Create a team BIS-LLM deployment

POST

teams

{team_id}

llm_models

cURL

curl --request POST \
--url https://api.baseten.co/v1/teams/{team_id}/llm_models \
--header "Authorization: Bearer $BASETEN_API_KEY" \
--data '{
  "resources": null,
  "region": null,
  "llm_version": null,
  "model_metadata": null,
  "autoscaling_settings": {
    "autoscaling_window": 600,
    "concurrency_target": null,
    "max_replica": 5,
    "max_scale_down_rate": null,
    "min_replica": 1,
    "scale_down_delay": 300,
    "target_in_flight_tokens": null,
    "target_utilization_percentage": null
  },
  "additional_autoscaling_config": {
    "metrics": [
      {
        "name": "in_flight_tokens",
        "target": 40000
      }
    ]
  },
  "metadata": {
    "environment": "production",
    "git_sha": "abc123"
  },
  "weights": [
    {
      "mount_location": "/models/base",
      "source": "hf://meta-llama/Llama-3-8B"
    }
  ],
  "name": null
}'

import requests
import os
API_KEY = os.environ.get("BASETEN_API_KEY", "<YOUR_API_KEY>")
url = "https://api.baseten.co/v1/teams/{team_id}/llm_models"

headers = {"Authorization": f"Bearer {API_KEY}"}

response = requests.request(
    "POST",
    url,
    headers=headers,
    json={'resources': None, 'region': None, 'llm_version': None, 'model_metadata': None, 'autoscaling_settings': {'autoscaling_window': 600, 'concurrency_target': None, 'max_replica': 5, 'max_scale_down_rate': None, 'min_replica': 1, 'scale_down_delay': 300, 'target_in_flight_tokens': None, 'target_utilization_percentage': None}, 'additional_autoscaling_config': {'metrics': [{'name': 'in_flight_tokens', 'target': 40000}]}, 'metadata': {'environment': 'production', 'git_sha': 'abc123'}, 'weights': [{'mount_location': '/models/base', 'source': 'hf://meta-llama/Llama-3-8B'}], 'name': None}
)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    resources: {},
    name: '<string>',
    region: '<string>',
    llm_version: '<string>',
    llm_config: {},
    environment_variables: {},
    model_metadata: {},
    autoscaling_settings: {
      autoscaling_window: 600,
      concurrency_target: null,
      max_replica: 5,
      max_scale_down_rate: null,
      min_replica: 1,
      scale_down_delay: 300,
      target_in_flight_tokens: null,
      target_utilization_percentage: null
    },
    additional_autoscaling_config: {metrics: [{name: 'in_flight_tokens', target: 40000}]},
    metadata: {environment: 'production', git_sha: 'abc123'},
    weights: [{mount_location: '/models/base', source: 'hf://meta-llama/Llama-3-8B'}]
  })
};

fetch('https://api.baseten.co/v1/teams/{team_id}/llm_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.baseten.co/v1/teams/{team_id}/llm_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([
    'resources' => [
        
    ],
    'name' => '<string>',
    'region' => '<string>',
    'llm_version' => '<string>',
    'llm_config' => [
        
    ],
    'environment_variables' => [
        
    ],
    'model_metadata' => [
        
    ],
    'autoscaling_settings' => [
        'autoscaling_window' => 600,
        'concurrency_target' => null,
        'max_replica' => 5,
        'max_scale_down_rate' => null,
        'min_replica' => 1,
        'scale_down_delay' => 300,
        'target_in_flight_tokens' => null,
        'target_utilization_percentage' => null
    ],
    'additional_autoscaling_config' => [
        'metrics' => [
                [
                                'name' => 'in_flight_tokens',
                                'target' => 40000
                ]
        ]
    ],
    'metadata' => [
        'environment' => 'production',
        'git_sha' => 'abc123'
    ],
    'weights' => [
        [
                'mount_location' => '/models/base',
                'source' => 'hf://meta-llama/Llama-3-8B'
        ]
    ]
  ]),
  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://api.baseten.co/v1/teams/{team_id}/llm_models"

