evaluations
Create evaluations test
Requires scopes: eval:write
POST
/
api
/
evaluations
/
{id}
/
playground
/
scorers
/
test
Create evaluations test
curl --request POST \
--url https://evalgate.com/api/evaluations/{id}/playground/scorers/test \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"input": "<string>",
"output": "<string>",
"configId": 123,
"expectedOutput": "<string>",
"context": "<string>"
}
'import requests
url = "https://evalgate.com/api/evaluations/{id}/playground/scorers/test"
payload = {
"input": "<string>",
"output": "<string>",
"configId": 123,
"expectedOutput": "<string>",
"context": "<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({
input: '<string>',
output: '<string>',
configId: 123,
expectedOutput: '<string>',
context: '<string>'
})
};
fetch('https://evalgate.com/api/evaluations/{id}/playground/scorers/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://evalgate.com/api/evaluations/{id}/playground/scorers/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([
'input' => '<string>',
'output' => '<string>',
'configId' => 123,
'expectedOutput' => '<string>',
'context' => '<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://evalgate.com/api/evaluations/{id}/playground/scorers/test"
payload := strings.NewReader("{\n \"input\": \"<string>\",\n \"output\": \"<string>\",\n \"configId\": 123,\n \"expectedOutput\": \"<string>\",\n \"context\": \"<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://evalgate.com/api/evaluations/{id}/playground/scorers/test")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"input\": \"<string>\",\n \"output\": \"<string>\",\n \"configId\": 123,\n \"expectedOutput\": \"<string>\",\n \"context\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://evalgate.com/api/evaluations/{id}/playground/scorers/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 \"input\": \"<string>\",\n \"output\": \"<string>\",\n \"configId\": 123,\n \"expectedOutput\": \"<string>\",\n \"context\": \"<string>\"\n}"
response = http.request(request)
puts response.read_body{
"provider": "local",
"model": "<string>",
"score": 123,
"passed": true,
"latencyMs": 123,
"aggregation": "all_pass",
"reasoning": "<string>",
"flags": [
"<string>"
],
"signals": {},
"judgeId": "<string>",
"retries": 123,
"parseStatus": "failed",
"judgeResults": [
{
"type": "decision",
"latencyMs": 123,
"judgeId": "<string>",
"provider": "local",
"model": "<string>",
"errorCode": "<string>",
"error": "<string>",
"result": {
"provider": "local",
"model": "<string>",
"score": 123,
"passed": true,
"latencyMs": 123,
"reasoning": "<string>",
"signals": {},
"judgeId": "<string>",
"retries": 123,
"parseStatus": "failed",
"confidence": 123,
"modelCallId": "<string>",
"decisions": [
{
"type": "choice",
"confidence": 123,
"question": "<string>",
"questionId": "<string>",
"choice": "<string>",
"probabilities": {}
}
],
"tokenUsage": {
"input": 123,
"output": 123,
"total": 123
},
"modelProvenance": {
"provider": "local",
"model": "<string>",
"temperature": 123,
"prompt_hash": "<string>",
"top_p": 123,
"max_tokens": 123,
"seed": 123
},
"cached": false,
"judgeFingerprint": {},
"criterionResults": [
{
"title": "<string>",
"score": 123,
"passed": true,
"reasoning": "<string>",
"criterionId": "<string>"
}
],
"decisionProvenance": {
"purpose": "platform_assistance",
"provider": "typesafe",
"model": "<string>",
"disposition": "pass",
"fallbackUsed": true,
"questionSchemaHash": "<string>",
"inputConstructionVersion": "<string>",
"modelVersion": "<string>",
"threshold": 123,
"inputDigest": "<string>",
"calibrationVersion": "<string>",
"decisionPolicyVersion": "<string>",
"fallbackReason": "<string>"
}
},
"modelCallId": "<string>",
"weight": 123,
"modelProvenance": {
"provider": "local",
"model": "<string>",
"temperature": 123,
"prompt_hash": "<string>",
"top_p": 123,
"max_tokens": 123,
"seed": 123
},
"providerExecutionState": "cancelled"
}
],
"disagreement": {
"rate": 123,
"reasoningDivergence": 123,
"outlierJudgeIds": [
"<string>"
],
"requiresEscalation": true,
"nonPassRate": 123,
"interJudgeRate": 123
},
"judgeResultId": 123,
"judgeConfigHash": "<string>",
"comparabilityStatus": "not_comparable",
"confidence": 123,
"totalCostUsd": 123,
"tokenUsage": {
"input": 123,
"output": 123,
"total": 123
},
"executionCompleteness": {
"state": "unknown",
"expected": 123,
"successful": 123,
"incomplete": 123,
"complete": false
},
"variance": 123
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}Authorizations
Organization-scoped EvalGate API key. Discover the supported agent scopes at /.well-known/oauth-protected-resource. Per-operation grants are listed in x-evalgate-required-scopes; OpenAPI bearer security requirement arrays remain empty as required for non-OAuth schemes.
