Quick Start

Get up and running with OrcAI in under 5 minutes.

Step 1: Create an Account

Sign up at api.orcai.cc/portal with your email. You'll receive a verification code to complete registration.

Step 2: Get Your API Key

Navigate to Dashboard → API Keys and create a new key. Copy it — you'll need it for all CLI tools.

Step 3: Configure Your Environment

# Set your OrcAI API key
export ORCAI_API_KEY="your-api-key-here"

# OrcAI gateway is compatible with OpenAI SDK
export OPENAI_API_KEY="$ORCAI_API_KEY"
export OPENAI_BASE_URL="https://api.orcai.cc/v1"

# For Anthropic SDK compatibility
export ANTHROPIC_API_KEY="$ORCAI_API_KEY"
export ANTHROPIC_BASE_URL="https://api.orcai.cc"

Step 4: Install a CLI Tool

Choose one or install all three:

Or install individually — see the One-Click Install page for details.

Step 5: Start Coding

# Use Claude Code
$ claude "Create a REST API with Express"

# Use Codex CLI
$ codex "Build a React dashboard component"

# Use Gemini CLI
$ gemini "Analyze this codebase and suggest improvements"

One-Click Install

Install Claude Code, Codex CLI, and Gemini CLI with a single command.

This script detects your OS and installs all three CLI tools with the correct configuration for OrcAI gateway.

Individual Installation

Claude Code (Anthropic)

# macOS / Linux / WSL
curl -fsSL https://claude.ai/install.sh | bash

# Verify installation
claude --version

# Windows PowerShell
irm https://claude.ai/install.ps1 | iex

# Or via WinGet
winget install Anthropic.ClaudeCode

npm install -g @anthropic-ai/claude-code

Codex CLI (OpenAI)

npm install -g @openai/codex

brew install --cask codex

# Download from GitHub Releases
# https://github.com/openai/codex/releases/latest

Gemini CLI (Google)

# Run without installing
npx @google/gemini-cli

npm install -g @google/gemini-cli

brew install gemini-cli

System Requirements

Claude Code

Anthropic's agentic coding tool that lives in your terminal.

Overview

Claude Code is an agentic coding tool by Anthropic that understands your entire codebase, executes routine tasks, explains complex code, and handles git workflows — all through natural language commands in your terminal.

Installation

Configuration with OrcAI

# Set OrcAI as your API provider
export ANTHROPIC_API_KEY="your-orcai-api-key"
export ANTHROPIC_BASE_URL="https://api.orcai.cc"

# Launch Claude Code
claude

Key Features

• Multi-file editing — Search and modify files across your entire codebase
• Git integration — Read issues, write code, run tests, submit PRs
• Agentic search — No manual context selection, Claude finds what it needs
• Plugin system — Custom commands and agents via slash commands
• Agent SDK — Build programmatic agents with @anthropic-ai/claude-agent-sdk
• MCP support — Connect to external tools via Model Context Protocol

Common Commands

# Start interactive session
$ claude

# Run a single command
$ claude "explain this function"

# Fix a specific issue
$ claude "fix the login bug in auth.js"

# Create a commit
$ claude "/commit"

# Run diagnostics
$ claude doctor

# Update to latest version
$ claude update

Supported Models via OrcAI

Codex CLI

OpenAI's terminal-based coding agent built in Rust.

Overview

Codex CLI is OpenAI's local terminal-based coding agent that can read, change, and run code on your machine. Built primarily in Rust for maximum speed, it features sandboxed execution for security and integrates with VS Code, Cursor, and Windsurf editors.

Installation

npm install -g @openai/codex

brew install --cask codex

Configuration with OrcAI

# Use OrcAI as the OpenAI-compatible backend
export OPENAI_API_KEY="your-orcai-api-key"
export OPENAI_BASE_URL="https://api.orcai.cc/v1"

# Launch Codex
codex

Key Features

• Built in Rust — 96% Rust codebase for maximum performance
• Sandboxed execution — Landlock/seccomp on Linux for secure code execution
• Editor integration — VS Code, Cursor, and Windsurf support
• GitHub Actions — CI/CD integration with openai/codex-action@v1
• Desktop app — Launch with codex app
• Web search — Built-in web search tool for context gathering
• Slash commands — /review, /fork, custom prompts

Usage Examples

# Interactive mode
$ codex

# Direct task
$ codex "Build a React dashboard component"

# Review code
$ codex "/review"

# Desktop app mode
$ codex app

Gemini CLI

Google's open-source AI agent with 1M token context window.