	payload := strings.NewReader("{\n  \"resources\": {},\n  \"name\": \"<string>\",\n  \"region\": \"<string>\",\n  \"llm_version\": \"<string>\",\n  \"llm_config\": {},\n  \"environment_variables\": {},\n  \"model_metadata\": {},\n  \"autoscaling_settings\": {\n    \"autoscaling_window\": 600,\n    \"concurrency_target\": null,\n    \"max_replica\": 5,\n    \"max_scale_down_rate\": null,\n    \"min_replica\": 1,\n    \"scale_down_delay\": 300,\n    \"target_in_flight_tokens\": null,\n    \"target_utilization_percentage\": null\n  },\n  \"additional_autoscaling_config\": {\n    \"metrics\": [\n      {\n        \"name\": \"in_flight_tokens\",\n        \"target\": 40000\n      }\n    ]\n  },\n  \"metadata\": {\n    \"environment\": \"production\",\n    \"git_sha\": \"abc123\"\n  },\n  \"weights\": [\n    {\n      \"mount_location\": \"/models/base\",\n      \"source\": \"hf://meta-llama/Llama-3-8B\"\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://api.baseten.co/v1/teams/{team_id}/llm_models")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"resources\": {},\n  \"name\": \"<string>\",\n  \"region\": \"<string>\",\n  \"llm_version\": \"<string>\",\n  \"llm_config\": {},\n  \"environment_variables\": {},\n  \"model_metadata\": {},\n  \"autoscaling_settings\": {\n    \"autoscaling_window\": 600,\n    \"concurrency_target\": null,\n    \"max_replica\": 5,\n    \"max_scale_down_rate\": null,\n    \"min_replica\": 1,\n    \"scale_down_delay\": 300,\n    \"target_in_flight_tokens\": null,\n    \"target_utilization_percentage\": null\n  },\n  \"additional_autoscaling_config\": {\n    \"metrics\": [\n      {\n        \"name\": \"in_flight_tokens\",\n        \"target\": 40000\n      }\n    ]\n  },\n  \"metadata\": {\n    \"environment\": \"production\",\n    \"git_sha\": \"abc123\"\n  },\n  \"weights\": [\n    {\n      \"mount_location\": \"/models/base\",\n      \"source\": \"hf://meta-llama/Llama-3-8B\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.baseten.co/v1/teams/{team_id}/llm_models")

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  \"resources\": {},\n  \"name\": \"<string>\",\n  \"region\": \"<string>\",\n  \"llm_version\": \"<string>\",\n  \"llm_config\": {},\n  \"environment_variables\": {},\n  \"model_metadata\": {},\n  \"autoscaling_settings\": {\n    \"autoscaling_window\": 600,\n    \"concurrency_target\": null,\n    \"max_replica\": 5,\n    \"max_scale_down_rate\": null,\n    \"min_replica\": 1,\n    \"scale_down_delay\": 300,\n    \"target_in_flight_tokens\": null,\n    \"target_utilization_percentage\": null\n  },\n  \"additional_autoscaling_config\": {\n    \"metrics\": [\n      {\n        \"name\": \"in_flight_tokens\",\n        \"target\": 40000\n      }\n    ]\n  },\n  \"metadata\": {\n    \"environment\": \"production\",\n    \"git_sha\": \"abc123\"\n  },\n  \"weights\": [\n    {\n      \"mount_location\": \"/models/base\",\n      \"source\": \"hf://meta-llama/Llama-3-8B\"\n    }\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "model_id": "<string>",
  "version_id": "<string>",
  "hostname": "<string>",
  "instance_type_name": "<string>"
}

Authorizations

Authorization

string

header

required

Send Authorization: Bearer <api_key>. The legacy Authorization: Api-Key <api_key> scheme is also accepted.

Path Parameters

team_id

string

required

Body

application/json

A request to create a BIS-LLM model

resources

Resources · object

required

Resources allocated to the model

name

string

required

Name of the model

region

string | null

Region in which to deploy the model

llm_version

string | null

Version of the helm chart to use.

llm_config

Llm Config · object

Configuration specific to the LLM model

environment_variables

Environment Variables · object

Environment variables for the model

model_metadata

Model Metadata · object | null

Model metadata persisted into model_config

autoscaling_settings

UpdateAutoscalingSettingsV1 · object | null

Autoscaling settings for the model

Show child attributes

Example:

{
  "autoscaling_window": 600,
  "concurrency_target": null,
  "max_replica": 5,
  "max_scale_down_rate": null,
  "min_replica": 1,
  "scale_down_delay": 300,
  "target_in_flight_tokens": null,
  "target_utilization_percentage": null
}

additional_autoscaling_config

Additional Autoscaling Config · object | null

Additional autoscaling configuration (e.g. target in-flight tokens)

