Create inference result

Create a new inference result. Identify the session with exactly one of sessionId or sessionCustomId. With sessionCustomId (your own conversation id) an existing session with that custom id is found and appended to: provide either versionId or productId as the anchor (if both are given, versionId wins). The session must already exist — create it first through the sessions API with that custom_id. If no matching session exists, the call is rejected with a 400. See Inference Results.

POST /inferenceResults

Create inference result

cURL

curl --request POST \
  --url https://api.galtea.ai/inferenceResults \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "sessionId": "session_123",
  "sessionCustomId": "my-conversation-42",
  "versionId": "ver_123",
  "productId": "prod_123",
  "userId": "user_123",
  "index": 0,
  "error": "<string>",
  "input": {},
  "actualOutput": "Model response text",
  "retrievalContext": "Retrieved context document",
  "latency": 123,
  "inputTokens": 123,
  "outputTokens": 123,
  "cacheReadInputTokens": 123,
  "tokens": 123,
  "costPerInputToken": 123,
  "costPerOutputToken": 123,
  "costPerCacheReadInputToken": 123,
  "cost": 123,
  "conversationSimulatorVersion": "<string>"
}
'

import requests

url = "https://api.galtea.ai/inferenceResults"

payload = {
    "sessionId": "session_123",
    "sessionCustomId": "my-conversation-42",
    "versionId": "ver_123",
    "productId": "prod_123",
    "userId": "user_123",
    "index": 0,
    "error": "<string>",
    "input": {},
    "actualOutput": "Model response text",
    "retrievalContext": "Retrieved context document",
    "latency": 123,
    "inputTokens": 123,
    "outputTokens": 123,
    "cacheReadInputTokens": 123,
    "tokens": 123,
    "costPerInputToken": 123,
    "costPerOutputToken": 123,
    "costPerCacheReadInputToken": 123,
    "cost": 123,
    "conversationSimulatorVersion": "<string>"
}
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({
    sessionId: 'session_123',
    sessionCustomId: 'my-conversation-42',
    versionId: 'ver_123',
    productId: 'prod_123',
    userId: 'user_123',
    index: 0,
    error: '<string>',
    input: {},
    actualOutput: 'Model response text',
    retrievalContext: 'Retrieved context document',
    latency: 123,
    inputTokens: 123,
    outputTokens: 123,
    cacheReadInputTokens: 123,
    tokens: 123,
    costPerInputToken: 123,
    costPerOutputToken: 123,
    costPerCacheReadInputToken: 123,
    cost: 123,
    conversationSimulatorVersion: '<string>'
  })
};

fetch('https://api.galtea.ai/inferenceResults', 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.galtea.ai/inferenceResults",
  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([
    'sessionId' => 'session_123',
    'sessionCustomId' => 'my-conversation-42',
    'versionId' => 'ver_123',
    'productId' => 'prod_123',
    'userId' => 'user_123',
    'index' => 0,
    'error' => '<string>',
    'input' => [
        
    ],
    'actualOutput' => 'Model response text',
    'retrievalContext' => 'Retrieved context document',
    'latency' => 123,
    'inputTokens' => 123,
    'outputTokens' => 123,
    'cacheReadInputTokens' => 123,
    'tokens' => 123,
    'costPerInputToken' => 123,
    'costPerOutputToken' => 123,
    'costPerCacheReadInputToken' => 123,
    'cost' => 123,
    'conversationSimulatorVersion' => '<string>'
  ]),
  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.galtea.ai/inferenceResults"

	payload := strings.NewReader("{\n  \"sessionId\": \"session_123\",\n  \"sessionCustomId\": \"my-conversation-42\",\n  \"versionId\": \"ver_123\",\n  \"productId\": \"prod_123\",\n  \"userId\": \"user_123\",\n  \"index\": 0,\n  \"error\": \"<string>\",\n  \"input\": {},\n  \"actualOutput\": \"Model response text\",\n  \"retrievalContext\": \"Retrieved context document\",\n  \"latency\": 123,\n  \"inputTokens\": 123,\n  \"outputTokens\": 123,\n  \"cacheReadInputTokens\": 123,\n  \"tokens\": 123,\n  \"costPerInputToken\": 123,\n  \"costPerOutputToken\": 123,\n  \"costPerCacheReadInputToken\": 123,\n  \"cost\": 123,\n  \"conversationSimulatorVersion\": \"<string>\"\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.galtea.ai/inferenceResults")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"sessionId\": \"session_123\",\n  \"sessionCustomId\": \"my-conversation-42\",\n  \"versionId\": \"ver_123\",\n  \"productId\": \"prod_123\",\n  \"userId\": \"user_123\",\n  \"index\": 0,\n  \"error\": \"<string>\",\n  \"input\": {},\n  \"actualOutput\": \"Model response text\",\n  \"retrievalContext\": \"Retrieved context document\",\n  \"latency\": 123,\n  \"inputTokens\": 123,\n  \"outputTokens\": 123,\n  \"cacheReadInputTokens\": 123,\n  \"tokens\": 123,\n  \"costPerInputToken\": 123,\n  \"costPerOutputToken\": 123,\n  \"costPerCacheReadInputToken\": 123,\n  \"cost\": 123,\n  \"conversationSimulatorVersion\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.galtea.ai/inferenceResults")

