Skip to main content
Deepgram's Docs

Search documentation

Type to search this documentation.

On this pageOverview

Think Models

GET https://agent.deepgram.com/v1/agent/settings/think/models

Retrieves the available think models that can be used for AI agent processing

Reference: https://developers.deepgram.com/reference/voice-agent/think-models

List of available think models

  • models (list of AgentThinkModelsV1ResponseModelsItems, required)

Invalid Request

  • ErrorResponse
  • err_code (string, optional) — The error code
  • err_msg (string, optional) — The error message
  • request_id (string, optional) — The request ID
  • category (string, optional) — The category of the error
  • message (string, optional) — A message about the error
  • details (string, optional) — A description of the error
  • request_id (string, optional) — The unique identifier of the request

OpenAI models

  • id (enum, required) — The unique identifier of the OpenAI model
    • Allowed values: gpt-5, gpt-5-mini, gpt-5-nano, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, gpt-4o, gpt-4o-mini
  • name (string, required) — The display name of the model
  • provider (any, required) — The provider of the model

Anthropic models

  • id (enum, required) — The unique identifier of the Anthropic model
    • Allowed values: claude-3-5-haiku-latest, claude-sonnet-4-20250514
  • name (string, required) — The display name of the model
  • provider (any, required) — The provider of the model

Google models

  • id (enum, required) — The unique identifier of the Google model
    • Allowed values: gemini-2.5-flash, gemini-2.0-flash, gemini-2.0-flash-lite
  • name (string, required) — The display name of the model
  • provider (any, required) — The provider of the model

Groq models

  • id (enum, required) — The unique identifier of the Groq model
    • Allowed values: openai/gpt-oss-20b
  • name (string, required) — The display name of the model
  • provider (any, required) — The provider of the model

AWS Bedrock models (custom models accepted)

  • id (string, required) — The unique identifier of the AWS Bedrock model (any model string accepted for BYO LLMs)
  • name (string, required) — The display name of the model
  • provider (any, required) — The provider of the model

Response

JSON
{
  "models": [
    {
      "id": "gpt-5",
      "name": "GPT-5",
      "provider": "open_ai"
    }
  ]
}

SDK Code

List
import requests

url = "https://agent.deepgram.com/v1/agent/settings/think/models"
response = requests.get(url)

print(response.json())
List
const res = await fetch(
  "https://agent.deepgram.com/v1/agent/settings/think/models",
);
const data = await res.json();
console.log(data);
Go
package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://agent.deepgram.com/v1/agent/settings/think/models"

	req, _ := http.NewRequest("GET", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
Ruby
require 'uri'
require 'net/http'

url = URI("https://agent.deepgram.com/v1/agent/settings/think/models")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)

response = http.request(request)
puts response.read_body
Java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.get("https://agent.deepgram.com/v1/agent/settings/think/models")
  .asString();
PHP
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('GET', 'https://agent.deepgram.com/v1/agent/settings/think/models');

echo $response->getBody();
C#
using RestSharp;

var client = new RestClient("https://agent.deepgram.com/v1/agent/settings/think/models");
var request = new RestRequest(Method.GET);
IRestResponse response = client.Execute(request);
Swift
import Foundation

let request = NSMutableURLRequest(url: NSURL(string: "https://agent.deepgram.com/v1/agent/settings/think/models")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "GET"

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
Suggest an edit

Propose a replacement for this page. The site team reviews it before applying any changes.

Export
Documentation menu