Path Parameters
Body
application/json
Response
Successful response
provider
Option 1 · enum<string>Option 2 · enum<string>Option 3 · enum<string>Option 4 · enum<string>Option 5 · enum<string>Option 6 · enum<string>Option 7 · enum<string>Option 8 · enum<string>Option 9 · enum<string>Option 10 · enum<string>Option 11 · enum<string>
required
Available options:
local aggregation
Option 1 · enum<string>Option 2 · enum<string>Option 3 · enum<string>Option 4 · enum<string>Option 5 · enum<string>Option 6 · enum<string>
required
Available options:
all_pass Show child attributes
Show child attributes
parseStatus
Option 1 · enum<string>Option 2 · enum<string>Option 3 · enum<string>Option 4 · enum<string>
required
Available options:
failed Show child attributes
Show child attributes
Show child attributes
Show child attributes
comparabilityStatus
Option 1 · enum<string>Option 2 · enum<string>Option 3 · enum<string>Option 4 · enum<string>
Available options:
not_comparable Show child attributes
Show child attributes
Show child attributes
Show child attributes
⌘I
Create evaluations test
curl --request POST \
--url https://evalgate.com/api/evaluations/{id}/playground/scorers/test \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"input": "<string>",
"output": "<string>",
"configId": 123,
"expectedOutput": "<string>",
"context": "<string>"
}
'import requests
url = "https://evalgate.com/api/evaluations/{id}/playground/scorers/test"
payload = {
"input": "<string>",
"output": "<string>",
"configId": 123,
"expectedOutput": "<string>",
"context": "<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({
input: '<string>',
output: '<string>',
configId: 123,
expectedOutput: '<string>',
context: '<string>'
})
};
fetch('https://evalgate.com/api/evaluations/{id}/playground/scorers/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://evalgate.com/api/evaluations/{id}/playground/scorers/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([
'input' => '<string>',
'output' => '<string>',
'configId' => 123,
'expectedOutput' => '<string>',
'context' => '<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://evalgate.com/api/evaluations/{id}/playground/scorers/test"
payload := strings.NewReader("{\n \"input\": \"<string>\",\n \"output\": \"<string>\",\n \"configId\": 123,\n \"expectedOutput\": \"<string>\",\n \"context\": \"<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://evalgate.com/api/evaluations/{id}/playground/scorers/test")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"input\": \"<string>\",\n \"output\": \"<string>\",\n \"configId\": 123,\n \"expectedOutput\": \"<string>\",\n \"context\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://evalgate.com/api/evaluations/{id}/playground/scorers/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 \"input\": \"<string>\",\n \"output\": \"<string>\",\n \"configId\": 123,\n \"expectedOutput\": \"<string>\",\n \"context\": \"<string>\"\n}"
response = http.request(request)
puts response.read_body{
"provider": "local",
"model": "<string>",
"score": 123,
"passed": true,
"latencyMs": 123,
"aggregation": "all_pass",
"reasoning": "<string>",
"flags": [
"<string>"
],
"signals": {},
"judgeId": "<string>",
"retries": 123,
"parseStatus": "failed",
"judgeResults": [
{
"type": "decision",
"latencyMs": 123,
"judgeId": "<string>",
"provider": "local",
"model": "<string>",
"errorCode": "<string>",
"error": "<string>",
"result": {
"provider": "local",
"model": "<string>",
"score": 123,
"passed": true,
"latencyMs": 123,
"reasoning": "<string>",
"signals": {},
"judgeId": "<string>",
"retries": 123,
"parseStatus": "failed",
"confidence": 123,
"modelCallId": "<string>",
"decisions": [
{
"type": "choice",
"confidence": 123,
"question": "<string>",
"questionId": "<string>",
"choice": "<string>",
"probabilities": {}
}
],
"tokenUsage": {
"input": 123,
"output": 123,
"total": 123
},
"modelProvenance": {
"provider": "local",
"model": "<string>",
"temperature": 123,
"prompt_hash": "<string>",
"top_p": 123,
"max_tokens": 123,
"seed": 123
},
"cached": false,
"judgeFingerprint": {},
"criterionResults": [
{
"title": "<string>",
"score": 123,
"passed": true,
"reasoning": "<string>",
"criterionId": "<string>"
}
],
"decisionProvenance": {
"purpose": "platform_assistance",
"provider": "typesafe",
"model": "<string>",
"disposition": "pass",
"fallbackUsed": true,
"questionSchemaHash": "<string>",
"inputConstructionVersion": "<string>",
"modelVersion": "<string>",
"threshold": 123,
"inputDigest": "<string>",
"calibrationVersion": "<string>",
"decisionPolicyVersion": "<string>",
"fallbackReason": "<string>"
}
},
"modelCallId": "<string>",
"weight": 123,
"modelProvenance": {
"provider": "local",
"model": "<string>",
"temperature": 123,
"prompt_hash": "<string>",
"top_p": 123,
"max_tokens": 123,
"seed": 123
},
"providerExecutionState": "cancelled"
}
],
"disagreement": {
"rate": 123,
"reasoningDivergence": 123,
"outlierJudgeIds": [
"<string>"
],
"requiresEscalation": true,
"nonPassRate": 123,
"interJudgeRate": 123
},
"judgeResultId": 123,
"judgeConfigHash": "<string>",
"comparabilityStatus": "not_comparable",
"confidence": 123,
"totalCostUsd": 123,
"tokenUsage": {
"input": 123,
"output": 123,
"total": 123
},
"executionCompleteness": {
"state": "unknown",
"expected": 123,
"successful": 123,
"incomplete": 123,
"complete": false
},
"variance": 123
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "<string>",
"details": "<unknown>",
"requestId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"redaction": {
"applied": true,
"fieldCount": 1,
"secretCount": 1
}
}
}