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  \"sessionId\": \"session_123\",\n  \"sessionCustomId\": \"my-conversation-42\",\n  \"versionId\": \"ver_123\",\n  \"productId\": \"prod_123\",\n  \"userId\": \"user_123\",\n  \"index\": 0,\n  \"error\": \"<string>\",\n  \"input\": {},\n  \"actualOutput\": \"Model response text\",\n  \"retrievalContext\": \"Retrieved context document\",\n  \"latency\": 123,\n  \"inputTokens\": 123,\n  \"outputTokens\": 123,\n  \"cacheReadInputTokens\": 123,\n  \"tokens\": 123,\n  \"costPerInputToken\": 123,\n  \"costPerOutputToken\": 123,\n  \"costPerCacheReadInputToken\": 123,\n  \"cost\": 123,\n  \"conversationSimulatorVersion\": \"<string>\"\n}"

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

201

{
  "id": "ir_123",
  "sessionId": "session_123",
  "userId": "user_123",
  "index": 0,
  "status": "PENDING",
  "error": null,
  "input": {
    "user_message": "User input text"
  },
  "actualOutput": "Model response",
  "latency": 150,
  "inputTokens": 100,
  "outputTokens": 50,
  "cacheReadInputTokens": 20,
  "tokens": 150,
  "costPerInputToken": 0.00001,
  "costPerOutputToken": 0.00003,
  "costPerCacheReadInputToken": 0.000005,
  "cost": 0.001,
  "creditsUsed": 1,
  "conversationSimulatorVersion": "1.0.0",
  "traceId": "a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4",
  "createdAt": "2023-11-07T05:31:56Z",
  "deletedAt": "2023-11-07T05:31:56Z"
}

{
  "error": "Error type",
  "message": "Error message description"
}

Authorizations

Authorization · string · header · required

API key authorization. Pass your API key in the Authorization header as a Bearer token. Both new (gsk_*) and legacy (gsk-) API keys are accepted, e.g. Authorization: Bearer gsk_... or Authorization: Bearer gsk-....

Body

application/json

sessionId · string

ID of the session. Provide this or sessionCustomId.

Example:

"session_123"

sessionCustomId · string

Your own conversation id. An existing session with this custom id is found and appended to; if none matches the call returns a 400, so create the session first through the sessions API. Requires versionId or productId. Provide this or sessionId.

Example:

"my-conversation-42"

versionId · string

Version anchor for the sessionCustomId lookup. Provide this or productId; if both are given, versionId wins.

Example:

"ver_123"

productId · string

Product anchor for the sessionCustomId lookup when no versionId is given: the existing session with that custom id is found across the product's versions.

Example:

"prod_123"

userId · string | null

ID of the user

Example:

"user_123"

index · integer

Index of the inference result

Example:

0

status · enum<string>

Status of the inference result

Available options: PENDING, GENERATED, FAILED, SKIPPED

error · string | null

Error message explaining why this inference result failed or was skipped

input · object | null

Structured input data. For plain text, use { user_message: "..." }

actualOutput · string object

Agent output. Plain text by default (the scored scalar); for voice, an envelope { assistant_message, content: [{ type, uri, transcript }] } carrying audio parts. An audio part without a transcript is rejected with a 400.

Example:

"Model response text"

retrievalContext · string | null

Retrieval context information

Example:

"Retrieved context document"

latency · number | null

Latency in milliseconds

inputTokens · integer | null

Number of input tokens

outputTokens · integer | null

Number of output tokens

cacheReadInputTokens · integer | null

Number of cache read input tokens

tokens · integer | null

Total number of tokens

costPerInputToken · number | null

Cost per input token

costPerOutputToken · number | null

Cost per output token

costPerCacheReadInputToken · number | null

Cost per cache read input token

cost · number | null

Total cost

conversationSimulatorVersion · string | null

Version of the conversation simulator

Response

201

application/json

Inference result created successfully

id · string

Example:

"ir_123"

sessionId · string

Example:

"session_123"

userId · string | null

Example:

"user_123"

index · integer

Order index within the session

Example:

0

status · enum<string>

Available options: PENDING, GENERATED, FAILED, SKIPPED

Example:

"PENDING"

error · string | null

Error message explaining why this inference result failed or was skipped

Example:

null

input · object | null

Structured input data. For plain text input, format is { user_message: "..." }

Example:

{ "user_message": "User input text" }

actualOutput · string object

The agent turn output. Plain text by default (the scored scalar). For voice turns, an envelope { assistant_message, content: [{ type, uri, transcript }] } carrying audio parts — the scored scalar stays the canonical transcript.

Example:

"Model response"

latency · integer | null

Example:

150

inputTokens · integer | null

Example:

100

outputTokens · integer | null

Example:

50

cacheReadInputTokens · integer | null

Example:

20

tokens · integer | null

Total tokens

Example:

150

costPerInputToken · number | null

Example:

0.00001

costPerOutputToken · number | null

Example:

0.00003

costPerCacheReadInputToken · number | null

Example:

0.000005

cost · number | null

Example:

0.001

creditsUsed · integer | null

Example:

1

conversationSimulatorVersion · string | null

Example:

"1.0.0"

traceId · string | null

W3C trace ID for the root span created during direct inference. The same trace ID is propagated to the user endpoint via the traceparent header.

Example:

"a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4"

createdAt · string<date-time>

deletedAt · string<date-time> | null