Example:

{
  "metrics": [
    {
      "name": "in_flight_tokens",
      "target": 40000
    }
  ]
}

metadata

Metadata · object | null

User-defined metadata for the deployment

Example:

{
  "environment": "production",
  "git_sha": "abc123"
}

weights

Weights · object[] | null

Weight configurations for BDN model weight distribution

Example:

[
  {
    "mount_location": "/models/base",
    "source": "hf://meta-llama/Llama-3-8B"
  }
]

Response

200 - application/json

Handle for a BIS-LLM model deployment.

model_id

string

required

Unique identifier of the model

version_id

string

required

Unique identifier of the model version

hostname

string

required

Hostname used to invoke the model

instance_type_name

string | null

Name of the instance type the model deployment is running on

⌘I

cURL

curl --request POST \
--url https://api.baseten.co/v1/teams/{team_id}/llm_models \
--header "Authorization: Bearer $BASETEN_API_KEY" \
--data '{
  "resources": null,
  "region": null,
  "llm_version": null,
  "model_metadata": null,
  "autoscaling_settings": {
    "autoscaling_window": 600,
    "concurrency_target": null,
    "max_replica": 5,
    "max_scale_down_rate": null,
    "min_replica": 1,
    "scale_down_delay": 300,
    "target_in_flight_tokens": null,
    "target_utilization_percentage": null
  },
  "additional_autoscaling_config": {
    "metrics": [
      {
        "name": "in_flight_tokens",
        "target": 40000
      }
    ]
  },
  "metadata": {
    "environment": "production",
    "git_sha": "abc123"
  },
  "weights": [
    {
      "mount_location": "/models/base",
      "source": "hf://meta-llama/Llama-3-8B"
    }
  ],
  "name": null
}'

import requests
import os
API_KEY = os.environ.get("BASETEN_API_KEY", "<YOUR_API_KEY>")
url = "https://api.baseten.co/v1/teams/{team_id}/llm_models"

headers = {"Authorization": f"Bearer {API_KEY}"}

response = requests.request(
    "POST",
    url,
    headers=headers,
    json={'resources': None, 'region': None, 'llm_version': None, 'model_metadata': None, 'autoscaling_settings': {'autoscaling_window': 600, 'concurrency_target': None, 'max_replica': 5, 'max_scale_down_rate': None, 'min_replica': 1, 'scale_down_delay': 300, 'target_in_flight_tokens': None, 'target_utilization_percentage': None}, 'additional_autoscaling_config': {'metrics': [{'name': 'in_flight_tokens', 'target': 40000}]}, 'metadata': {'environment': 'production', 'git_sha': 'abc123'}, 'weights': [{'mount_location': '/models/base', 'source': 'hf://meta-llama/Llama-3-8B'}], 'name': None}
)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    resources: {},
    name: '<string>',
    region: '<string>',
    llm_version: '<string>',
    llm_config: {},
    environment_variables: {},
    model_metadata: {},
    autoscaling_settings: {
      autoscaling_window: 600,
      concurrency_target: null,
      max_replica: 5,
      max_scale_down_rate: null,
      min_replica: 1,
      scale_down_delay: 300,
      target_in_flight_tokens: null,
      target_utilization_percentage: null
    },
    additional_autoscaling_config: {metrics: [{name: 'in_flight_tokens', target: 40000}]},
    metadata: {environment: 'production', git_sha: 'abc123'},
    weights: [{mount_location: '/models/base', source: 'hf://meta-llama/Llama-3-8B'}]
  })
};

fetch('https://api.baseten.co/v1/teams/{team_id}/llm_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.baseten.co/v1/teams/{team_id}/llm_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([
    'resources' => [
        
    ],
    'name' => '<string>',
    'region' => '<string>',
    'llm_version' => '<string>',
    'llm_config' => [
        
