> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fireworks.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Manual setup (advanced)

> Configure a coding harness for Fireworks by hand, without installing the Nexus CLI.

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](/nexus/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.

| | With the Nexus CLI | With manual setup |
| - | - | - |
| Fireworks models in the picker | Added for you | Set the model ID in your config |
| Anthropic model turns in Claude Code | Paid by your Claude login | Need an Anthropic [Provider Key](/nexus/provider-keys) or an `x-anthropic-api-key` header |
| MCP tool search | Turned on | Claude Code: add `ENABLE_TOOL_SEARCH`. Codex: needs the model catalog the Nexus CLI writes |
| Session cost status line (Claude Code) | Installed | Not available |
| Claude Code telemetry and nonessential traffic | Turned off | Left as you have it |
| Undo | `nexus <harness> off` | Restore your own backup |
| Upgrades | `nexus upgrade` refreshes connected harnesses | Update your configs yourself |

## Before you start

1. Create an API key in [Fireworks settings](https://app.fireworks.ai/settings/users/api-keys) and export it:

   ```bash wrap theme={null}
   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](/nexus/open-models), such as `glm-latest`, or `auto` for [Nexus Auto](/nexus/auto).

## Set up your harness

| Harness | Status | Manual setup |
| - | - | - |
| [Claude Code](/nexus/harnesses/claude-code) | Generally available | [Manual setup tab](/nexus/harnesses/claude-code#manual-setup-advanced) |
| [Claude Agent SDK](/nexus/harnesses/claude-code#claude-agent-sdk) | Preview | Reads your Claude Code settings. Set up Claude Code first. |
| [Claude Desktop](/nexus/harnesses/claude-desktop) | Preview | Not available. Use the Nexus CLI. |
| [Codex](/nexus/harnesses/codex) | Generally available | [Manual setup tab](/nexus/harnesses/codex#manual-setup-advanced) |
| [ChatGPT desktop app](/nexus/harnesses/chatgpt) | Generally available | [Manual setup tab](/nexus/harnesses/chatgpt#manual-setup-advanced) |
| [OpenCode](/nexus/harnesses/opencode) | Generally available | [Manual setup tab](/nexus/harnesses/opencode#manual-setup-advanced) |
| [Pi](/nexus/harnesses/pi) | Generally available | [Manual setup tab](/nexus/harnesses/pi#manual-setup-advanced) |
| [Cursor IDE](/nexus/harnesses/cursor) | Preview | [Manual setup tab](/nexus/harnesses/cursor#manual-setup-advanced) |
| [VS Code](/nexus/harnesses/vscode) | Preview | [Manual setup tab](/nexus/harnesses/vscode#manual-setup-advanced) |
| [Copilot App](/nexus/harnesses/copilot-app) | Preview | [Manual setup tab](/nexus/harnesses/copilot-app#manual-setup-advanced) |
| [Copilot CLI](/nexus/harnesses/copilot-cli) | Preview | [Manual setup tab](/nexus/harnesses/copilot-cli#manual-setup-advanced) |
| [DeepSeek Harness](/nexus/harnesses/deepseek) | Generally available | [Manual setup tab](/nexus/harnesses/deepseek#manual-setup-advanced) |

## 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](/nexus/provider-keys). The [harness setup builder](/nexus/auto#nexus-cli) 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](/nexus/microsoft-foundry#configure-a-harness-manually).