Skip to content
POST/api/v1/prompts/ab-tests

Create an A/B test, route a request, or check for a winner

Action-discriminated A/B test manager backed by an ABTestManager that is constructed FRESH PER REQUEST and holds its tests only on that instance — nothing is persisted. action='create' returns a new test object with 2-20 variants (201) but that test is gone the moment the response is sent; action='route' { testId, requestId } and action='check-winner' { testId } therefore cannot find a test created by an earlier call and answer 400 ROUTING_ERROR / 404 NOT_FOUND respectively. Useful only for shaping a test definition client-side. Rate-limited to 30/min.

Authentication

Send Authorization: Bearer YOUR_API_KEY on every request. Generate API keys at /dashboard/settings/api-keys.

Request body required

Schema
{
  "application/json": {
    "schema": {
      "oneOf": [
        {
          "type": "object",
          "properties": {
            "action": {
              "type": "string",
              "enum": [
                "create"
              ]
            },
            "name": {
              "type": "string",
              "minLength": 1,
              "maxLength": 200
            },
            "promptId": {
              "type": "string",
              "minLength": 1,
              "maxLength": 200
            },
            "variants": {
              "minItems": 2,
              "maxItems": 20,
              "type": "array",
              "items": {}
            },
            "trafficSplit": {},
            "winnerCriteria": {
              "type": "object",
              "additionalProperties": {}
            }
          },
          "required": [
            "action",
            "name",
            "promptId",
            "variants"
          ],
          "additionalProperties": false
        },
        {
          "type": "object",
          "properties": {
            "action": {
              "type": "string",
              "enum": [
                "route"
              ]
            },
            "testId": {
              "type": "string",
              "minLength": 1,
              "maxLength": 200
            },
            "requestId": {
              "type": "string",
              "minLength": 1,
              "maxLength": 200
            }
          },
          "required": [
            "action",
            "testId",
            "requestId"
          ],
          "additionalProperties": false
        },
        {
          "type": "object",
          "properties": {
            "action": {
              "type": "string",
              "enum": [
                "check-winner"
              ]
            },
            "testId": {
              "type": "string",
              "minLength": 1,
              "maxLength": 200
            }
          },
          "required": [
            "action",
            "testId"
          ],
          "additionalProperties": false
        }
      ]
    }
  }
}

Response

200 example

{
  "success": true
}

All status codes

200Routed variant or winner-check result.
201Test created.
400(no description)
401(no description)
403Forbidden — the credential is valid but lacks the API-key scope, member role, or plan entitlement this operation requires.
404Test not found (route/check-winner).
429(no description)
500Internal Server Error — an unhandled error was converted to the standard error envelope (INTERNAL_ERROR).

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/prompts/ab-tests \
  -H "Authorization: Bearer $EVALGUARD_API_KEY"

TypeScript

// The TypeScript SDK (@evalguard/sdk) exposes TYPED methods — runEval,
// getEval, runSecurityScan, checkFirewall, … — not a generic request().
// For an arbitrary endpoint, call it directly:

const res = await fetch("https://evalguard.ai/api/v1/prompts/ab-tests", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}` },
});
console.log(res.status, await res.json());

Python

# The Python SDK (pip install evalguardai) exposes TYPED methods on
# EvalGuardClient — run_eval, get_eval, … — not a generic request().
# For an arbitrary endpoint, call it directly:

import os
import requests

headers = {"Authorization": f"Bearer {os.environ['EVALGUARD_API_KEY']}"}

response = requests.request("POST", "https://evalguard.ai/api/v1/prompts/ab-tests", headers=headers)
print(response.status_code, response.json())

Go

package main

import (
	"context"
	"fmt"
	"net/http"
	"os"
)

func main() {
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/prompts/ab-tests", nil)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
	resp, err := http.DefaultClient.Do(req)
	if err != nil { panic(err) }
	defer resp.Body.Close()
	fmt.Println(resp.Status)
}

Errors

400401403404429500

Other Prompts endpoints