Skip to content
POST/api/v1/evals/safe-regenerate

Eval -> regenerate loop with cost-budget enforcement

Evaluates the input on per-dimension rubrics; if the worst dim is below the threshold, asks the BYOK LLM to regenerate, then re-evaluates. Stops on pass, max iterations, or no-improvement. Pre-flight cost estimate gates against `maxCostUsd` (402 if exceeded). Records final outcome to `safe_regenerate_runs` + `cost_ledger`.

Authentication

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

Request body required

Example

{
  "content": "<The candidate output to evaluate.>",
  "prompt": "<The prompt that produced the content.>",
  "threshold": 0.8,
  "maxIterations": 3,
  "dimensions": [
    "string"
  ],
  "scorerSet": "basic",
  "regeneratorModel": "string",
  "projectId": "00000000-0000-0000-0000-000000000000",
  "recordHistory": false,
  "maxCostUsd": 0
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "properties": {
        "content": {
          "type": "string",
          "minLength": 1,
          "maxLength": 50000,
          "description": "The candidate output to evaluate."
        },
        "prompt": {
          "type": "string",
          "minLength": 1,
          "maxLength": 50000,
          "description": "The prompt that produced the content."
        },
        "threshold": {
          "default": 0.8,
          "type": "number",
          "minimum": 0,
          "maximum": 1
        },
        "maxIterations": {
          "default": 3,
          "type": "integer",
          "minimum": 1,
          "maximum": 10
        },
        "dimensions": {
          "maxItems": 20,
          "type": "array",
          "items": {
            "type": "string",
            "minLength": 1,
            "maxLength": 50
          },
          "description": "Subset of pillars to gate on (default: all in scorerSet)."
        },
        "scorerSet": {
          "default": "basic",
          "type": "string",
          "enum": [
            "basic",
            "deep"
          ]
        },
        "regeneratorModel": {
          "type": "string",
          "minLength": 3,
          "maxLength": 120
        },
        "projectId": {
          "type": "string",
          "format": "uuid",
          "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
        },
        "recordHistory": {
          "default": false,
          "type": "boolean"
        },
        "maxCostUsd": {
          "type": "number",
          "minimum": 0,
          "maximum": 100
        }
      },
      "required": [
        "content",
        "prompt",
        "threshold",
        "maxIterations",
        "scorerSet",
        "recordHistory"
      ],
      "additionalProperties": false
    }
  }
}

Response

200 example

{
  "result": {
    "content": "string",
    "finalScore": 0,
    "passedThreshold": false,
    "iterationsTaken": 0,
    "iterationScores": [
      0
    ],
    "stopReason": "passed"
  },
  "cost": {
    "estimatedWorstCaseUsd": 0,
    "actualUsd": 0,
    "llmCallCount": 0,
    "actualInputTokens": 0,
    "actualOutputTokens": 0
  }
}

All status codes

200Evaluation + regen result.
400(no description)
401(no description)
402Payment required — estimated cost exceeds the per-call budget cap.
429(no description)

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/evals/safe-regenerate \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "content": "<The candidate output to evaluate.>", "prompt": "<The prompt that produced the content.>", "threshold": 0.8, "maxIterations": 3, "dimensions": [ "string" ], "scorerSet": "basic", "regeneratorModel": "string", "projectId": "00000000-0000-0000-0000-000000000000", "recordHistory": false, "maxCostUsd": 0 }'

TypeScript

import { EvalGuard } from "@evalguard/sdk";

const client = new EvalGuard({ apiKey: process.env.EVALGUARD_API_KEY });

const response = await client.request({
  method: "POST",
  path: "/api/v1/evals/safe-regenerate",
  body: {
    "content": "<The candidate output to evaluate.>",
    "prompt": "<The prompt that produced the content.>",
    "threshold": 0.8,
    "maxIterations": 3,
    "dimensions": [
      "string"
    ],
    "scorerSet": "basic",
    "regeneratorModel": "string",
    "projectId": "00000000-0000-0000-0000-000000000000",
    "recordHistory": false,
    "maxCostUsd": 0
  },
});
console.log(response);

Python

from evalguard import EvalGuard
import os

client = EvalGuard(api_key=os.environ["EVALGUARD_API_KEY"])

response = client.request(
    method="POST",
    path="/api/v1/evals/safe-regenerate",
    body={
    "content": "<The candidate output to evaluate.>",
    "prompt": "<The prompt that produced the content.>",
    "threshold": 0.8,
    "maxIterations": 3,
    "dimensions": [
        "string"
    ],
    "scorerSet": "basic",
    "regeneratorModel": "string",
    "projectId": "00000000-0000-0000-0000-000000000000",
    "recordHistory": False,
    "maxCostUsd": 0
},
)
print(response)

Go

package main

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

func main() {
	body := strings.NewReader(`{"content":"<The candidate output to evaluate.>","prompt":"<The prompt that produced the content.>","threshold":0.8,"maxIterations":3,"dimensions":["string"],"scorerSet":"basic","regeneratorModel":"string","projectId":"00000000-0000-0000-0000-000000000000","recordHistory":false,"maxCostUsd":0}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/evals/safe-regenerate", 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

400401402429

Other Evaluations endpoints