create llm

curl --request POST \
  --url https://api.anam.ai/v1/llms \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "displayName": "My GPT-4o",
  "urls": [
    {
      "url": "https://api.openai.com/v1/chat/completions"
    }
  ],
  "llmFormat": "openai",
  "modelName": "gpt-4o",
  "secret": "sk-…",
  "temperature": 0.7
}
'

import requests

url = "https://api.anam.ai/v1/llms"

payload = {
    "displayName": "My GPT-4o",
    "urls": [{ "url": "https://api.openai.com/v1/chat/completions" }],
    "llmFormat": "openai",
    "modelName": "gpt-4o",
    "secret": "sk-…",
    "temperature": 0.7
}
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({
    displayName: 'My GPT-4o',
    urls: [{url: 'https://api.openai.com/v1/chat/completions'}],
    llmFormat: 'openai',
    modelName: 'gpt-4o',
    secret: 'sk-…',
    temperature: 0.7
  })
};

fetch('https://api.anam.ai/v1/llms', 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.anam.ai/v1/llms",
  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([
    'displayName' => 'My GPT-4o',
    'urls' => [
        [
                'url' => 'https://api.openai.com/v1/chat/completions'
        ]
    ],
    'llmFormat' => 'openai',
    'modelName' => 'gpt-4o',
    'secret' => 'sk-…',
    'temperature' => 0.7
  ]),
  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.anam.ai/v1/llms"

	payload := strings.NewReader("{\n  \"displayName\": \"My GPT-4o\",\n  \"urls\": [\n    {\n      \"url\": \"https://api.openai.com/v1/chat/completions\"\n    }\n  ],\n  \"llmFormat\": \"openai\",\n  \"modelName\": \"gpt-4o\",\n  \"secret\": \"sk-…\",\n  \"temperature\": 0.7\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.anam.ai/v1/llms")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"displayName\": \"My GPT-4o\",\n  \"urls\": [\n    {\n      \"url\": \"https://api.openai.com/v1/chat/completions\"\n    }\n  ],\n  \"llmFormat\": \"openai\",\n  \"modelName\": \"gpt-4o\",\n  \"secret\": \"sk-…\",\n  \"temperature\": 0.7\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.anam.ai/v1/llms")

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  \"displayName\": \"My GPT-4o\",\n  \"urls\": [\n    {\n      \"url\": \"https://api.openai.com/v1/chat/completions\"\n    }\n  ],\n  \"llmFormat\": \"openai\",\n  \"modelName\": \"gpt-4o\",\n  \"secret\": \"sk-…\",\n  \"temperature\": 0.7\n}"

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

{
  "id": "a7cf662c-2ace-4de1-a21e-ef0fbf144bb7",
  "displayName": "GPT-4o",
  "description": "OpenAI GPT-4o default configuration.",
  "llmFormat": "openai",
  "urls": [
    {
      "url": "https://api.openai.com/v1/chat/completions"
    }
  ],
  "modelName": "gpt-4o",
  "temperature": 0.7,
  "maxTokens": 1024,
  "deploymentName": null,
  "apiVersion": null,
  "metadata": {},
  "displayTags": [
    "openai"
  ],
  "isDefault": true,
  "isGlobal": true,
  "isZdr": false,
  "isDeprecated": false,
  "createdByOrganizationId": null,
  "createdAt": "2026-04-20T10:00:00.000Z",
  "updatedAt": null
}

{
  "error": "Service temporarily unavailable",
  "message": "We could not check your API key. Please retry shortly."
}

POST

llms

create llm

curl --request POST \
  --url https://api.anam.ai/v1/llms \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "displayName": "My GPT-4o",
  "urls": [
    {
      "url": "https://api.openai.com/v1/chat/completions"
    }
  ],
  "llmFormat": "openai",
  "modelName": "gpt-4o",
  "secret": "sk-…",
  "temperature": 0.7
}
'

import requests

url = "https://api.anam.ai/v1/llms"

payload = {
    "displayName": "My GPT-4o",
    "urls": [{ "url": "https://api.openai.com/v1/chat/completions" }],
    "llmFormat": "openai",
    "modelName": "gpt-4o",
    "secret": "sk-…",
    "temperature": 0.7
}
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({
    displayName: 'My GPT-4o',
    urls: [{url: 'https://api.openai.com/v1/chat/completions'}],
    llmFormat: 'openai',
    modelName: 'gpt-4o',
    secret: 'sk-…',
    temperature: 0.7
  })
};

fetch('https://api.anam.ai/v1/llms', 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.anam.ai/v1/llms",
  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([
    'displayName' => 'My GPT-4o',
    'urls' => [
        [
                'url' => 'https://api.openai.com/v1/chat/completions'
        ]
    ],
    'llmFormat' => 'openai',
    'modelName' => 'gpt-4o',
    'secret' => 'sk-…',
    'temperature' => 0.7
  ]),
  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.anam.ai/v1/llms"

	payload := strings.NewReader("{\n  \"displayName\": \"My GPT-4o\",\n  \"urls\": [\n    {\n      \"url\": \"https://api.openai.com/v1/chat/completions\"\n    }\n  ],\n  \"llmFormat\": \"openai\",\n  \"modelName\": \"gpt-4o\",\n  \"secret\": \"sk-…\",\n  \"temperature\": 0.7\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.anam.ai/v1/llms")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"displayName\": \"My GPT-4o\",\n  \"urls\": [\n    {\n      \"url\": \"https://api.openai.com/v1/chat/completions\"\n    }\n  ],\n  \"llmFormat\": \"openai\",\n  \"modelName\": \"gpt-4o\",\n  \"secret\": \"sk-…\",\n  \"temperature\": 0.7\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.anam.ai/v1/llms")

