List Agent Think Models | Deepgram's Docs

GET/v1/agent/settings/think/modelsList Agent Think Models

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

Responses

objectAgentThinkModelsV1Response

AgentThinkModelsV1Response

modelsarray of valuerequired

Show child attributes

Show array items

oneOf · 5 options

Option 1objectAgentThinkModelsV1ResponseModelsItems0

AgentThinkModelsV1ResponseModelsItems0

OpenAI models

idstringrequired

The unique identifier of the OpenAI model

one of "gpt-5", "gpt-5-mini", "gpt-5-nano", "gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano", "gpt-4o", "gpt-4o-mini"

namestringrequired

The display name of the model

providervaluerequired

The provider of the model

Option 2objectAgentThinkModelsV1ResponseModelsItems1

AgentThinkModelsV1ResponseModelsItems1

Anthropic models

idstringrequired

The unique identifier of the Anthropic model

one of "claude-3-5-haiku-latest", "claude-sonnet-4-20250514"

namestringrequired

The display name of the model

providervaluerequired

The provider of the model

Option 3objectAgentThinkModelsV1ResponseModelsItems2

AgentThinkModelsV1ResponseModelsItems2

Google models

idstringrequired

The unique identifier of the Google model

one of "gemini-2.5-flash", "gemini-2.0-flash", "gemini-2.0-flash-lite"

namestringrequired

The display name of the model

providervaluerequired

The provider of the model

Option 4objectAgentThinkModelsV1ResponseModelsItems3

AgentThinkModelsV1ResponseModelsItems3

Groq models

idstringrequired

The unique identifier of the Groq model

one of "openai/gpt-oss-20b"

namestringrequired

The display name of the model

providervaluerequired

The provider of the model

Option 5objectAgentThinkModelsV1ResponseModelsItems4

AgentThinkModelsV1ResponseModelsItems4

AWS Bedrock models (custom models accepted)

idstringrequired

The unique identifier of the AWS Bedrock model (any model string accepted for BYO LLMs)

namestringrequired

The display name of the model

providervaluerequired

The provider of the model

Example response

{
  "models": [
    {
      "id": "gpt-4.1",
      "name": "string",
      "provider": null
    }
  ]
}

valueErrorResponse

ErrorResponse

oneOf · 3 options

Option 1stringErrorResponseTextError

ErrorResponseTextError

Option 2objectErrorResponseLegacyError

ErrorResponseLegacyError

err_codestring

The error code

err_msgstring

The error message

request_idstring

The request ID

Option 3objectErrorResponseModernError

ErrorResponseModernError

categorystring

The category of the error

detailsstring

A description of the error

messagestring

A message about the error

request_idstring

The unique identifier of the request

Example response

{
  "err_code": "string",
  "err_msg": "string",
  "request_id": "string"
}

Examples

curl -X GET 'https://agent.deepgram.com/v1/agent/settings/think/models'

const response = await fetch('https://agent.deepgram.com/v1/agent/settings/think/models', { method: 'GET' });
const data = await response.json();

const response = await fetch('https://agent.deepgram.com/v1/agent/settings/think/models', { method: 'GET' });
console.log(await response.json());

import requests

response = requests.request("GET", "https://agent.deepgram.com/v1/agent/settings/think/models")
print(response.json())

package main

import (
	"context"
	"net/http"
)

func main() {
	ctx := context.Background()
	req, err := http.NewRequestWithContext(ctx, "GET", "https://agent.deepgram.com/v1/agent/settings/think/models", nil)
	if err != nil {
		panic(err)
	}
	resp, err := http.DefaultClient.Do(req)
	if err != nil {
		panic(err)
	}
	defer resp.Body.Close()
}

<?php
$request = curl_init("https://agent.deepgram.com/v1/agent/settings/think/models");
curl_setopt($request, CURLOPT_CUSTOMREQUEST, "GET");
$response = curl_exec($request);
curl_close($request);

var request = HttpRequest.newBuilder(URI.create("https://agent.deepgram.com/v1/agent/settings/think/models"))
    .method("GET", HttpRequest.BodyPublishers.noBody())
    .build();
var response = HttpClient.newHttpClient().send(request, HttpResponse.BodyHandlers.ofString());

require 'net/http'

uri = URI("https://agent.deepgram.com/v1/agent/settings/think/models")
request = Net::HTTPGenericRequest.new("GET", false, true, uri)
response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) { |http| http.request(request) }

using var client = new HttpClient();
using var request = new HttpRequestMessage(HttpMethod.Get, "https://agent.deepgram.com/v1/agent/settings/think/models");
using var response = await client.SendAsync(request);

{
  "models": [
    {
      "id": "gpt-4.1",
      "name": "string",
      "provider": null
    }
  ]
}

{
  "err_code": "string",
  "err_msg": "string",
  "request_id": "string"
}