curl --request POST \
--url https://gateway.errorbar.ai/v1/dedicated \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"name": "<string>",
"modelName": "<string>",
"flavorName": "<string>",
"gpuType": "<string>",
"gpuCount": 123,
"region": "<string>",
"minReplicas": 123,
"maxReplicas": 123,
"description": "<string>",
"customWeightsId": "<string>",
"fineTuningJobId": "<string>"
}
'import requests
url = "https://gateway.errorbar.ai/v1/dedicated"
payload = {
"name": "<string>",
"modelName": "<string>",
"flavorName": "<string>",
"gpuType": "<string>",
"gpuCount": 123,
"region": "<string>",
"minReplicas": 123,
"maxReplicas": 123,
"description": "<string>",
"customWeightsId": "<string>",
"fineTuningJobId": "<string>"
}
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({
name: '<string>',
modelName: '<string>',
flavorName: '<string>',
gpuType: '<string>',
gpuCount: 123,
region: '<string>',
minReplicas: 123,
maxReplicas: 123,
description: '<string>',
customWeightsId: '<string>',
fineTuningJobId: '<string>'
})
};
fetch('https://gateway.errorbar.ai/v1/dedicated', 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://gateway.errorbar.ai/v1/dedicated",
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([
'name' => '<string>',
'modelName' => '<string>',
'flavorName' => '<string>',
'gpuType' => '<string>',
'gpuCount' => 123,
'region' => '<string>',
'minReplicas' => 123,
'maxReplicas' => 123,
'description' => '<string>',
'customWeightsId' => '<string>',
'fineTuningJobId' => '<string>'
]),
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://gateway.errorbar.ai/v1/dedicated"
payload := strings.NewReader("{\n \"name\": \"<string>\",\n \"modelName\": \"<string>\",\n \"flavorName\": \"<string>\",\n \"gpuType\": \"<string>\",\n \"gpuCount\": 123,\n \"region\": \"<string>\",\n \"minReplicas\": 123,\n \"maxReplicas\": 123,\n \"description\": \"<string>\",\n \"customWeightsId\": \"<string>\",\n \"fineTuningJobId\": \"<string>\"\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://gateway.errorbar.ai/v1/dedicated")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"name\": \"<string>\",\n \"modelName\": \"<string>\",\n \"flavorName\": \"<string>\",\n \"gpuType\": \"<string>\",\n \"gpuCount\": 123,\n \"region\": \"<string>\",\n \"minReplicas\": 123,\n \"maxReplicas\": 123,\n \"description\": \"<string>\",\n \"customWeightsId\": \"<string>\",\n \"fineTuningJobId\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://gateway.errorbar.ai/v1/dedicated")
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 \"name\": \"<string>\",\n \"modelName\": \"<string>\",\n \"flavorName\": \"<string>\",\n \"gpuType\": \"<string>\",\n \"gpuCount\": 123,\n \"region\": \"<string>\",\n \"minReplicas\": 123,\n \"maxReplicas\": 123,\n \"description\": \"<string>\",\n \"customWeightsId\": \"<string>\",\n \"fineTuningJobId\": \"<string>\"\n}"
response = http.request(request)
puts response.read_body{
"id": "<string>",
"name": "<string>",
"description": "<string>",
"model_name": "<string>",
"flavor_name": "<string>",
"gpu_type": "<string>",
"gpu_count": 123,
"region": "<string>",
"min_replicas": 123,
"max_replicas": 123,
"status": "STARTING",
"enabled": true,
"hourly_rate_usd": 123,
"markup_bps": 123,
"pending_cost_usd": 123,
"routing_key": "<string>",
"base_url": "<string>",
"last_metered_at": "<string>",
"created_at": "<string>"
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>"
}
}{
"error": {
"message": "Invalid API key",
"type": "invalid_request_error",
"code": "invalid_api_key"
}
}{
"error": {
"message": "Insufficient balance: deploying this endpoint requires at least 1h of runway. Top up and try again.",
"type": "insufficient_quota",
"code": "insufficient_balance"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>"
}
}Create dedicated endpoint
Provision a new dedicated GPU endpoint. Requires an owner/admin key and enough prepaid balance for the minimum runway. Discover valid model/GPU/region/count combinations from the templates endpoint first.
