Quick Start Guide

This guide is for API consumers — how to integrate OSP API into your application.

---

Step 1: Get Your API Key

1. Log in to your OSP API admin panel
2. Go to User → API Key
3. Click Generate New Key and copy it

⚠️ The key is shown only once — store it securely

---

Step 2: Send Your First Request

OSP API is OpenAI-compatible. Use /v1/chat/completions:

curl -X POST https://api.osp.io/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Response:

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "choices": [{
    "index": 0,
    "message": {"role": "assistant", "content": "Hello! How can I help you?"},
    "finish_reason": "stop"
  }],
  "usage": {"prompt_tokens": 9, "completion_tokens": 20, "total_tokens": 29}
}

---

Step 3: Switch Models

Change the model field in your request:

Model	Parameter	Provider
GPT-4	gpt-4	OpenAI
GPT-4o	gpt-4o	OpenAI
Claude 3.5 Sonnet	claude-3-5-sonnet	Anthropic
Gemini Pro	gemini-pro	Google
iFlytek Spark	spark-3.5	iFlytek

---

Common Models

Model	Use Case	Provider
gpt-4 / gpt-4o	Chat, code, writing	OpenAI
claude-3-5-sonnet	Analysis, long context	Anthropic
gemini-pro	Multimodal, reasoning	Google
midjourney	Image generation	Midjourney
suno-ai	Music generation	Suno
gpt-4o-mini	Fast chat	OpenAI
o1-mini	Fast reasoning	OpenAI

---

Billing

• Token billing: Input + output tokens combined
• Channel markup: Different providers have different base prices
• Usage dashboard: Check "Data Dashboard" in admin panel

---

Need Help?

• See API Docs
• Contact your OSP API administrator