Test Llm Config Inline

curl --request POST \
  --url https://api-prod.interactly.ai/workflows/v1/llm-configs/test \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "system_prompt": "<string>",
  "config": {
    "logical_id": "<string>",
    "named_llm_config_id": "<string>",
    "named_llm_config_name": "<string>",
    "provider": "azure_openai",
    "streaming": false,
    "max_retries": 3,
    "max_parse_retries": 3,
    "max_tokens": 123,
    "temperature": 0.5,
    "request_timeout_ms": 123,
    "seed": 123,
    "model_kwargs": {},
    "api_key": "<string>",
    "do_not_split_sentences": false,
    "truncated_max_recent_messages": 123,
    "model": "gpt-5-mini",
    "type": "azure_openai_llm",
    "endpoint": "<string>",
    "api_version": "<string>",
    "reasoning_effort": "low"
  },
  "messages": [
    {
      "content": "<string>",
      "role": "human"
    }
  ]
}
'

import requests

url = "https://api-prod.interactly.ai/workflows/v1/llm-configs/test"

payload = {
    "system_prompt": "<string>",
    "config": {
        "logical_id": "<string>",
        "named_llm_config_id": "<string>",
        "named_llm_config_name": "<string>",
        "provider": "azure_openai",
        "streaming": False,
        "max_retries": 3,
        "max_parse_retries": 3,
        "max_tokens": 123,
        "temperature": 0.5,
        "request_timeout_ms": 123,
        "seed": 123,
        "model_kwargs": {},
        "api_key": "<string>",
        "do_not_split_sentences": False,
        "truncated_max_recent_messages": 123,
        "model": "gpt-5-mini",
        "type": "azure_openai_llm",
        "endpoint": "<string>",
        "api_version": "<string>",
        "reasoning_effort": "low"
    },
    "messages": [
        {
            "content": "<string>",
            "role": "human"
        }
    ]
}
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({
    system_prompt: '<string>',
    config: {
      logical_id: '<string>',
      named_llm_config_id: '<string>',
      named_llm_config_name: '<string>',
      provider: 'azure_openai',
      streaming: false,
      max_retries: 3,
      max_parse_retries: 3,
      max_tokens: 123,
      temperature: 0.5,
      request_timeout_ms: 123,
      seed: 123,
      model_kwargs: {},
      api_key: '<string>',
      do_not_split_sentences: false,
      truncated_max_recent_messages: 123,
      model: 'gpt-5-mini',
      type: 'azure_openai_llm',
      endpoint: '<string>',
      api_version: '<string>',
      reasoning_effort: 'low'
    },
    messages: [{content: '<string>', role: 'human'}]
  })
};

fetch('https://api-prod.interactly.ai/workflows/v1/llm-configs/test', 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-prod.interactly.ai/workflows/v1/llm-configs/test",
  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([
    'system_prompt' => '<string>',
    'config' => [
        'logical_id' => '<string>',
        'named_llm_config_id' => '<string>',
        'named_llm_config_name' => '<string>',
        'provider' => 'azure_openai',
        'streaming' => false,
        'max_retries' => 3,
        'max_parse_retries' => 3,
        'max_tokens' => 123,
        'temperature' => 0.5,
        'request_timeout_ms' => 123,
        'seed' => 123,
        'model_kwargs' => [
                
        ],
        'api_key' => '<string>',
        'do_not_split_sentences' => false,
        'truncated_max_recent_messages' => 123,
        'model' => 'gpt-5-mini',
        'type' => 'azure_openai_llm',
        'endpoint' => '<string>',
        'api_version' => '<string>',
        'reasoning_effort' => 'low'
    ],
    'messages' => [
        [
                'content' => '<string>',
                'role' => 'human'
        ]
    ]
  ]),
  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-prod.interactly.ai/workflows/v1/llm-configs/test"