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  \"displayName\": \"My GPT-4o\",\n  \"urls\": [\n    {\n      \"url\": \"https://api.openai.com/v1/chat/completions\"\n    }\n  ],\n  \"llmFormat\": \"openai\",\n  \"modelName\": \"gpt-4o\",\n  \"secret\": \"sk-…\",\n  \"temperature\": 0.7\n}"

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

{
  "id": "a7cf662c-2ace-4de1-a21e-ef0fbf144bb7",
  "displayName": "GPT-4o",
  "description": "OpenAI GPT-4o default configuration.",
  "llmFormat": "openai",
  "urls": [
    {
      "url": "https://api.openai.com/v1/chat/completions"
    }
  ],
  "modelName": "gpt-4o",
  "temperature": 0.7,
  "maxTokens": 1024,
  "deploymentName": null,
  "apiVersion": null,
  "metadata": {},
  "displayTags": [
    "openai"
  ],
  "isDefault": true,
  "isGlobal": true,
  "isZdr": false,
  "isDeprecated": false,
  "createdByOrganizationId": null,
  "createdAt": "2026-04-20T10:00:00.000Z",
  "updatedAt": null
}

{
  "error": "Service temporarily unavailable",
  "message": "We could not check your API key. Please retry shortly."
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Endpoint URLs, model and credentials for the LLM. secret is encrypted at rest and never returned. llmFormat is the upstream API's wire protocol: openai, groq_openai and gemini need urls, modelName and secret; azure_openai needs urls, deploymentName, apiVersion and secret; none needs only displayName.

displayName

string

required

llmFormat

enum<string>

required

Available options:

openai,

azure_openai,

groq_openai,

gemini,

none

description

string

urls

object[]

Minimum array length: 1

Show child attributes

modelName

string

deploymentName

string

apiVersion

string

temperature

number | null

Required range: 0 <= x <= 2

maxTokens

integer

default:4096

Required range: x >= 1

secret

string

metadata

object

reasoningEffort

string | null

Reasoning effort for models that take it, sent to the provider as is, such as low, medium or high (values depend on the model). Omit or set null for the model default.

Maximum string length: 50

Example:

"minimal"

reasoningFormat

enum<string> | null

Groq reasoning format hint. Omit or set null to use the model default.

Available options:

parsed,

hidden,

null

Response

Successfully created LLM

An LLM configuration a persona can use. Secrets are never returned.

string<uuid>

Unique identifier for the LLM configuration.

displayName

string

Human-readable name shown in the Lab.

description

string | null

Free-form description of the LLM configuration.

llmFormat

enum<string>

Wire format used to call the upstream LLM.

Available options:

openai,

azure_openai,

groq_openai,

gemini,

none

urls

object[]

Endpoints configured for this LLM. Omitted for Anam's global LLMs.

Show child attributes

modelName

string | null

Upstream model identifier (e.g. gpt-4o).

temperature

number | null

Sampling temperature applied when calling the LLM.

maxTokens

integer | null

Maximum tokens generated per response.

deploymentName

string | null

Azure OpenAI deployment name. Only used when llmFormat is azure_openai; omitted for Anam's global LLMs.

apiVersion

string | null

Azure OpenAI API version. Only used when llmFormat is azure_openai; omitted for Anam's global LLMs.

metadata

object

Free-form provider-specific metadata.

displayTags

string[]

Tags used to categorise the LLM in the Lab UI.

isDefault

boolean

Whether this LLM is a built-in default available to every organization.

isGlobal

boolean

Whether this LLM is visible to every organization.

isZdr

boolean

Whether this LLM meets the Zero Data Retention requirements.

isDeprecated

boolean

read-only

Whether this stock LLM is deprecated. Deprecated LLMs remain available to ephemeral sessions but cannot be newly assigned to personas.

reasoningEffort

string | null

Reasoning effort hint for models that accept it. Forwarded verbatim to the provider/engine; supported values depend on the model. Null means the model default is used.

reasoningFormat

enum<string> | null

Reasoning format hint for models that accept it. Null means the model default is used.

Available options:

parsed,

hidden,

null

createdByOrganizationId

string | null

ID of the organization that created the LLM, or null for global defaults. IDs may be either UUIDs or nanoid-style strings depending on when the organization was created.

createdAt

string<date-time>

Timestamp when the LLM was created.

updatedAt

string<date-time> | null

Timestamp when the LLM was last updated.

Use the API

Sessions

Meetings

Avatar Videos

Personas

Avatars

Voices

Pronunciation Dictionaries

LLMs

Knowledge

Tools

Share Links

Engine

create llm

Authorizations

Body

Response