Create a private endpoint
curl --request POST \
--url https://openrouter.ai/api/v1/private-endpoints \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model_permaslug": "openai/gpt-4o-2024-08-06",
"provider_slug": "azure",
"upstream_model_id": "gpt-4o-prod",
"activate": {
"workspace_id": "550e8400-e29b-41d4-a716-446655440000"
},
"base_url": "https://contoso.openai.azure.com",
"declared_parameters": [
"temperature",
"seed"
],
"declared_region": "us",
"declared_zdr": true,
"pricing": {
"cache_read": "0.00000025",
"cache_write": "0.000003125",
"completion": "0.00001",
"prompt": "0.0000025"
},
"settings": {
"context_length": 128000,
"reasoning": {
"supported": true
}
}
}
'import requests
url = "https://openrouter.ai/api/v1/private-endpoints"
payload = {
"model_permaslug": "openai/gpt-4o-2024-08-06",
"provider_slug": "azure",
"upstream_model_id": "gpt-4o-prod",
"activate": { "workspace_id": "550e8400-e29b-41d4-a716-446655440000" },
"base_url": "https://contoso.openai.azure.com",
"declared_parameters": ["temperature", "seed"],
"declared_region": "us",
"declared_zdr": True,
"pricing": {
"cache_read": "0.00000025",
"cache_write": "0.000003125",
"completion": "0.00001",
"prompt": "0.0000025"
},
"settings": {
"context_length": 128000,
"reasoning": { "supported": True }
}
}
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_permaslug: 'openai/gpt-4o-2024-08-06',
provider_slug: 'azure',
upstream_model_id: 'gpt-4o-prod',
activate: {workspace_id: '550e8400-e29b-41d4-a716-446655440000'},
base_url: 'https://contoso.openai.azure.com',
declared_parameters: ['temperature', 'seed'],
declared_region: 'us',
declared_zdr: true,
pricing: {
cache_read: '0.00000025',
cache_write: '0.000003125',
completion: '0.00001',
prompt: '0.0000025'
},
settings: {context_length: 128000, reasoning: {supported: true}}
})
};
fetch('https://openrouter.ai/api/v1/private-endpoints', 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://openrouter.ai/api/v1/private-endpoints",
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_permaslug' => 'openai/gpt-4o-2024-08-06',
'provider_slug' => 'azure',
'upstream_model_id' => 'gpt-4o-prod',
'activate' => [
'workspace_id' => '550e8400-e29b-41d4-a716-446655440000'
],
'base_url' => 'https://contoso.openai.azure.com',
'declared_parameters' => [
'temperature',
'seed'
],
'declared_region' => 'us',
'declared_zdr' => true,
'pricing' => [
'cache_read' => '0.00000025',
'cache_write' => '0.000003125',
'completion' => '0.00001',
'prompt' => '0.0000025'
],
'settings' => [
'context_length' => 128000,
'reasoning' => [
'supported' => true
]
]
]),
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://openrouter.ai/api/v1/private-endpoints"
