---
title: "Start Load Test"
method: POST
path: "/load_test/start"
---

# Start Load Test

`POST /load_test/start`

Start a load test. Returns immediately with a load_test_id for polling.

## Request body

- StartLoadTestRequestInput
  - `config_name` 'default' | 'aexp' | 'digital_ocean' | 'pepsi' | 'traversal' | 'kraken' | 'slack_demo' | 'baseten' | 'capital_one' | 'health_check' | 'nubank' | 'autodesk' | 'optum' | 'harvey' | 'hsbc' | 'blackstone' | 'metlife'
  - `incident_prompts` IncidentPrompt[], required
    - `description` string, required
    - `incident_time` string, required — ISO 8601 timestamp
    - `config_name` 'default' | 'aexp' | 'digital_ocean' | 'pepsi' | 'traversal' | 'kraken' | 'slack_demo' | 'baseten' | 'capital_one' | 'health_check' | 'nubank' | 'autodesk' | 'optum' | 'harvey' | 'hsbc' | 'blackstone' | 'metlife', required
  - `runs_per_incident` integer — Sessions per incident
  - `concurrency` integer, required — Maximum sessions to run concurrently. Lower values run sessions in waves.
  - `thinking_mode` 'auto' | 'deep' | 'fast' | 'lightning' — Determines the investigation depth and approach. - AUTO: Use message classifier to determine RCA vs CHAT - DEEP: Force RCA (root cause analysis) investigation - FAST: Force CHAT (exploratory) investigation - LIGHTNING: Fast, tool-rich investigation with tight iteration cap. Uses the union of all tools from fast + deep configs with a speed-focused prompt.
  - `mode` 'rca' | 'chat' | 'triage' | 'alert_story'

## Response `200`

Successful Response

- StartLoadTestResponse
  - `load_test_id` string, required
  - `message` string

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/traversal/apis/fastapi.md) · [All operations](https://skmtc.net/traversal/apis/fastapi/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/traversal/fastapi/revisions/2134ebffd1ef/schema)