Skip to content
POST/api/v1/evals/hallucination-analysis

Heuristic hallucination root-cause analysis

Analyzes an input/output pair for hallucinations using a heuristic (no LLM call). Returns a synchronous result with score, causes, remediations and a summary. Optional context (RAG grounding) and expectedOutput improve detection.

Authentication

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

Request body required

Example

{
  "input": "string",
  "output": "string",
  "context": "<Optional grounding context (e.g. retriev>",
  "expectedOutput": "string"
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "properties": {
        "input": {
          "type": "string",
          "minLength": 1,
          "maxLength": 100000
        },
        "output": {
          "type": "string",
          "minLength": 1,
          "maxLength": 100000
        },
        "context": {
          "type": "string",
          "maxLength": 200000,
          "description": "Optional grounding context (e.g. retrieved RAG passages)."
        },
        "expectedOutput": {
          "type": "string",
          "maxLength": 100000
        }
      },
      "required": [
        "input",
        "output"
      ],
      "additionalProperties": false
    }
  }
}

Response

200 example

{
  "success": true
}

All status codes

200Hallucination analysis: { isHallucination, score, causes, remediations, summary }.
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.
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/evals/hallucination-analysis \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "input": "string", "output": "string", "context": "<Optional grounding context (e.g. retriev>", "expectedOutput": "string" }'

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/evals/hallucination-analysis", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "input": "string",
    "output": "string",
    "context": "<Optional grounding context (e.g. retriev>",
    "expectedOutput": "string"
  }),
});
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']}"}
headers["Content-Type"] = "application/json"

response = requests.request(
    "POST",
    "https://evalguard.ai/api/v1/evals/hallucination-analysis",
    headers=headers,
    json={
    "input": "string",
    "output": "string",
    "context": "<Optional grounding context (e.g. retriev>",
    "expectedOutput": "string"
},
)
print(response.status_code, response.json())

Go

package main

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

func main() {
	body := strings.NewReader(`{"input":"string","output":"string","context":"<Optional grounding context (e.g. retriev>","expectedOutput":"string"}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/evals/hallucination-analysis", body)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
	req.Header.Set("Content-Type", "application/json")
	resp, err := http.DefaultClient.Do(req)
	if err != nil { panic(err) }
	defer resp.Body.Close()
	fmt.Println(resp.Status)
}

Errors

400401403429500

Other Evals endpoints