Create Model
curl --request POST \
--url https://api.egp.scale.com/v5/models \
--header 'Content-Type: application/json' \
--header 'x-api-key: <api-key>' \
--data '
{
"name": "<string>",
"vendor_configuration": {
"model_image": {
"registry": "<string>",
"repository": "<string>",
"tag": "<string>",
"command": [
"<string>"
],
"predict_route": "/predict",
"streaming_predict_route": "<string>",
"streaming_command": [
"<string>"
],
"request_schema": {},
"response_schema": {},
"env_vars": {},
"readiness_delay": 120,
"healthcheck_route": "/readyz"
},
"model_infra": {
"endpoint_type": "sync",
"cpus": 3,
"gpus": 0,
"memory": "8Gi",
"storage": "16Gi",
"min_workers": 0,
"max_workers": 1,
"per_worker": 10,
"high_priority": false,
"labels": {},
"public_inference": false
}
},
"model_type": "generic",
"model_vendor": "launch",
"model_metadata": {},
"on_conflict": "error"
}
'import requests
url = "https://api.egp.scale.com/v5/models"
payload = {
"name": "<string>",
"vendor_configuration": {
"model_image": {
"registry": "<string>",
"repository": "<string>",
"tag": "<string>",
"command": ["<string>"],
"predict_route": "/predict",
"streaming_predict_route": "<string>",
"streaming_command": ["<string>"],
"request_schema": {},
"response_schema": {},
"env_vars": {},
"readiness_delay": 120,
"healthcheck_route": "/readyz"
},
"model_infra": {
"endpoint_type": "sync",
"cpus": 3,
"gpus": 0,
"memory": "8Gi",
"storage": "16Gi",
"min_workers": 0,
"max_workers": 1,
"per_worker": 10,
"high_priority": False,
"labels": {},
"public_inference": False
}
},
"model_type": "generic",
"model_vendor": "launch",
"model_metadata": {},
"on_conflict": "error"
}
headers = {
"x-api-key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
name: '<string>',
vendor_configuration: {
model_image: {
registry: '<string>',
repository: '<string>',
tag: '<string>',
command: ['<string>'],
predict_route: '/predict',
streaming_predict_route: '<string>',
streaming_command: ['<string>'],
request_schema: {},
response_schema: {},
env_vars: {},
readiness_delay: 120,
healthcheck_route: '/readyz'
},
model_infra: {
endpoint_type: 'sync',
cpus: 3,
gpus: 0,
memory: '8Gi',
storage: '16Gi',
min_workers: 0,
max_workers: 1,
per_worker: 10,
high_priority: false,
labels: {},
public_inference: false
}
},
model_type: 'generic',
model_vendor: 'launch',
model_metadata: {},
on_conflict: 'error'
})
};
fetch('https://api.egp.scale.com/v5/models', 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.egp.scale.com/v5/models",
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>',
'vendor_configuration' => [
'model_image' => [
'registry' => '<string>',
'repository' => '<string>',
'tag' => '<string>',
'command' => [
'<string>'
],
'predict_route' => '/predict',
'streaming_predict_route' => '<string>',
'streaming_command' => [
'<string>'
],
'request_schema' => [
],
'response_schema' => [
],
'env_vars' => [
],
'readiness_delay' => 120,
'healthcheck_route' => '/readyz'
],
'model_infra' => [
'endpoint_type' => 'sync',
'cpus' => 3,
'gpus' => 0,
'memory' => '8Gi',
'storage' => '16Gi',
'min_workers' => 0,
'max_workers' => 1,
'per_worker' => 10,
'high_priority' => false,
'labels' => [
],
'public_inference' => false
]
],
'model_type' => 'generic',
'model_vendor' => 'launch',
'model_metadata' => [
],
'on_conflict' => 'error'
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-api-key: <api-key>"
],
]);
$response = curl_exec($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.egp.scale.com/v5/models"
