Skip to content
POST/api/v1/pipelines/run

Trigger a pipeline run

Starts a pipeline run from either a `templateId`, a full `config`, or a `steps[]` array (one is required); `projectId` is required. Validates the pipeline, resolves the provider from `model` (default `openai:gpt-4o-mini`), reserves one `evals` usage unit (429 `USAGE_LIMIT_EXCEEDED` when the plan cap is hit), and persists the run to `eval_runs` with `status:"running"`. Returns 201 immediately with `{runId, pipeline, status, message, steps}` — note the field is `runId`. Steps (dataset / eval / security-scan / compliance / gate / report / compare / notify) then execute in the background in-process and write progress back onto the same `eval_runs` row; poll that run to observe completion. Editor role, rate-limited 5/min.

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

201Created.
202Pipeline 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.
404Not Found — NOT_FOUND.
409Conflict — CONFLICT.
429(no description)
500Internal Server Error — DB_ERROR.

Code samples

cURL

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

400401403404409429500

Other Evals endpoints