curl --request POST \
--url https://gateway.errorbar.ai/v1/dedicated \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"name": "<string>",
"modelName": "<string>",
"flavorName": "<string>",
"gpuType": "<string>",
"gpuCount": 123,
"region": "<string>",
"minReplicas": 123,
"maxReplicas": 123,
"description": "<string>",
"customWeightsId": "<string>",
"fineTuningJobId": "<string>"
}
'import requests
url = "https://gateway.errorbar.ai/v1/dedicated"
payload = {
"name": "<string>",
"modelName": "<string>",
"flavorName": "<string>",
"gpuType": "<string>",
"gpuCount": 123,
"region": "<string>",
"minReplicas": 123,
"maxReplicas": 123,
"description": "<string>",
"customWeightsId": "<string>",
"fineTuningJobId": "<string>"
}
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({
name: '<string>',
modelName: '<string>',
flavorName: '<string>',
gpuType: '<string>',
gpuCount: 123,
region: '<string>',
minReplicas: 123,
maxReplicas: 123,
description: '<string>',
customWeightsId: '<string>',
fineTuningJobId: '<string>'
})
};
fetch('https://gateway.errorbar.ai/v1/dedicated', 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://gateway.errorbar.ai/v1/dedicated",
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([
'name' => '<string>',
'modelName' => '<string>',
'flavorName' => '<string>',
'gpuType' => '<string>',
'gpuCount' => 123,
'region' => '<string>',
'minReplicas' => 123,
'maxReplicas' => 123,
'description' => '<string>',
'customWeightsId' => '<string>',
'fineTuningJobId' => '<string>'
]),
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://gateway.errorbar.ai/v1/dedicated"
payload := strings.NewReader("{\n \"name\": \"<string>\",\n \"modelName\": \"<string>\",\n \"flavorName\": \"<string>\",\n \"gpuType\": \"<string>\",\n \"gpuCount\": 123,\n \"region\": \"<string>\",\n \"minReplicas\": 123,\n \"maxReplicas\": 123,\n \"description\": \"<string>\",\n \"customWeightsId\": \"<string>\",\n \"fineTuningJobId\": \"<string>\"\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://gateway.errorbar.ai/v1/dedicated")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"name\": \"<string>\",\n \"modelName\": \"<string>\",\n \"flavorName\": \"<string>\",\n \"gpuType\": \"<string>\",\n \"gpuCount\": 123,\n \"region\": \"<string>\",\n \"minReplicas\": 123,\n \"maxReplicas\": 123,\n \"description\": \"<string>\",\n \"customWeightsId\": \"<string>\",\n \"fineTuningJobId\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://gateway.errorbar.ai/v1/dedicated")
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 \"name\": \"<string>\",\n \"modelName\": \"<string>\",\n \"flavorName\": \"<string>\",\n \"gpuType\": \"<string>\",\n \"gpuCount\": 123,\n \"region\": \"<string>\",\n \"minReplicas\": 123,\n \"maxReplicas\": 123,\n \"description\": \"<string>\",\n \"customWeightsId\": \"<string>\",\n \"fineTuningJobId\": \"<string>\"\n}"
response = http.request(request)
puts response.read_body{
"id": "<string>",
"name": "<string>",
"description": "<string>",
"model_name": "<string>",
"flavor_name": "<string>",
"gpu_type": "<string>",
"gpu_count": 123,
"region": "<string>",
"min_replicas": 123,
"max_replicas": 123,
"status": "STARTING",
"enabled": true,
"hourly_rate_usd": 123,
"markup_bps": 123,
"pending_cost_usd": 123,
"routing_key": "<string>",
"base_url": "<string>",
"last_metered_at": "<string>",
"created_at": "<string>"
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>"
}
}{
"error": {
"message": "Invalid API key",
"type": "invalid_request_error",
"code": "invalid_api_key"
}
}{
"error": {
"message": "Insufficient balance: deploying this endpoint requires at least 1h of runway. Top up and try again.",
"type": "insufficient_quota",
"code": "insufficient_balance"
}
}{
"error": {
"message": "<string>",
"type": "<string>",
"code": "<string>"
}
}Authorizations
Your workspace API key, e.g. sk_sovereign_..., sent as Authorization: Bearer <key>.
Body
This body is camelCase, unlike the snake_case loop endpoints. The service validates the model/flavor/GPU/region combo against the deploy templates, prices it, and requires prepaid balance for the first hour.
A template name from GET /v1/dedicated/templates.
A flavor of that template.
At least 1.
At least minReplicas.
Serve a fine-tuned model's weights by artifact id (used when deploying a trained model).
The source fine-tuning job id, when deploying a model trained on this platform.
Response
The created endpoint.
Live-reconciled from the control plane on every list/get.
STARTING, UPDATING, RUNNING, STOPPING, STOPPED, DELETED, WARNING Whether the endpoint is started. Billing runs only while RUNNING and enabled.
Your price per GPU-hour for this configuration (rate frozen at deploy).
Cost accrued since the last metering sweep, at the frozen rate.
Call the endpoint through the gateway as model "dedicated/<routing_key>".
The inference base URL to point your client at.