payload := strings.NewReader("{\n \"model_permaslug\": \"openai/gpt-4o-2024-08-06\",\n \"provider_slug\": \"azure\",\n \"upstream_model_id\": \"gpt-4o-prod\",\n \"activate\": {\n \"workspace_id\": \"550e8400-e29b-41d4-a716-446655440000\"\n },\n \"base_url\": \"https://contoso.openai.azure.com\",\n \"declared_parameters\": [\n \"temperature\",\n \"seed\"\n ],\n \"declared_region\": \"us\",\n \"declared_zdr\": true,\n \"pricing\": {\n \"cache_read\": \"0.00000025\",\n \"cache_write\": \"0.000003125\",\n \"completion\": \"0.00001\",\n \"prompt\": \"0.0000025\"\n },\n \"settings\": {\n \"context_length\": 128000,\n \"reasoning\": {\n \"supported\": true\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://openrouter.ai/api/v1/private-endpoints")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model_permaslug\": \"openai/gpt-4o-2024-08-06\",\n \"provider_slug\": \"azure\",\n \"upstream_model_id\": \"gpt-4o-prod\",\n \"activate\": {\n \"workspace_id\": \"550e8400-e29b-41d4-a716-446655440000\"\n },\n \"base_url\": \"https://contoso.openai.azure.com\",\n \"declared_parameters\": [\n \"temperature\",\n \"seed\"\n ],\n \"declared_region\": \"us\",\n \"declared_zdr\": true,\n \"pricing\": {\n \"cache_read\": \"0.00000025\",\n \"cache_write\": \"0.000003125\",\n \"completion\": \"0.00001\",\n \"prompt\": \"0.0000025\"\n },\n \"settings\": {\n \"context_length\": 128000,\n \"reasoning\": {\n \"supported\": true\n }\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://openrouter.ai/api/v1/private-endpoints")
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_permaslug\": \"openai/gpt-4o-2024-08-06\",\n \"provider_slug\": \"azure\",\n \"upstream_model_id\": \"gpt-4o-prod\",\n \"activate\": {\n \"workspace_id\": \"550e8400-e29b-41d4-a716-446655440000\"\n },\n \"base_url\": \"https://contoso.openai.azure.com\",\n \"declared_parameters\": [\n \"temperature\",\n \"seed\"\n ],\n \"declared_region\": \"us\",\n \"declared_zdr\": true,\n \"pricing\": {\n \"cache_read\": \"0.00000025\",\n \"cache_write\": \"0.000003125\",\n \"completion\": \"0.00001\",\n \"prompt\": \"0.0000025\"\n },\n \"settings\": {\n \"context_length\": 128000,\n \"reasoning\": {\n \"supported\": true\n }\n }\n}"
response = http.request(request)
puts response.read_body{
"data": {
"created_at": "2026-09-24T10:30:00Z",
"id": "5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11",
"model_name": "OpenAI: GPT-4o",
"model_permaslug": "openai/gpt-4o-2024-08-06",
"model_slug": "openai/gpt-4o",
"provider_name": "Azure",
"status": "active",
"declared_region": "us",
"declared_zdr": true,
"max_completion_tokens": 131072
}
}{
"error": {
"code": 400,
"message": "Invalid request parameters"
}
}{
"error": {
"code": 401,
"message": "Missing Authentication header"
}
}{
"error": {
"code": 403,
"message": "Only management keys can perform this operation"
}
}{
"data": {
"endpoint": {
"created_at": "2026-09-24T10:30:00Z",
"id": "5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11",
"model_name": "OpenAI: GPT-4o",
"model_permaslug": "openai/gpt-4o-2024-08-06",
"model_slug": "openai/gpt-4o",
"provider_name": "Azure",
"status": "active",
"declared_region": "us",
"declared_zdr": true,
"max_completion_tokens": 131072
},
"validation": {
"checks": [
{
"name": "auth_ok",
"passed": true
}
],
"passed": true,
"parameters": [
{
"parameter": "response_format",
"supported": true
}
]
}
},
"error": {
"code": 123,
"message": "<string>"
}
}{
"error": {
"code": 408,
"message": "Operation timed out. Please try again later."
