Manual setup (advanced)

The Nexus CLI writes your harness settings for you and can undo them with one command. Most people should use it. Manual setup is for when you can’t or won’t install a CLI, or when you need settings the Nexus CLI doesn’t write.

​

When to use manual setup

• You can’t install the Nexus CLI. It needs Node.js 18 or later, git, and bash, and runs an install script.
• You manage harness configs yourself, through dotfiles or a team rollout.
• You want Nexus Auto to use Anthropic or OpenAI models without Provider Keys. The Nexus CLI doesn’t send x-anthropic-api-key or x-openai-api-key headers for any harness, so you add them yourself.
• You want to review every setting that changes.

​

What changes without the Nexus CLI

You point the harness at the same Fireworks endpoints, using your own API key. Some things the Nexus CLI normally handles become your job.

​

Before you start

1. Create an API key in Fireworks settings and export it:
   export FIREWORKS_API_KEY="fw_..."
   
2. Back up the config file you’re about to edit.
3. Use these endpoints:

   API	Base URL to configure	Full endpoint	Typical clients
   Anthropic Messages	https://api.fireworks.ai/inference	https://api.fireworks.ai/inference/v1/messages	Anthropic SDK, Claude Code
   OpenAI Chat Completions	https://api.fireworks.ai/inference/v1	https://api.fireworks.ai/inference/v1/chat/completions	OpenAI SDK, Fireworks SDK, most gateways and harnesses
   OpenAI Responses	https://api.fireworks.ai/inference/v1	https://api.fireworks.ai/inference/v1/responses	OpenAI SDK, Codex

   Anthropic-style clients add /v1/messages to the base URL themselves, so their base URL stops at /inference.

Use any model ID from Open Models, such as glm-latest, or auto for Nexus Auto.

​

Set up your harness

​

Use Nexus Auto with manual setup

For Nexus Auto to use an Anthropic or OpenAI model, the harness has to send an x-anthropic-api-key or x-openai-api-key header, or your account needs Provider Keys. The harness setup builder generates the config with the headers included. Cursor IDE and the Copilot App can’t send extra headers, so they need Provider Keys.

​

Microsoft Foundry

To configure a harness manually against Fireworks on Microsoft Foundry, see Configure a harness manually.