Skip to content
POST/api/v1/simulation

Run a simulation

Previews OR executes a multi-turn persona simulation against a target model. `systemPrompt` is always required. WITHOUT `run: true` this is preview-only: it returns `status: "configured"` with the personas that would fire and their maxTurns, and makes no model call. WITH `run: true` it executes — that path also requires `orgId` (400 MISSING_ORG_ID), spends the org's stored BYOK provider key when it has one (falling back to the platform key, reported as `keySource`), reserves one `evals` usage unit (429 USAGE_LIMIT_EXCEEDED once the plan allowance is spent), and runs at most 5 personas at up to `maxTurns` (default 5) turns each. Optional `personaIds` (400 if none match), `model` (default `llama-3.3-70b-versatile`), `provider`, `concurrency`. A persona whose provider call failed is reported as `errored`, never as passed/failed; if every persona errored the request is a 502 SIMULATION_FAILED and the reserved unit is released. Returns `{status: executed|partial, model, provider, keySource, personasRun/Completed/Skipped, passed, failed, errored, durationMs, results[]}`.

Authentication

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

Response

202 example

{
  "run_id": "00000000-0000-0000-0000-000000000000"
}

All status codes

200OK.
202Simulation queued.
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).
502Bad Gateway — SIMULATION_FAILED.

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/simulation \
  -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/simulation", {
  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/simulation", 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/simulation", 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

400401403429500502

Other Evals endpoints