}
}{
"data": {
"endpoint": {
"created_at": "2026-09-24T10:30:00Z",
"id": "5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11",
"model_name": "OpenAI: GPT-4o",
"model_permaslug": "openai/gpt-4o-2024-08-06",
"model_slug": "openai/gpt-4o",
"provider_name": "Azure",
"status": "active",
"declared_region": "us",
"declared_zdr": true,
"max_completion_tokens": 131072
},
"validation": {
"checks": [
{
"name": "auth_ok",
"passed": true
}
],
"passed": true,
"parameters": [
{
"parameter": "response_format",
"supported": true
}
]
}
},
"error": {
"code": 123,
"message": "<string>"
}
}{
"data": {
"endpoint": {
"created_at": "2026-09-24T10:30:00Z",
"id": "5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11",
"model_name": "OpenAI: GPT-4o",
"model_permaslug": "openai/gpt-4o-2024-08-06",
"model_slug": "openai/gpt-4o",
"provider_name": "Azure",
"status": "active",
"declared_region": "us",
"declared_zdr": true,
"max_completion_tokens": 131072
},
"validation": {
"checks": [
{
"name": "auth_ok",
"passed": true
}
],
"passed": true,
"parameters": [
{
"parameter": "response_format",
"supported": true
}
]
}
},
"error": {
"code": 123,
"message": "<string>"
}
}{
"data": {
"endpoint": {
"created_at": "2026-09-24T10:30:00Z",
"id": "5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11",
"model_name": "OpenAI: GPT-4o",
"model_permaslug": "openai/gpt-4o-2024-08-06",
"model_slug": "openai/gpt-4o",
"provider_name": "Azure",
"status": "active",
"declared_region": "us",
"declared_zdr": true,
"max_completion_tokens": 131072
},
"validation": {
"checks": [
{
"name": "auth_ok",
"passed": true
}
],
"passed": true,
"parameters": [
{
"parameter": "response_format",
"supported": true
}
]
}
},
"error": {
"code": 123,
"message": "<string>"
}
}{
"data": {
"endpoint": {
"created_at": "2026-09-24T10:30:00Z",
"id": "5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11",
"model_name": "OpenAI: GPT-4o",
"model_permaslug": "openai/gpt-4o-2024-08-06",
"model_slug": "openai/gpt-4o",
"provider_name": "Azure",
"status": "active",
"declared_region": "us",
"declared_zdr": true,
"max_completion_tokens": 131072
},
"validation": {
"checks": [
{
"name": "auth_ok",
"passed": true
}
],
"passed": true,
"parameters": [
{
"parameter": "response_format",
"supported": true
}
]
}
},
"error": {
"code": 123,
"message": "<string>"
}
}Private Endpoints
Create a private endpoint
Create a private endpoint as a draft. Drafts are not routable: validate one with POST /private-endpoints/{id}/validate, then activate it with POST /private-endpoints/{id}/activate. Pass activate to do all three in one call; if validation fails the draft is kept and returned with the failed checks. Send an Idempotency-Key header to make retries safe: a repeated key with the same request returns the endpoint the first request created; reusing it with different fields returns 422 idempotency_key_reused. Returns 400 parameters_invalid when tool_choice is declared without tools. The response does not echo declared_parameters or tested_parameters; read them with GET /private-endpoints/{id}. Management key required.
POST
/
private-endpoints
Create a private endpoint
curl --request POST \
--url https://openrouter.ai/api/v1/private-endpoints \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model_permaslug": "openai/gpt-4o-2024-08-06",
"provider_slug": "azure",
"upstream_model_id": "gpt-4o-prod",
"activate": {
"workspace_id": "550e8400-e29b-41d4-a716-446655440000"
},
"base_url": "https://contoso.openai.azure.com",
"declared_parameters": [
"temperature",
"seed"
],
"declared_region": "us",
"declared_zdr": true,
"pricing": {
"cache_read": "0.00000025",
"cache_write": "0.000003125",
"completion": "0.00001",
"prompt": "0.0000025"
},
"settings": {
