Get Started in 2 Steps
Register, one command, start building.
Claude Code
Anthropic's agentic coding CLI. Edit files, run commands, manage git.
AnthropicCodex CLI
OpenAI's terminal coding agent. Sandboxed code execution.
OpenAIGemini CLI
Google's open-source AI agent. 1M token context window.
GoogleRegister + Buy Quota + Get Key
In your browser, takes about 2 minutes
1.1 Register an account
Go to api.orcai.cc/portal and register with your email. After registration you'll be automatically logged in.
1.2 Buy quota
Go to the top-up page and choose a package:
| Plan | Quota | Price (USDT) | Validity |
|---|---|---|---|
| Starter | $10 | $1.50 | No expiry |
| Most Popular | $100 | $14.30 | No expiry |
| Professional | $500 | $62.00 | No expiry |
1.3 Copy your API Key
A default API Key (starts with sk-) was automatically created when you registered. Go to the API Keys page and copy it.
One Command to Install + Configure
In your terminal, installs all 3 CLI tools and configures your API key
Run this single command (replace YOUR_API_KEY with the key you copied):
Install + Configure All CLI Tools
This command does everything:
- Installs Node.js (if not present)
- Installs Claude Code, Codex CLI, and Gemini CLI
- Configures environment variables (API key + OrcAI endpoint)
After running, open a new terminal and try:
# Anthropic Claude Code $ claude # OpenAI Codex CLI $ codex # Google Gemini CLI $ gemini
Claude Code
Anthropic's agentic coding tool that lives in your terminal.
Launch
$ 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 — Automatically finds relevant context
- MCP support — Connect external tools via Model Context Protocol
- Slash commands — Built-in /commit, /review, and custom plugins
Supported Models
| Model | ID | Best For |
|---|---|---|
| Claude Opus 4 | claude-opus-4-6 | Complex reasoning, large refactors |
| Claude Sonnet 4 | claude-sonnet-4-6 | Balanced speed and quality |
| Claude Haiku 3.5 | claude-haiku-4-5-20251001 | Fast tasks, simple edits |
Manual Configuration
If you didn't use the install script, configure manually:
export ANTHROPIC_BASE_URL=https://api.orcai.cc/v1 export ANTHROPIC_API_KEY=sk-your-key claude
Codex CLI
OpenAI's terminal-based coding agent built in Rust.
Launch
$ codex
Key Features
- Built in Rust — 96% Rust codebase for maximum performance
- Sandboxed execution — Secure code execution environment
- Editor integration — Works with VS Code, Cursor, and Windsurf
- Desktop app — Launch with codex app for a GUI
- Web search — Built-in web search for context
Manual Configuration
export OPENAI_BASE_URL=https://api.orcai.cc/v1 export OPENAI_API_KEY=sk-your-key codex
Gemini CLI
Google's open-source AI agent with 1M token context window.
Launch
$ gemini
Key Features
- 1M token context — Largest context window of any CLI tool
- Open source — Apache 2.0 license, fully transparent
- Google Search — Real-time web search grounding
- Checkpointing — Save and resume sessions
- Non-interactive mode — Scriptable for automation
Manual Configuration
export GEMINI_API_KEY=sk-your-key gemini
CC-Switch
Desktop GUI app for managing AI CLI tools visually.
CC-Switch is a cross-platform desktop application that provides a visual interface for configuring Claude Code, Codex CLI, and Gemini CLI. If you prefer a GUI over command-line configuration, this is for you.
--key, everything is configured. CC-Switch is an alternative for users who prefer visual management.
Download
Get the latest release for your platform: github.com/farion1231/cc-switch/releases
Add OrcAI as a Provider
| Field | Value |
|---|---|
| Provider Name | OrcAI |
| API Key | sk-your-key |
| API Endpoint | https://api.orcai.cc/v1 |
| API Format | Anthropic Messages API |
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="sk-your-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: 'sk-your-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
| Method | Endpoint | Description |
|---|---|---|
POST | /v1/chat/completions | Chat completion (streaming supported) |
GET | /v1/models | List available models |
POST | /v1/embeddings | Generate text embeddings |
POST | /v1/images/generations | Generate images |
Authentication
Secure your API requests with bearer token authentication.
API Key
Authorization: Bearer sk-your-api-key
Pricing
| Plan | Quota | Price (USDT) | Validity | Models |
|---|---|---|---|---|
| Starter | $10 | $1.50 | No expiry | All models |
| Most Popular | $100 | $14.30 | No expiry | All models |
| Professional | $500 | $62.00 | No expiry | All models |
- Don't expose API keys in client-side code
- Use environment variables or .env files
- Rotate keys regularly
Models
50+ AI models from leading providers, one API.
Anthropic
| Model | ID | Context | Best For |
|---|---|---|---|
| Claude Opus 4 | claude-opus-4-6 | 200K | Complex reasoning, coding |
| Claude Sonnet 4 | claude-sonnet-4-6 | 200K | Balanced performance |
| Claude Haiku 3.5 | claude-haiku-4-5-20251001 | 200K | Fast, lightweight |
OpenAI
| Model | ID | Context | Best For |
|---|---|---|---|
| GPT-4o | gpt-4o | 128K | Multimodal, general purpose |
| GPT-4o Mini | gpt-4o-mini | 128K | Cost-effective |
| o1 | o1 | 200K | Advanced reasoning |
| o3 | o3 | 200K | Deep reasoning |
| Model | ID | Context | Best For |
|---|---|---|---|
| Gemini 2.5 Pro | gemini-2.5-pro | 1M | Large context tasks |
| Gemini 2.5 Flash | gemini-2.5-flash | 1M | Fast, cost-effective |