Skip to content
GET/api/v1/evals/{runId}/export

Download an eval run as a formatted file

Downloads the eval-run results in one of five formats (?format=json|csv|html|human-eval|junit, default json; anything else is 400 INVALID_FORMAT). Maps the stored eval_runs row + its eval_cases (ordered by case_index) back into the EvalOutput shape and dispatches to the matching @evalguard/core formatter. Access is enforced in code, not by RLS: the handler resolves the run's project → org and requires an org_members row for the caller (404 if the run does not exist, 403 NOT_ORG_MEMBER otherwise); the read runs on the service-role client for API-key callers, so RLS does not apply there. Returns a `Content-Disposition: attachment` response with filename `evalguard-<first 8 chars of runId>.<ext>` and `Cache-Control: private, no-store`.

Authentication

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

Parameters

runId in pathrequired
string
format in queryrequired

Output format. `json` is machine-readable; `csv` is spreadsheet-friendly; `html` is a standalone shareable summary; `human-eval` is a YAML reviewer workbook; `junit` is JUnit XML for CI integration.

string

Response

All status codes

200Formatted run output
400Invalid runId or unknown format
401Unauthenticated
403Not a member of the run's organization
404Run not found
429Too Many Requests — the per-key or per-organization rate limit was exceeded. Honour the Retry-After header.
500Internal Server Error — DB_ERROR.

Code samples

cURL

# {runId} is shown with an EXAMPLE value — replace it with real values.
curl -X GET \
  https://evalguard.ai/api/v1/evals/00000000-0000-0000-0000-000000000000/export \
  -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:
// {runId} is shown with an EXAMPLE value — replace it with real values.

const res = await fetch("https://evalguard.ai/api/v1/evals/00000000-0000-0000-0000-000000000000/export", {
  method: "GET",
  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:
# {runId} is shown with an EXAMPLE value — replace it with real values.

import os
import requests

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

response = requests.request("GET", "https://evalguard.ai/api/v1/evals/00000000-0000-0000-0000-000000000000/export", headers=headers)
print(response.status_code, response.json())

Go

package main

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

// {runId} is shown with an EXAMPLE value — replace it with real values.
func main() {
	req, _ := http.NewRequestWithContext(context.Background(), "GET", "https://evalguard.ai/api/v1/evals/00000000-0000-0000-0000-000000000000/export", 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 Evals endpoints