"context_length": 128000,
"reasoning": {
"supported": true
}
}
}
'import requests
url = "https://openrouter.ai/api/v1/private-endpoints"
payload = {
"model_permaslug": "openai/gpt-4o-2024-08-06",
"provider_slug": "azure",
"upstream_model_id": "gpt-4o-prod",
"activate": { "workspace_id": "550e8400-e29b-41d4-a716-446655440000" },
"base_url": "https://contoso.openai.azure.com",
"declared_parameters": ["temperature", "seed"],
"declared_region": "us",
"declared_zdr": True,
"pricing": {
"cache_read": "0.00000025",
"cache_write": "0.000003125",
"completion": "0.00001",
"prompt": "0.0000025"
},
"settings": {
"context_length": 128000,
"reasoning": { "supported": True }
}
}
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_permaslug: 'openai/gpt-4o-2024-08-06',
provider_slug: 'azure',
upstream_model_id: 'gpt-4o-prod',
activate: {workspace_id: '550e8400-e29b-41d4-a716-446655440000'},
base_url: 'https://contoso.openai.azure.com',
declared_parameters: ['temperature', 'seed'],
declared_region: 'us',
declared_zdr: true,
pricing: {
cache_read: '0.00000025',
cache_write: '0.000003125',
completion: '0.00001',
prompt: '0.0000025'
},
settings: {context_length: 128000, reasoning: {supported: true}}
})
};
fetch('https://openrouter.ai/api/v1/private-endpoints', 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://openrouter.ai/api/v1/private-endpoints",
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_permaslug' => 'openai/gpt-4o-2024-08-06',
'provider_slug' => 'azure',
'upstream_model_id' => 'gpt-4o-prod',
'activate' => [
'workspace_id' => '550e8400-e29b-41d4-a716-446655440000'
],
'base_url' => 'https://contoso.openai.azure.com',
'declared_parameters' => [
'temperature',
'seed'
],
'declared_region' => 'us',
'declared_zdr' => true,
'pricing' => [
'cache_read' => '0.00000025',
'cache_write' => '0.000003125',
'completion' => '0.00001',
'prompt' => '0.0000025'
],
'settings' => [
'context_length' => 128000,
'reasoning' => [
'supported' => true
]
]
]),
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://openrouter.ai/api/v1/private-endpoints"
payload := strings.NewReader("{\n \"model_permaslug\": \"openai/gpt-4o-2024-08-06\",\n \"provider_slug\": \"azure\",\n \"upstream_model_id\": \"gpt-4o-prod\",\n \"activate\": {\n \"workspace_id\": \"550e8400-e29b-41d4-a716-446655440000\"\n },\n \"base_url\": \"https://contoso.openai.azure.com\",\n \"declared_parameters\": [\n \"temperature\",\n \"seed\"\n ],\n \"declared_region\": \"us\",\n \"declared_zdr\": true,\n \"pricing\": {\n \"cache_read\": \"0.00000025\",\n \"cache_write\": \"0.000003125\",\n \"completion\": \"0.00001\",\n \"prompt\": \"0.0000025\"\n },\n \"settings\": {\n \"context_length\": 128000,\n \"reasoning\": {\n \"supported\": true\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://openrouter.ai/api/v1/private-endpoints")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model_permaslug\": \"openai/gpt-4o-2024-08-06\",\n \"provider_slug\": \"azure\",\n \"upstream_model_id\": \"gpt-4o-prod\",\n \"activate\": {\n \"workspace_id\": \"550e8400-e29b-41d4-a716-446655440000\"\n },\n \"base_url\": \"https://contoso.openai.azure.com\",\n \"declared_parameters\": [\n \"temperature\",\n \"seed\"\n ],\n \"declared_region\": \"us\",\n \"declared_zdr\": true,\n \"pricing\": {\n \"cache_read\": \"0.00000025\",\n \"cache_write\": \"0.000003125\",\n \"completion\": \"0.00001\",\n \"prompt\": \"0.0000025\"\n },\n \"settings\": {\n \"context_length\": 128000,\n \"reasoning\": {\n \"supported\": true\n }\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://openrouter.ai/api/v1/private-endpoints")