	payload := strings.NewReader("{\n  \"system_prompt\": \"<string>\",\n  \"config\": {\n    \"logical_id\": \"<string>\",\n    \"named_llm_config_id\": \"<string>\",\n    \"named_llm_config_name\": \"<string>\",\n    \"provider\": \"azure_openai\",\n    \"streaming\": false,\n    \"max_retries\": 3,\n    \"max_parse_retries\": 3,\n    \"max_tokens\": 123,\n    \"temperature\": 0.5,\n    \"request_timeout_ms\": 123,\n    \"seed\": 123,\n    \"model_kwargs\": {},\n    \"api_key\": \"<string>\",\n    \"do_not_split_sentences\": false,\n    \"truncated_max_recent_messages\": 123,\n    \"model\": \"gpt-5-mini\",\n    \"type\": \"azure_openai_llm\",\n    \"endpoint\": \"<string>\",\n    \"api_version\": \"<string>\",\n    \"reasoning_effort\": \"low\"\n  },\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"role\": \"human\"\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-prod.interactly.ai/workflows/v1/llm-configs/test")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"system_prompt\": \"<string>\",\n  \"config\": {\n    \"logical_id\": \"<string>\",\n    \"named_llm_config_id\": \"<string>\",\n    \"named_llm_config_name\": \"<string>\",\n    \"provider\": \"azure_openai\",\n    \"streaming\": false,\n    \"max_retries\": 3,\n    \"max_parse_retries\": 3,\n    \"max_tokens\": 123,\n    \"temperature\": 0.5,\n    \"request_timeout_ms\": 123,\n    \"seed\": 123,\n    \"model_kwargs\": {},\n    \"api_key\": \"<string>\",\n    \"do_not_split_sentences\": false,\n    \"truncated_max_recent_messages\": 123,\n    \"model\": \"gpt-5-mini\",\n    \"type\": \"azure_openai_llm\",\n    \"endpoint\": \"<string>\",\n    \"api_version\": \"<string>\",\n    \"reasoning_effort\": \"low\"\n  },\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"role\": \"human\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api-prod.interactly.ai/workflows/v1/llm-configs/test")

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  \"system_prompt\": \"<string>\",\n  \"config\": {\n    \"logical_id\": \"<string>\",\n    \"named_llm_config_id\": \"<string>\",\n    \"named_llm_config_name\": \"<string>\",\n    \"provider\": \"azure_openai\",\n    \"streaming\": false,\n    \"max_retries\": 3,\n    \"max_parse_retries\": 3,\n    \"max_tokens\": 123,\n    \"temperature\": 0.5,\n    \"request_timeout_ms\": 123,\n    \"seed\": 123,\n    \"model_kwargs\": {},\n    \"api_key\": \"<string>\",\n    \"do_not_split_sentences\": false,\n    \"truncated_max_recent_messages\": 123,\n    \"model\": \"gpt-5-mini\",\n    \"type\": \"azure_openai_llm\",\n    \"endpoint\": \"<string>\",\n    \"api_version\": \"<string>\",\n    \"reasoning_effort\": \"low\"\n  },\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"role\": \"human\"\n    }\n  ]\n}"

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

{
  "success": true,
  "response": "<string>",
  "error": "<string>",
  "provider": "<string>",
  "model": "<string>",
  "prompt_tokens": 123,
  "completion_tokens": 123,
  "total_tokens": 123,
  "latency_ms": 123,
  "winning_member": {
    "index": 123,
    "logical_id": "<string>",
    "provider": "<string>",
    "model": "<string>"
  },
  "backchannel_response": "<string>",
  "backchannel_member": {
    "index": 123,
    "logical_id": "<string>",
    "provider": "<string>",
    "model": "<string>"
  },
  "backchannel_prompt_tokens": 123,
  "backchannel_completion_tokens": 123,
  "backchannel_total_tokens": 123
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

LLM Configs

Test Llm Config Inline

Run a one-shot test invocation against a fully inline LLM configuration that has not been persisted yet (the create flow), and return the model’s reply.

Because there is no stored record to recover secrets from, the provider api_key must be supplied in body.config (or omitted to fall back to the team’s stored vendor credentials). Provider/runtime failures are returned as HTTP 200 with success=False and a clean error message, mirroring the saved-config test endpoint, so the dashboard can render them inline.

