"logprobs": True,
"stop": "<string>",
"max_tokens": 123,
"presence_penalty": 123,
"frequency_penalty": 123,
"logit_bias": {},
"user": "<string>",
"prompt_version_fqn": "<string>",
"prompt_variables": {}
}
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: '<string>',
messages: [{role: 'system', content: '<string>', name: '<string>'}],
tools: [
{
type: '<string>',
function: {name: '<string>', description: '<string>', parameters: {}}
}
],
tool_choice: 'none',
temperature: 123,
top_p: 123,
top_k: 123,
n: 123,
stream: true,
logprobs: true,
stop: '<string>',
max_tokens: 123,
presence_penalty: 123,
frequency_penalty: 123,
logit_bias: {},
user: '<string>',
prompt_version_fqn: '<string>',
prompt_variables: {}
})
};
fetch('https://{gatewayBaseURL}/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://{gatewayBaseURL}/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' => [
[
'role' => 'system',
'content' => '<string>',
'name' => '<string>'
]
],
'tools' => [
[
'type' => '<string>',
'function' => [
'name' => '<string>',
'description' => '<string>',
'parameters' => [
]
]
]
],
'tool_choice' => 'none',
'temperature' => 123,
'top_p' => 123,
'top_k' => 123,
'n' => 123,
'stream' => true,
'logprobs' => true,
'stop' => '<string>',
'max_tokens' => 123,
'presence_penalty' => 123,
'frequency_penalty' => 123,
'logit_bias' => [
],
'user' => '<string>',
'prompt_version_fqn' => '<string>',
'prompt_variables' => [
]
]),
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://{gatewayBaseURL}/chat/completions"
payload := strings.NewReader("{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"<string>\",\n \"name\": \"<string>\"\n }\n ],\n \"tools\": [\n {\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"parameters\": {}\n }\n }\n ],\n \"tool_choice\": \"none\",\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"n\": 123,\n \"stream\": true,\n \"logprobs\": true,\n \"stop\": \"<string>\",\n \"max_tokens\": 123,\n \"presence_penalty\": 123,\n \"frequency_penalty\": 123,\n \"logit_bias\": {},\n \"user\": \"<string>\",\n \"prompt_version_fqn\": \"<string>\",\n \"prompt_variables\": {}\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://{gatewayBaseURL}/chat/completions")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"<string>\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"<string>\",\n \"name\": \"<string>\"\n }\n ],\n \"tools\": [\n {\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"parameters\": {}\n }\n }\n ],\n \"tool_choice\": \"none\",\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"n\": 123,\n \"stream\": true,\n \"logprobs\": true,\n \"stop\": \"<string>\",\n \"max_tokens\": 123,\n \"presence_penalty\": 123,\n \"frequency_penalty\": 123,\n \"logit_bias\": {},\n \"user\": \"<string>\",\n \"prompt_version_fqn\": \"<string>\",\n \"prompt_variables\": {}\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://{gatewayBaseURL}/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\": \"<string>\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"<string>\",\n \"name\": \"<string>\"\n }\n ],\n \"tools\": [\n {\n \"type\": \"<string>\",\n \"function\": {\n \"name\": \"<string>\",\n \"description\": \"<string>\",\n \"parameters\": {}\n }\n }\n ],\n \"tool_choice\": \"none\",\n \"temperature\": 123,\n \"top_p\": 123,\n \"top_k\": 123,\n \"n\": 123,\n \"stream\": true,\n \"logprobs\": true,\n \"stop\": \"<string>\",\n \"max_tokens\": 123,\n \"presence_penalty\": 123,\n \"frequency_penalty\": 123,\n \"logit_bias\": {},\n \"user\": \"<string>\",\n \"prompt_version_fqn\": \"<string>\",\n \"prompt_variables\": {}\n}"
response = http.request(request)
puts response.read_body{
"id": "<string>",
"object": "<string>",
"created": 123,
"model": "<string>",
"choices": [
{
"index": 123,
"message": {
"role": "<string>",
"content": "<string>",
"refusal": "<string>"
},
"finish_reason": "<string>",
"logprobs": "<unknown>"
}
],
"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
}
},
"service_tier": "<string>",
"system_fingerprint": "<string>"
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Headers
Optional metadata for the request
JSON-encoded logging configuration for the request
Body
application/json
Parameters for generating chat completions.
Identifier for the language model to be used for generation.
messages
(System Message · object | User Message · object | Assistant Message · object | Function Message · object | Tool Message · object | Developer Message · object)[]
required
Conversation history as an array of messages for contextual generation.
- System Message
- User Message
- Assistant Message
- Function Message
- Tool Message
- Developer Message
Show child attributes
Show child attributes
Array of tool definitions available for the model to use during generation.
Show child attributes
Show child attributes
tool_choice
Option 1 · enum<string>Option 2 · enum<string>Option 3 · enum<string>Option 4 · objectOption 5 · any
Controls tool usage behavior. Use "none" to disable, "auto" for model choice, "required" to force tool use, or specify tool for forced usage.
Available options:
none Sampling temperature between 0 and 2. Higher values make output more random, lower values more deterministic.
Nucleus sampling parameter. Limits cumulative probability of tokens considered for sampling.
Limits sampling to the K most-likely next tokens.
Number of response alternatives to generate.
Enable streaming of partial response chunks as they are generated.
Include log probabilities of tokens: set to boolean for Chat Completions; integer for legacy Completions (number of top-token logprobs).
Sequence(s) at which to stop generation. Can be a single string or array of strings.
Maximum number of tokens to generate in the response.
Penalty factor for new tokens based on their presence in existing text. Range: -2.0 to 2.0
Penalty factor for new tokens based on their frequency in existing text. Range: -2.0 to 2.0
Modify the likelihood of specified tokens appearing in the completion.
Show child attributes
Show child attributes
Unique identifier for the end-user making the request, for monitoring and detecting abuse.
Fully qualified name (FQN) of the prompt template to use for automatic prompt hydration.
Key-value pairs of variables to substitute in the prompt template when using prompt_version_fqn.
Show child attributes
Show child attributes
Response
Chat completions generated successfully.
Id of the response.
Type of the object, e.g., 'chat.completion'.
Timestamp of when the response was created.
The model used to generate the response.
Array of choices returned by the model.
Show child attributes
Show child attributes
Details about token usage.
Show child attributes
Show child attributes
Service tier used for the request.
System fingerprint, if available.
Was this page helpful?