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_permaslug\": \"openai/gpt-4o-2024-08-06\",\n \"provider_slug\": \"azure\",\n \"upstream_model_id\": \"gpt-4o-prod\",\n \"activate\": {\n \"workspace_id\": \"550e8400-e29b-41d4-a716-446655440000\"\n },\n \"base_url\": \"https://contoso.openai.azure.com\",\n \"declared_parameters\": [\n \"temperature\",\n \"seed\"\n ],\n \"declared_region\": \"us\",\n \"declared_zdr\": true,\n \"pricing\": {\n \"cache_read\": \"0.00000025\",\n \"cache_write\": \"0.000003125\",\n \"completion\": \"0.00001\",\n \"prompt\": \"0.0000025\"\n },\n \"settings\": {\n \"context_length\": 128000,\n \"reasoning\": {\n \"supported\": true\n }\n }\n}"
response = http.request(request)
puts response.read_body{
"data": {
"created_at": "2026-09-24T10:30:00Z",
"id": "5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11",
"model_name": "OpenAI: GPT-4o",
"model_permaslug": "openai/gpt-4o-2024-08-06",
"model_slug": "openai/gpt-4o",
"provider_name": "Azure",
"status": "active",
"declared_region": "us",
"declared_zdr": true,
"max_completion_tokens": 131072
}
}{
"error": {
"code": 400,
"message": "Invalid request parameters"
}
}{
"error": {
"code": 401,
"message": "Missing Authentication header"
}
}{
"error": {
"code": 403,
"message": "Only management keys can perform this operation"
}
}{
"data": {
"endpoint": {
"created_at": "2026-09-24T10:30:00Z",
"id": "5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11",
"model_name": "OpenAI: GPT-4o",
"model_permaslug": "openai/gpt-4o-2024-08-06",
"model_slug": "openai/gpt-4o",
"provider_name": "Azure",
"status": "active",
"declared_region": "us",
"declared_zdr": true,
"max_completion_tokens": 131072
},
"validation": {
"checks": [
{
"name": "auth_ok",
"passed": true
}
],
"passed": true,
"parameters": [
{
"parameter": "response_format",
"supported": true
}
]
}
},
"error": {
"code": 123,
"message": "<string>"
}
}{
"error": {
"code": 408,
"message": "Operation timed out. Please try again later."
}
}{
"data": {
"endpoint": {
"created_at": "2026-09-24T10:30:00Z",
"id": "5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11",
"model_name": "OpenAI: GPT-4o",
"model_permaslug": "openai/gpt-4o-2024-08-06",
"model_slug": "openai/gpt-4o",
"provider_name": "Azure",
"status": "active",
"declared_region": "us",
"declared_zdr": true,
"max_completion_tokens": 131072
},
"validation": {
"checks": [
{
"name": "auth_ok",
"passed": true
}
],
"passed": true,
"parameters": [
{
"parameter": "response_format",
"supported": true
}
]
}
},
"error": {
"code": 123,
"message": "<string>"
}
}{
"data": {
"endpoint": {
"created_at": "2026-09-24T10:30:00Z",
"id": "5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11",
"model_name": "OpenAI: GPT-4o",
"model_permaslug": "openai/gpt-4o-2024-08-06",
"model_slug": "openai/gpt-4o",
"provider_name": "Azure",
"status": "active",
"declared_region": "us",
"declared_zdr": true,
"max_completion_tokens": 131072
},
"validation": {
"checks": [
{
"name": "auth_ok",
"passed": true
}
],
"passed": true,
"parameters": [
{
"parameter": "response_format",
"supported": true
}
]
}
},
"error": {
"code": 123,
"message": "<string>"
}
}{
"data": {
"endpoint": {
"created_at": "2026-09-24T10:30:00Z",
"id": "5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11",
"model_name": "OpenAI: GPT-4o",
"model_permaslug": "openai/gpt-4o-2024-08-06",
"model_slug": "openai/gpt-4o",
"provider_name": "Azure",
"status": "active",
"declared_region": "us",
"declared_zdr": true,
"max_completion_tokens": 131072
},
"validation": {
"checks": [
{
"name": "auth_ok",
"passed": true
}
],
"passed": true,
"parameters": [
{
"parameter": "response_format",
"supported": true
}
]
}
},
"error": {
"code": 123,
"message": "<string>"
}
}{
"data": {
"endpoint": {
"created_at": "2026-09-24T10:30:00Z",
"id": "5b1c4c4e-7d0a-4a8e-9f3a-2d6c1b0e8a11",