POST

workflows

llm-configs

test

Test Llm Config Inline

curl --request POST \
  --url https://api-prod.interactly.ai/workflows/v1/llm-configs/test \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "system_prompt": "<string>",
  "config": {
    "logical_id": "<string>",
    "named_llm_config_id": "<string>",
    "named_llm_config_name": "<string>",
    "provider": "azure_openai",
    "streaming": false,
    "max_retries": 3,
    "max_parse_retries": 3,
    "max_tokens": 123,
    "temperature": 0.5,
    "request_timeout_ms": 123,
    "seed": 123,
    "model_kwargs": {},
    "api_key": "<string>",
    "do_not_split_sentences": false,
    "truncated_max_recent_messages": 123,
    "model": "gpt-5-mini",
    "type": "azure_openai_llm",
    "endpoint": "<string>",
    "api_version": "<string>",
    "reasoning_effort": "low"
  },
  "messages": [
    {
      "content": "<string>",
      "role": "human"
    }
  ]
}
'

import requests

url = "https://api-prod.interactly.ai/workflows/v1/llm-configs/test"

payload = {
    "system_prompt": "<string>",
    "config": {
        "logical_id": "<string>",
        "named_llm_config_id": "<string>",
        "named_llm_config_name": "<string>",
        "provider": "azure_openai",
        "streaming": False,
        "max_retries": 3,
        "max_parse_retries": 3,
        "max_tokens": 123,
        "temperature": 0.5,
        "request_timeout_ms": 123,
        "seed": 123,
        "model_kwargs": {},
        "api_key": "<string>",
        "do_not_split_sentences": False,
        "truncated_max_recent_messages": 123,
        "model": "gpt-5-mini",
        "type": "azure_openai_llm",
        "endpoint": "<string>",
        "api_version": "<string>",
        "reasoning_effort": "low"
    },
    "messages": [
        {
            "content": "<string>",
            "role": "human"
        }
    ]
}
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({
    system_prompt: '<string>',
    config: {
      logical_id: '<string>',
      named_llm_config_id: '<string>',
      named_llm_config_name: '<string>',
      provider: 'azure_openai',
      streaming: false,
      max_retries: 3,
      max_parse_retries: 3,
      max_tokens: 123,
      temperature: 0.5,
      request_timeout_ms: 123,
      seed: 123,
      model_kwargs: {},
      api_key: '<string>',
      do_not_split_sentences: false,
      truncated_max_recent_messages: 123,
      model: 'gpt-5-mini',
      type: 'azure_openai_llm',
      endpoint: '<string>',
      api_version: '<string>',
      reasoning_effort: 'low'
    },
    messages: [{content: '<string>', role: 'human'}]
  })
};

fetch('https://api-prod.interactly.ai/workflows/v1/llm-configs/test', 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-prod.interactly.ai/workflows/v1/llm-configs/test",
  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([
    'system_prompt' => '<string>',
    'config' => [
        'logical_id' => '<string>',
        'named_llm_config_id' => '<string>',
        'named_llm_config_name' => '<string>',
        'provider' => 'azure_openai',
        'streaming' => false,
        'max_retries' => 3,
        'max_parse_retries' => 3,
        'max_tokens' => 123,
        'temperature' => 0.5,
        'request_timeout_ms' => 123,
        'seed' => 123,
        'model_kwargs' => [
                
        ],
        'api_key' => '<string>',
        'do_not_split_sentences' => false,
        'truncated_max_recent_messages' => 123,
        'model' => 'gpt-5-mini',
        'type' => 'azure_openai_llm',
        'endpoint' => '<string>',
        'api_version' => '<string>',
        'reasoning_effort' => 'low'
    ],
    'messages' => [
        [
                'content' => '<string>',
                'role' => 'human'
        ]
    ]
  ]),
  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-prod.interactly.ai/workflows/v1/llm-configs/test"

	payload := strings.NewReader("{\n  \"system_prompt\": \"<string>\",\n  \"config\": {\n    \"logical_id\": \"<string>\",\n    \"named_llm_config_id\": \"<string>\",\n    \"named_llm_config_name\": \"<string>\",\n    \"provider\": \"azure_openai\",\n    \"streaming\": false,\n    \"max_retries\": 3,\n    \"max_parse_retries\": 3,\n    \"max_tokens\": 123,\n    \"temperature\": 0.5,\n    \"request_timeout_ms\": 123,\n    \"seed\": 123,\n    \"model_kwargs\": {},\n    \"api_key\": \"<string>\",\n    \"do_not_split_sentences\": false,\n    \"truncated_max_recent_messages\": 123,\n    \"model\": \"gpt-5-mini\",\n    \"type\": \"azure_openai_llm\",\n    \"endpoint\": \"<string>\",\n    \"api_version\": \"<string>\",\n    \"reasoning_effort\": \"low\"\n  },\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"role\": \"human\"\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-prod.interactly.ai/workflows/v1/llm-configs/test")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"system_prompt\": \"<string>\",\n  \"config\": {\n    \"logical_id\": \"<string>\",\n    \"named_llm_config_id\": \"<string>\",\n    \"named_llm_config_name\": \"<string>\",\n    \"provider\": \"azure_openai\",\n    \"streaming\": false,\n    \"max_retries\": 3,\n    \"max_parse_retries\": 3,\n    \"max_tokens\": 123,\n    \"temperature\": 0.5,\n    \"request_timeout_ms\": 123,\n    \"seed\": 123,\n    \"model_kwargs\": {},\n    \"api_key\": \"<string>\",\n    \"do_not_split_sentences\": false,\n    \"truncated_max_recent_messages\": 123,\n    \"model\": \"gpt-5-mini\",\n    \"type\": \"azure_openai_llm\",\n    \"endpoint\": \"<string>\",\n    \"api_version\": \"<string>\",\n    \"reasoning_effort\": \"low\"\n  },\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"role\": \"human\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api-prod.interactly.ai/workflows/v1/llm-configs/test")