    ],
    'environment_variables' => [
        
    ],
    'model_metadata' => [
        
    ],
    'autoscaling_settings' => [
        'autoscaling_window' => 600,
        'concurrency_target' => null,
        'max_replica' => 5,
        'max_scale_down_rate' => null,
        'min_replica' => 1,
        'scale_down_delay' => 300,
        'target_in_flight_tokens' => null,
        'target_utilization_percentage' => null
    ],
    'additional_autoscaling_config' => [
        'metrics' => [
                [
                                'name' => 'in_flight_tokens',
                                'target' => 40000
                ]
        ]
    ],
    'metadata' => [
        'environment' => 'production',
        'git_sha' => 'abc123'
    ],
    'weights' => [
        [
                'mount_location' => '/models/base',
                'source' => 'hf://meta-llama/Llama-3-8B'
        ]
    ]
  ]),
  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://api.baseten.co/v1/teams/{team_id}/llm_models"

	payload := strings.NewReader("{\n  \"resources\": {},\n  \"name\": \"<string>\",\n  \"region\": \"<string>\",\n  \"llm_version\": \"<string>\",\n  \"llm_config\": {},\n  \"environment_variables\": {},\n  \"model_metadata\": {},\n  \"autoscaling_settings\": {\n    \"autoscaling_window\": 600,\n    \"concurrency_target\": null,\n    \"max_replica\": 5,\n    \"max_scale_down_rate\": null,\n    \"min_replica\": 1,\n    \"scale_down_delay\": 300,\n    \"target_in_flight_tokens\": null,\n    \"target_utilization_percentage\": null\n  },\n  \"additional_autoscaling_config\": {\n    \"metrics\": [\n      {\n        \"name\": \"in_flight_tokens\",\n        \"target\": 40000\n      }\n    ]\n  },\n  \"metadata\": {\n    \"environment\": \"production\",\n    \"git_sha\": \"abc123\"\n  },\n  \"weights\": [\n    {\n      \"mount_location\": \"/models/base\",\n      \"source\": \"hf://meta-llama/Llama-3-8B\"\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://api.baseten.co/v1/teams/{team_id}/llm_models")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"resources\": {},\n  \"name\": \"<string>\",\n  \"region\": \"<string>\",\n  \"llm_version\": \"<string>\",\n  \"llm_config\": {},\n  \"environment_variables\": {},\n  \"model_metadata\": {},\n  \"autoscaling_settings\": {\n    \"autoscaling_window\": 600,\n    \"concurrency_target\": null,\n    \"max_replica\": 5,\n    \"max_scale_down_rate\": null,\n    \"min_replica\": 1,\n    \"scale_down_delay\": 300,\n    \"target_in_flight_tokens\": null,\n    \"target_utilization_percentage\": null\n  },\n  \"additional_autoscaling_config\": {\n    \"metrics\": [\n      {\n        \"name\": \"in_flight_tokens\",\n        \"target\": 40000\n      }\n    ]\n  },\n  \"metadata\": {\n    \"environment\": \"production\",\n    \"git_sha\": \"abc123\"\n  },\n  \"weights\": [\n    {\n      \"mount_location\": \"/models/base\",\n      \"source\": \"hf://meta-llama/Llama-3-8B\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.baseten.co/v1/teams/{team_id}/llm_models")

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  \"resources\": {},\n  \"name\": \"<string>\",\n  \"region\": \"<string>\",\n  \"llm_version\": \"<string>\",\n  \"llm_config\": {},\n  \"environment_variables\": {},\n  \"model_metadata\": {},\n  \"autoscaling_settings\": {\n    \"autoscaling_window\": 600,\n    \"concurrency_target\": null,\n    \"max_replica\": 5,\n    \"max_scale_down_rate\": null,\n    \"min_replica\": 1,\n    \"scale_down_delay\": 300,\n    \"target_in_flight_tokens\": null,\n    \"target_utilization_percentage\": null\n  },\n  \"additional_autoscaling_config\": {\n    \"metrics\": [\n      {\n        \"name\": \"in_flight_tokens\",\n        \"target\": 40000\n      }\n    ]\n  },\n  \"metadata\": {\n    \"environment\": \"production\",\n    \"git_sha\": \"abc123\"\n  },\n  \"weights\": [\n    {\n      \"mount_location\": \"/models/base\",\n      \"source\": \"hf://meta-llama/Llama-3-8B\"\n    }\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "model_id": "<string>",
  "version_id": "<string>",
  "hostname": "<string>",
  "instance_type_name": "<string>"
}

Reference

Inference API

Management API

CLI reference

SDK reference

Training API

Frontier Gateway API

CI/CD

Create a team BIS-LLM deployment

Authorizations

Path Parameters

Body

Response