payload := strings.NewReader("{\n \"name\": \"<string>\",\n \"vendor_configuration\": {\n \"model_image\": {\n \"registry\": \"<string>\",\n \"repository\": \"<string>\",\n \"tag\": \"<string>\",\n \"command\": [\n \"<string>\"\n ],\n \"predict_route\": \"/predict\",\n \"streaming_predict_route\": \"<string>\",\n \"streaming_command\": [\n \"<string>\"\n ],\n \"request_schema\": {},\n \"response_schema\": {},\n \"env_vars\": {},\n \"readiness_delay\": 120,\n \"healthcheck_route\": \"/readyz\"\n },\n \"model_infra\": {\n \"endpoint_type\": \"sync\",\n \"cpus\": 3,\n \"gpus\": 0,\n \"memory\": \"8Gi\",\n \"storage\": \"16Gi\",\n \"min_workers\": 0,\n \"max_workers\": 1,\n \"per_worker\": 10,\n \"high_priority\": false,\n \"labels\": {},\n \"public_inference\": false\n }\n },\n \"model_type\": \"generic\",\n \"model_vendor\": \"launch\",\n \"model_metadata\": {},\n \"on_conflict\": \"error\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-api-key", "<api-key>")
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.egp.scale.com/v5/models")
.header("x-api-key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"name\": \"<string>\",\n \"vendor_configuration\": {\n \"model_image\": {\n \"registry\": \"<string>\",\n \"repository\": \"<string>\",\n \"tag\": \"<string>\",\n \"command\": [\n \"<string>\"\n ],\n \"predict_route\": \"/predict\",\n \"streaming_predict_route\": \"<string>\",\n \"streaming_command\": [\n \"<string>\"\n ],\n \"request_schema\": {},\n \"response_schema\": {},\n \"env_vars\": {},\n \"readiness_delay\": 120,\n \"healthcheck_route\": \"/readyz\"\n },\n \"model_infra\": {\n \"endpoint_type\": \"sync\",\n \"cpus\": 3,\n \"gpus\": 0,\n \"memory\": \"8Gi\",\n \"storage\": \"16Gi\",\n \"min_workers\": 0,\n \"max_workers\": 1,\n \"per_worker\": 10,\n \"high_priority\": false,\n \"labels\": {},\n \"public_inference\": false\n }\n },\n \"model_type\": \"generic\",\n \"model_vendor\": \"launch\",\n \"model_metadata\": {},\n \"on_conflict\": \"error\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.egp.scale.com/v5/models")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"name\": \"<string>\",\n \"vendor_configuration\": {\n \"model_image\": {\n \"registry\": \"<string>\",\n \"repository\": \"<string>\",\n \"tag\": \"<string>\",\n \"command\": [\n \"<string>\"\n ],\n \"predict_route\": \"/predict\",\n \"streaming_predict_route\": \"<string>\",\n \"streaming_command\": [\n \"<string>\"\n ],\n \"request_schema\": {},\n \"response_schema\": {},\n \"env_vars\": {},\n \"readiness_delay\": 120,\n \"healthcheck_route\": \"/readyz\"\n },\n \"model_infra\": {\n \"endpoint_type\": \"sync\",\n \"cpus\": 3,\n \"gpus\": 0,\n \"memory\": \"8Gi\",\n \"storage\": \"16Gi\",\n \"min_workers\": 0,\n \"max_workers\": 1,\n \"per_worker\": 10,\n \"high_priority\": false,\n \"labels\": {},\n \"public_inference\": false\n }\n },\n \"model_type\": \"generic\",\n \"model_vendor\": \"launch\",\n \"model_metadata\": {},\n \"on_conflict\": \"error\"\n}"
response = http.request(request)
puts response.read_body{
"id": "<string>",
"name": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"created_by_user_id": "<string>",
"object": "model",
"vendor_configuration": {
"model_image": {
"registry": "<string>",
"repository": "<string>",
"tag": "<string>",
"command": [
"<string>"
],
"predict_route": "/predict",
"streaming_predict_route": "<string>",
"streaming_command": [
"<string>"
],
"request_schema": {},
"response_schema": {},
"env_vars": {},
"readiness_delay": 120,
"healthcheck_route": "/readyz"
},
"model_infra": {
"endpoint_type": "sync",
"cpus": 3,
"gpus": 0,
"memory": "8Gi",
"storage": "16Gi",
"min_workers": 0,
"max_workers": 1,
"per_worker": 10,
"high_priority": false,
"labels": {},
"public_inference": false
}
},
"status_reason": "<string>",
"model_metadata": {}
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}Models
Create Model
POST
/
v5
/
models
Create Model
curl --request POST \
--url https://api.egp.scale.com/v5/models \
--header 'Content-Type: application/json' \
--header 'x-api-key: <api-key>' \
--data '
{
"name": "<string>",
"vendor_configuration": {
"model_image": {
"registry": "<string>",
"repository": "<string>",
"tag": "<string>",
"command": [
"<string>"
],
"predict_route": "/predict",