"model_name": "OpenAI: GPT-4o",
"model_permaslug": "openai/gpt-4o-2024-08-06",
"model_slug": "openai/gpt-4o",
"provider_name": "Azure",
"status": "active",
"declared_region": "us",
"declared_zdr": true,
"max_completion_tokens": 131072
},
"validation": {
"checks": [
{
"name": "auth_ok",
"passed": true
}
],
"passed": true,
"parameters": [
{
"parameter": "response_format",
"supported": true
}
]
}
},
"error": {
"code": 123,
"message": "<string>"
}
}Authorizations
API key as bearer token in Authorization header
Headers
Retry-safe create: a repeated create with the same key from the same organization returns the endpoint the first request created instead of creating another. The endpoint is returned as it is now. Reusing a key with a different request body (model, provider, base URL, upstream model ID, declared ZDR or region, pricing, or declared parameters) is rejected with 422 idempotency_key_reused. Declared parameters are compared as a set, so a retry that reorders or repeats a name replays the endpoint. activate and settings are not compared, and later edits to the endpoint do not affect the comparison. settings is still validated before the replay, so a retry with invalid settings returns 400 settings_invalid instead of the endpoint.
Required string length:
1 - 255Example:
"wayfair-gpt-4o-eastus-2026-09"
Body
application/json
Permanent slug of the model this endpoint serves.
Minimum string length:
1Example:
"openai/gpt-4o-2024-08-06"
Slug of the upstream provider.
Minimum string length:
1Example:
"azure"
Model or deployment identifier sent to the upstream provider.
Minimum string length:
1Example:
"gpt-4o-prod"
Validate and activate in the same call. On a failed validation the draft is kept and returned with a 422, so fix it and call /validate and /activate instead of creating it again.
Show child attributes
Show child attributes
Example:
{
"workspace_id": "550e8400-e29b-41d4-a716-446655440000"
}
HTTPS base URL of your deployment. Required unless the provider derives its URL from the BYOK credential (Azure, Amazon Bedrock, Google Vertex).
Minimum string length:
1Example:
"https://contoso.openai.azure.com"
Parameters the upstream supports beyond the tested ones. Replaces the earlier declaration; tested parameters stay. Order and repeated names are ignored, but the list holds at most as many entries as there are declarable parameters, repeats included. tool_choice requires tools to be tested or declared.
Maximum array length:
25A chat request parameter the endpoint accepts.
Available options:
temperature, top_p, top_k, min_p, top_a, frequency_penalty, presence_penalty, repetition_penalty, max_tokens, max_completion_tokens, logit_bias, logprobs, top_logprobs, prediction, seed, response_format, structured_outputs, stop, tools, tool_choice, parallel_tool_calls, reasoning, reasoning_effort, web_search_options, verbosity Example:
["temperature", "seed"]
Attest where this deployment processes data.
Available options:
global, europe, us, null Example:
"us"
Attest that this deployment retains no prompt or completion data.
Negotiated per-token rates reported for requests routed to this endpoint.
Show child attributes
Show child attributes
Example:
{
"cache_read": "0.00000025",
"cache_write": "0.000003125",
"completion": "0.00001",
"prompt": "0.0000025"
}
Capabilities and limits to set over the ones copied from the public endpoint for this model and provider (or from the model). Omitted fields keep the copied values.
Show child attributes
Show child attributes
Example:
{
"context_length": 128000,
"reasoning": { "supported": true }
}
Response
The created endpoint: a draft, or active when activate was passed
Show child attributes
Show child attributes
Was this page helpful?