List LLMs

GET

llms

List LLMs

curl --request GET \
  --url https://api.dialnexa.com/v1/llms \
  --header 'Authorization: Bearer <token>'

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.dialnexa.com/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.dialnexa.com/v1/llms",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://api.dialnexa.com/v1/llms"

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

	req.Header.Add("Authorization", "Bearer <token>")

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

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

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.dialnexa.com/v1/llms")

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

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

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

[
  {
    "id": "llm_mfgt5q2x8k4w7r",
    "name": "GPT-4.1 Mini",
    "provider": "openai"
  }
]

{
  "message": "Request validation failed: Validation failed (numeric string is expected)"
}

{
  "message": "API key is missing or invalid. You can generate this by logging in into dashboard"
}

{
  "message": "An unexpected error occurred. Please try again later."
}

Read only List LLMs returns one page of models available as primary language models for DialNexa agents. Each entry includes the model’s stable id, display name and upstream provider (one of openai, google, gemini, groq, deepseek or sarvam). Use the id field as the value for llm_id when creating or updating an agent. The catalogue evolves continually as providers ship new models, so always call this endpoint at deploy time rather than hard-coding the list. API-key responses contain id, name, and provider. Tool-support and prompt-budget metadata are available in the dashboard and MCP catalog. DialNexa validates model compatibility when you save an agent with functions or integration tools.

When to use this

Agent build UIs: populate the LLM selector when creating or editing an agent.
Provider diversification: choose models from multiple providers so an upstream incident with one provider does not take down every agent.
Cost optimization: switch high-volume agents to smaller models when conversational quality stays acceptable.
Tool use: DialNexa checks that the chosen primary and fallback models support tool calling when you save an agent with functions, so an unsupported choice is rejected at that point.

How to choose an LLM

The right LLM depends on the use case:

Repeated scripts: test candidate models against the prompts, interruptions, and expected outcomes of your use case.
Complex conversations: test multi-turn reasoning, recovery, and tone before selecting a model for live calls.
Latency-sensitive flows: measure response timing on draft test calls and compare it with the configured fallback delay.
Multilingual or India-first: confirm the model handles your target language well by testing with the LLM Playground before publishing.

See LLMs and conversation behavior for deeper guidance.

List LLMs pagination

The default page size is 20. Requests above 100 models per page are capped at 100. API-key responses are plain arrays without pagination metadata; increment page until the returned array is shorter than your effective page size.

Query parameters

Parameter	Description
`page`	Page number, starting at 1. Must be a whole number; `0` or below is treated as `1`.
`limit`	Models per page. Must be a whole number. Default 20; `0` also returns 20, values above 100 are treated as 100, and a negative value fails with `500`.
`sortBy`	Column to sort by, for example `id`, `name` or `provider`. Default id. An unknown column returns `500`.
`sortOrder`	Sort direction. Default ASC. One of `ASC`, `DESC`.

Errors

401 Unauthorized is returned when the API key is missing or revoked.

Get LLM Details: fetch a single model’s detail.
Update Agent: change the LLM assigned to an existing agent.
LLM Playground: sandbox for testing model behavior on your prompts.
LLMs and conversation behavior: choosing the right model.

Authorizations

Authorization

string

header

required

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

Query Parameters

page

number

Page number, starting at 1. Must be a whole number; 0 or below is treated as 1.

Example:

1

limit

number

Models per page. Must be a whole number. Default 20; 0 also returns 20, values above 100 are treated as 100, and a negative value fails with 500.

Example:

20

sortBy

string

Column to sort by, for example id, name or provider. Default id. An unknown column returns 500.

Example:

"id"

sortOrder

enum<string>

Sort direction. Default ASC.

Available options:

ASC,

DESC

Response

LLMs returned successfully.

string

required

Signed LLM ID

Example:

"llm_mfgt5q2x8k4w7r"

name

string

provider

enum<string>

Available options:

google,

openai,

deepseek,

groq,

gemini,

sarvam

List LLMs

curl --request GET \
  --url https://api.dialnexa.com/v1/llms \
  --header 'Authorization: Bearer <token>'

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.dialnexa.com/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.dialnexa.com/v1/llms",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://api.dialnexa.com/v1/llms"

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

	req.Header.Add("Authorization", "Bearer <token>")

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

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

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.dialnexa.com/v1/llms")

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

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

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

[
  {
    "id": "llm_mfgt5q2x8k4w7r",
    "name": "GPT-4.1 Mini",
    "provider": "openai"
  }
]

{
  "message": "Request validation failed: Validation failed (numeric string is expected)"
}

{
  "message": "API key is missing or invalid. You can generate this by logging in into dashboard"
}

{
  "message": "An unexpected error occurred. Please try again later."
}

Overview

Endpoints

When to use this

How to choose an LLM

Query parameters

Errors

Authorizations

Query Parameters

Response

​When to use this

​How to choose an LLM

​List LLMs pagination

​Query parameters

​Errors

​Related endpoints

Authorizations

Query Parameters

Response

When to use this

How to choose an LLM

List LLMs pagination

Query parameters

Errors

Related endpoints