"streaming_predict_route": "<string>",
"streaming_command": [
"<string>"
],
"request_schema": {},
"response_schema": {},
"env_vars": {},
"readiness_delay": 120,
"healthcheck_route": "/readyz"
},
"model_infra": {
"endpoint_type": "sync",
"cpus": 3,
"gpus": 0,
"memory": "8Gi",
"storage": "16Gi",
"min_workers": 0,
"max_workers": 1,
"per_worker": 10,
"high_priority": false,
"labels": {},
"public_inference": false
}
},
"model_type": "generic",
"model_vendor": "launch",
"model_metadata": {},
"on_conflict": "error"
}
'import requests
url = "https://api.egp.scale.com/v5/models"
payload = {
"name": "<string>",
"vendor_configuration": {
"model_image": {
"registry": "<string>",
"repository": "<string>",
"tag": "<string>",
"command": ["<string>"],
"predict_route": "/predict",
"streaming_predict_route": "<string>",
"streaming_command": ["<string>"],
"request_schema": {},
"response_schema": {},
"env_vars": {},
"readiness_delay": 120,
"healthcheck_route": "/readyz"
},
"model_infra": {
"endpoint_type": "sync",
"cpus": 3,
"gpus": 0,
"memory": "8Gi",
"storage": "16Gi",
"min_workers": 0,
"max_workers": 1,
"per_worker": 10,
"high_priority": False,
"labels": {},
"public_inference": False
}
},
"model_type": "generic",
"model_vendor": "launch",
"model_metadata": {},
"on_conflict": "error"
}
headers = {
"x-api-key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
name: '<string>',
vendor_configuration: {
model_image: {
registry: '<string>',
repository: '<string>',
tag: '<string>',
command: ['<string>'],
predict_route: '/predict',
streaming_predict_route: '<string>',
streaming_command: ['<string>'],
request_schema: {},
response_schema: {},
env_vars: {},
readiness_delay: 120,
healthcheck_route: '/readyz'
},
model_infra: {
endpoint_type: 'sync',
cpus: 3,
gpus: 0,
memory: '8Gi',
storage: '16Gi',
min_workers: 0,
max_workers: 1,
per_worker: 10,
high_priority: false,
labels: {},
public_inference: false
}
},
model_type: 'generic',
model_vendor: 'launch',
model_metadata: {},
on_conflict: 'error'
})
};
fetch('https://api.egp.scale.com/v5/models', 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.egp.scale.com/v5/models",
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>',
'vendor_configuration' => [
'model_image' => [
'registry' => '<string>',
'repository' => '<string>',
'tag' => '<string>',
'command' => [
'<string>'
],
'predict_route' => '/predict',
'streaming_predict_route' => '<string>',
'streaming_command' => [
'<string>'
],
'request_schema' => [
],
'response_schema' => [
],
'env_vars' => [
],
'readiness_delay' => 120,
'healthcheck_route' => '/readyz'
],
'model_infra' => [
'endpoint_type' => 'sync',
'cpus' => 3,
'gpus' => 0,
'memory' => '8Gi',
'storage' => '16Gi',
'min_workers' => 0,
'max_workers' => 1,
'per_worker' => 10,
'high_priority' => false,
'labels' => [
],
'public_inference' => false
]
],
'model_type' => 'generic',
'model_vendor' => 'launch',
'model_metadata' => [
],
'on_conflict' => 'error'
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-api-key: <api-key>"
],
]);
$response = curl_exec($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.egp.scale.com/v5/models"
payload := strings.NewReader("{\n \"name\": \"<string>\",\n \"vendor_configuration\": {\n \"model_image\": {\n \"registry\": \"<string>\",\n \"repository\": \"<string>\",\n \"tag\": \"<string>\",\n \"command\": [\n \"<string>\"\n ],\n \"predict_route\": \"/predict\",\n \"streaming_predict_route\": \"<string>\",\n \"streaming_command\": [\n \"<string>\"\n ],\n \"request_schema\": {},\n \"response_schema\": {},\n \"env_vars\": {},\n \"readiness_delay\": 120,\n \"healthcheck_route\": \"/readyz\"\n },\n \"model_infra\": {\n \"endpoint_type\": \"sync\",\n \"cpus\": 3,\n \"gpus\": 0,\n \"memory\": \"8Gi\",\n \"storage\": \"16Gi\",\n \"min_workers\": 0,\n \"max_workers\": 1,\n \"per_worker\": 10,\n \"high_priority\": false,\n \"labels\": {},\n \"public_inference\": false\n }\n },\n \"model_type\": \"generic\",\n \"model_vendor\": \"launch\",\n \"model_metadata\": {},\n \"on_conflict\": \"error\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-api-key", "<api-key>")
