# Quick Start — Access 100+ LLMs in 3 Minutes

Source: https://ofox.io/docs/develop

One API key gives you access to 100+ LLMs, including GPT, Claude, Gemini, and DeepSeek. First, choose how you want to use OfoxAI.

## Choose How to Use OfoxAI

- [Use in tools (no code)](https://ofox.io/docs/integrations) — Enter the API address and key in tools such as Cherry Studio, Claude Code, Codex, or Chatbox.
- [Integrate via API (code)](https://ofox.io/docs/develop#steps) — Compatible with the official OpenAI, Anthropic, and Gemini SDKs. Only the API address and key need to change.

## Integrate the API in Three Steps

### Get an API Key

Sign in to the [OfoxAI Console](https://app.ofox.ai), go to **Settings** → **API Keys**, and create a new key. The key is shown only once when it is created, so store it securely. See [API Key Setup & Usage](https://ofox.io/docs/develop/authentication) for details.

### Set the API Address

Choose the address that matches the SDK you use:

- OpenAI compatible: `https://api.ofox.io/v1` — General purpose, recommended
- Anthropic native: `https://api.ofox.io/anthropic`
- Gemini native: `https://api.ofox.io/gemini`

### Send Your First Request

Replace `<your OFOXAI_API_KEY>` with the key from step 1 and run the code. If you receive a reply from the model, the integration is working.

**cURL**

```bash filename="Terminal"
curl https://api.ofox.io/v1/chat/completions \
  -H "Authorization: Bearer <your OFOXAI_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-6.1-sol",
    "messages": [
      {"role": "user", "content": "What is the meaning of life?"}
    ]
  }'
```

**Python**

```python filename="quickstart.py"
from openai import OpenAI

client = OpenAI(
    base_url="https://api.ofox.io/v1",
    api_key="<your OFOXAI_API_KEY>"
)

response = client.chat.completions.create(
    model="openai/gpt-6.1-sol",
    messages=[{"role": "user", "content": "What is the meaning of life?"}]
)

print(response.choices[0].message.content)
```

**TypeScript**

```typescript filename="quickstart.ts"
import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.ofox.io/v1',
  apiKey: '<your OFOXAI_API_KEY>'
})

const response = await client.chat.completions.create({
  model: 'openai/gpt-6.1-sol',
  messages: [{ role: 'user', content: 'What is the meaning of life?' }]
})

console.log(response.choices[0].message.content)
```

To use the official Anthropic or Gemini SDK, see [Anthropic Messages](https://ofox.io/docs/api/anthropic/messages) and [Gemini Generate Content](https://ofox.io/docs/api/gemini/generate-content).

## Find by Task

- [Use with Claude Code](https://ofox.io/docs/integrations/claude-code) — Connect the coding assistant to OfoxAI, including environment variable setup.
- [Chat in Cherry Studio](https://ofox.io/docs/integrations/cherry-studio) — Add OfoxAI as a provider in the chat client.
- [Generate and edit images](https://ofox.io/docs/develop/models/gpt-image) — GPT Image text to image, image editing, and inpainting.
- [Generate video](https://ofox.io/docs/api/videos) — Asynchronous tasks: create, retrieve, and callbacks.
- [Migrate an existing OpenAI project](https://ofox.io/docs/integrations/openai-sdk) — Only base_url and the API key need to change.
- [Reduce costs](https://ofox.io/docs/develop/advanced/prompt-caching) — Prompt caching and provider routing.
- [Handle errors](https://ofox.io/docs/develop/guides/error-handling) — Common error codes, retries, and troubleshooting.
- [Browse all models](https://ofox.io/docs/develop/models) — Model IDs, pricing, and context length.

## More Resources
- [API Key Setup & Usage](https://ofox.io/docs/develop/authentication): how to include the key in requests for each of the three protocols
- [Pricing](https://ofox.io/docs/develop/observability/pricing) and [Usage Tracking](https://ofox.io/docs/develop/observability/usage-tracking)
- [Security & Data](https://ofox.io/docs/develop/security)
- [API Reference](https://ofox.io/docs/api): parameters and responses for every endpoint