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  \"system_prompt\": \"<string>\",\n  \"config\": {\n    \"logical_id\": \"<string>\",\n    \"named_llm_config_id\": \"<string>\",\n    \"named_llm_config_name\": \"<string>\",\n    \"provider\": \"azure_openai\",\n    \"streaming\": false,\n    \"max_retries\": 3,\n    \"max_parse_retries\": 3,\n    \"max_tokens\": 123,\n    \"temperature\": 0.5,\n    \"request_timeout_ms\": 123,\n    \"seed\": 123,\n    \"model_kwargs\": {},\n    \"api_key\": \"<string>\",\n    \"do_not_split_sentences\": false,\n    \"truncated_max_recent_messages\": 123,\n    \"model\": \"gpt-5-mini\",\n    \"type\": \"azure_openai_llm\",\n    \"endpoint\": \"<string>\",\n    \"api_version\": \"<string>\",\n    \"reasoning_effort\": \"low\"\n  },\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"role\": \"human\"\n    }\n  ]\n}"

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

{
  "success": true,
  "response": "<string>",
  "error": "<string>",
  "provider": "<string>",
  "model": "<string>",
  "prompt_tokens": 123,
  "completion_tokens": 123,
  "total_tokens": 123,
  "latency_ms": 123,
  "winning_member": {
    "index": 123,
    "logical_id": "<string>",
    "provider": "<string>",
    "model": "<string>"
  },
  "backchannel_response": "<string>",
  "backchannel_member": {
    "index": 123,
    "logical_id": "<string>",
    "provider": "<string>",
    "model": "<string>"
  },
  "backchannel_prompt_tokens": 123,
  "backchannel_completion_tokens": 123,
  "backchannel_total_tokens": 123
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Authorizations

Authorization

string

header

required

Retrieve your API Key from Dashboard API Keys Section.

Body

application/json

system_prompt

string

required

Required, non-empty system prompt.

Minimum string length: 1

config

Azure OpenAI · object

required

Full config to test inline, before any config record is persisted (create flow). Unlike the saved-config test, there is no stored record to recover secrets from: the provider api_key must be supplied here, or omitted to fall back to the team's stored vendor credentials.

Azure OpenAI
OpenAI
Google
Anthropic
Custom LLM
Workflow Default LLM
No LLM
Group of LLMs
Group of regular and backchanneling LLMs

Show child attributes

messages

LLMTestMessage · object[]

Optional ordered conversation history to send to the model.

Show child attributes

Response

Successful Response

success

boolean

required

response

string | null

Concatenated model output text on success.

error

string | null

Clean error message when success is False.

provider

string | null

model

string | null

prompt_tokens

integer | null

completion_tokens

integer | null

total_tokens

integer | null

latency_ms

integer | null

winning_member

LLMTestMemberInfo · object | null

Which group member produced the main response.

Show child attributes

backchannel_response

string | null

Backchannel text emitted before the main response, if any.

backchannel_member

LLMTestMemberInfo · object | null

Producer of the backchannel response (null for a static backchannel).

Show child attributes

backchannel_prompt_tokens

integer | null

backchannel_completion_tokens

integer | null

backchannel_total_tokens

integer | null

Test Llm Config List Global Variables Endpoint

Getting Started

APIs

Campaigns

Workflows

SMS

Test Llm Config Inline

Authorizations

Body

Response