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.egp.scale.com/v5/models")
.header("x-api-key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"name\": \"<string>\",\n \"vendor_configuration\": {\n \"model_image\": {\n \"registry\": \"<string>\",\n \"repository\": \"<string>\",\n \"tag\": \"<string>\",\n \"command\": [\n \"<string>\"\n ],\n \"predict_route\": \"/predict\",\n \"streaming_predict_route\": \"<string>\",\n \"streaming_command\": [\n \"<string>\"\n ],\n \"request_schema\": {},\n \"response_schema\": {},\n \"env_vars\": {},\n \"readiness_delay\": 120,\n \"healthcheck_route\": \"/readyz\"\n },\n \"model_infra\": {\n \"endpoint_type\": \"sync\",\n \"cpus\": 3,\n \"gpus\": 0,\n \"memory\": \"8Gi\",\n \"storage\": \"16Gi\",\n \"min_workers\": 0,\n \"max_workers\": 1,\n \"per_worker\": 10,\n \"high_priority\": false,\n \"labels\": {},\n \"public_inference\": false\n }\n },\n \"model_type\": \"generic\",\n \"model_vendor\": \"launch\",\n \"model_metadata\": {},\n \"on_conflict\": \"error\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.egp.scale.com/v5/models")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"name\": \"<string>\",\n \"vendor_configuration\": {\n \"model_image\": {\n \"registry\": \"<string>\",\n \"repository\": \"<string>\",\n \"tag\": \"<string>\",\n \"command\": [\n \"<string>\"\n ],\n \"predict_route\": \"/predict\",\n \"streaming_predict_route\": \"<string>\",\n \"streaming_command\": [\n \"<string>\"\n ],\n \"request_schema\": {},\n \"response_schema\": {},\n \"env_vars\": {},\n \"readiness_delay\": 120,\n \"healthcheck_route\": \"/readyz\"\n },\n \"model_infra\": {\n \"endpoint_type\": \"sync\",\n \"cpus\": 3,\n \"gpus\": 0,\n \"memory\": \"8Gi\",\n \"storage\": \"16Gi\",\n \"min_workers\": 0,\n \"max_workers\": 1,\n \"per_worker\": 10,\n \"high_priority\": false,\n \"labels\": {},\n \"public_inference\": false\n }\n },\n \"model_type\": \"generic\",\n \"model_vendor\": \"launch\",\n \"model_metadata\": {},\n \"on_conflict\": \"error\"\n}"
response = http.request(request)
puts response.read_body{
"id": "<string>",
"name": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"created_by_user_id": "<string>",
"object": "model",
"vendor_configuration": {
"model_image": {
"registry": "<string>",
"repository": "<string>",
"tag": "<string>",
"command": [
"<string>"
],
"predict_route": "/predict",
"streaming_predict_route": "<string>",
"streaming_command": [
"<string>"
],
"request_schema": {},
"response_schema": {},
"env_vars": {},
"readiness_delay": 120,
"healthcheck_route": "/readyz"
},
"model_infra": {
"endpoint_type": "sync",
"cpus": 3,
"gpus": 0,
"memory": "8Gi",
"storage": "16Gi",
"min_workers": 0,
"max_workers": 1,
"per_worker": 10,
"high_priority": false,
"labels": {},
"public_inference": false
}
},
"status_reason": "<string>",
"model_metadata": {}
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}Authorizations
Headers
Body
application/json
- LaunchModelCreateRequest
- LLMEngineModelCreateRequest
Unique name to reference your model
Show child attributes
Show child attributes
Allowed value:
"generic"Allowed value:
"launch"Available options:
error, update Response
Successful Response
Available options:
generic, completion, chat_completion Available options:
openai, cohere, vertex_ai, anthropic, azure, gemini, launch, llmengine, model_zoo, bedrock, xai, fireworks_ai Available options:
failed, ready, deploying, deployment_timeout Available options:
user, service_account Allowed value:
"model"- LaunchVendorConfiguration
- LLMEngineVendorConfiguration
Show child attributes
Show child attributes
Available options:
unknown, available, unavailable ⌘I

