Kling 4.0 is LIVE — Unbelievably Real Video | Try Now →
Agent Setup

Connect Factory Droid to WaveSpeed LLM API

Copy the recommended ~/.factory/settings.json setup for Factory Droid, route requests to /v1/chat/completions, and verify local agent calls in WaveSpeed Logs.

Factory's coding agent; add WaveSpeed as a custom model.

Config file

~/.factory/settings.json

Protocol

OpenAI-compatible chat completions

Endpoint

/v1/chat/completions

Manual setup

1

Create a WaveSpeed access key

2

Export the required key locally

3

Paste config into~/.factory/settings.json

4

Run droid exec and check Logs

OpenAI-compatible chat completions

Usage appears in Dashboard and Logs

Switch models without rewriting agent code

One-command setup

Configures Factory Droid, checks that it works, and backs up your previous settings. Add --undo to restore them.

  1. 1

    Install the WaveSpeed CLI

    npm install -g @wavespeed/cli
  2. 2

    Sign in

    wavespeed login
  3. 3

    Configure Factory Droid

    wavespeed setup droid

No Node.js? See other install options

Manual setup

Edit ~/.factory/settings.json
// File: ~/.factory/settings.json  (add to the existing "customModels" array if you already have one)
{
  "customModels": [
    {
      "model": "deepseek/deepseek-v4.1-flash-1017",
      "displayName": "WaveSpeed deepseek/deepseek-v4.1-flash-1017",
      "baseUrl": "https://llm.wavespeed.ai/v1",
      "apiKey": "${WAVESPEED_API_KEY}",
      "provider": "generic-chat-completion-api",
      "maxOutputTokens": 16000
    }
  ],
  "sessionDefaultSettings": { "model": "custom:deepseek/deepseek-v4.1-flash-1017" }
}

Do not replace the variable name

WAVESPEED_API_KEY is the environment variable name that the agent reads. Keep this name in the config file, and put your real API key in your shell instead.

1

Temporary for this terminal

Works until you close this terminal window.

export WAVESPEED_API_KEY="wsk_live_..."
2

Keep it after restart

Writes the key into your shell profile so new terminals can read it.

echo 'export WAVESPEED_API_KEY="wsk_live_..."' >> ~/.zshrc
source ~/.zshrc

Agent integration guide

Use Factory Droid with WaveSpeed LLM API

This guide shows how to connect Factory Droid to WaveSpeed AI with ~/.factory/settings.json, OpenAI-compatible chat completions, /v1/chat/completions, base URL https://llm.wavespeed.ai/v1, and default model deepseek/deepseek-v4.1-flash-1017. Copy the configuration above, export your API key, run the agent, then verify requests in Logs.

1

Create a WaveSpeed access key

2

Export the required key locally

3

Paste config into

~/.factory/settings.json
4

Run droid exec and check Logs

What this Factory Droid setup configures

Protocol

OpenAI-compatible chat completions

Endpoint

/v1/chat/completions

Model

deepseek/deepseek-v4.1-flash-1017

The copy-ready configuration above is the only Factory Droid file you need to edit for the recommended setup: ~/.factory/settings.json. Keep the API key in your shell environment so it is not committed to a repository.

Troubleshooting

The API key is not being picked up

Export WAVESPEED_API_KEY in the same shell where you run Factory Droid. If you use a shell profile, reload the terminal before starting the agent.

Requests fail with a protocol or endpoint error

Check that Factory Droid is using OpenAI-compatible chat completions and endpoint /v1/chat/completions. Protocol mismatches are the most common cause of 404 or payload errors.

The selected model does not work

Confirm the model id exists in WaveSpeed Models, then paste the exact id into ~/.factory/settings.json. You can start with the default model shown on this page.

No requests appear in Logs

Make sure Factory Droid is using the WaveSpeed base URL and your current API key. Then send a new prompt from the local agent and refresh Logs.

Can this Factory Droid guide show up in search?

Yes. This page is built as an indexable setup guide for users searching for Factory Droid custom provider, OpenAI-compatible endpoint, base URL, and local agent configuration workflows.