Overview

Gemini CLI is Google's open-source AI agent powered by Gemini models with a massive 1M token context window. It includes a free tier with generous limits (60 requests/min, 1,000 requests/day) and supports Google Search grounding, MCP servers, and conversation checkpointing.

Installation

# No install needed — runs via npx
npx @google/gemini-cli

npm install -g @google/gemini-cli

brew install gemini-cli

Configuration with OrcAI

# Use OrcAI gateway for Gemini API
export GEMINI_API_KEY="your-orcai-api-key"

# Launch Gemini CLI
gemini

Key Features

• 1M token context — Largest context window of any CLI tool
• Free tier — 60 requests/min, 1,000 requests/day at no cost
• Open source — Apache 2.0 license, fully transparent
• Google Search grounding — Real-time web search integration
• MCP support — Custom tool integrations via Model Context Protocol
• Conversation checkpointing — Save and resume sessions
• Custom context files — GEMINI.md for project-specific instructions
• Non-interactive mode — Scriptable for automation pipelines

Free Tier Limits

OpenClaw

Multi-channel AI bot framework for Telegram, Discord, Slack, and 10+ platforms.

Overview

OpenClaw is a personal AI assistant framework that runs on your own devices and connects to 13+ messaging platforms. It supports voice, browser control, device integration, and a powerful skill system for extending functionality.

Installation

# Install globally
npm install -g openclaw@latest

# Run onboarding
openclaw onboard --install-daemon

# Or install from source
git clone https://github.com/openclaw/openclaw.git
cd openclaw
pnpm install && pnpm ui:build && pnpm build
pnpm openclaw onboard --install-daemon

Telegram Bot Setup

1. Create a bot via @BotFather on Telegram (/newbot)
2. Configure the bot token in OpenClaw:

{
  channels: {
    telegram: {
      enabled: true,
      botToken: "YOUR_BOT_TOKEN",
      dmPolicy: "pairing",
      groups: { "*": { requireMention: true } }
    }
  }
}

# Start gateway and approve pairing
openclaw gateway
openclaw pairing list telegram
openclaw pairing approve telegram <CODE>

Supported Platforms

Key Features

• Multi-channel inbox — One AI, 13+ messaging platforms
• Voice Wake + Talk — ElevenLabs voice integration
• Browser control — Chrome/Chromium automation
• Skill system — Extensible via ClawHub skills
• Device nodes — Camera, screen recording, location (iOS/Android/macOS)
• Local-first — Runs on your own devices, no cloud dependency
• Pairing security — Secure authentication for DMs and groups

API Overview

OpenAI-compatible REST API for accessing 50+ AI models.

Base URL

https://api.orcai.cc/v1

Quick Example

curl https://api.orcai.cc/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [{"role": "user", "content": "Hello!"}],
    "max_tokens": 1024
  }'

from openai import OpenAI

client = OpenAI(
    api_key="your-orcai-api-key",
    base_url="https://api.orcai.cc/v1"
)

response = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=1024
)
print(response.choices[0].message.content)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'your-orcai-api-key',
  baseURL: 'https://api.orcai.cc/v1'
});

const response = await client.chat.completions.create({
  model: 'claude-sonnet-4-6',
  messages: [{ role: 'user', content: 'Hello!' }],
  max_tokens: 1024
});
console.log(response.choices[0].message.content);

Endpoints

Authentication

Secure your API requests with bearer token authentication.

API Key

All API requests require a valid API key passed in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Getting Your API Key

1. Log in to OrcAI Portal
2. Navigate to API Keys section
3. Click Create New Key
4. Copy the key — it won't be shown again

Rate Limits

Models

50+ AI models from leading providers, accessible through one API.

Anthropic Models

OpenAI Models

Google Models