API Documentation
Everything you need to integrate SparkAI Stream into your applications
Coming Soon
Our API is currently under development. The documentation below shows what will be available at launch.
Authentication
All API requests require authentication using an API key. Include your key in the request header:
Authorization: Bearer YOUR_API_KEY
Generate API keys from your dashboard once you create an account.
Chat API
Send messages to our AI and receive streaming or complete responses.
Endpoint
POST https://api.sparkaistream.com/v1/chat
Request Body
{
"model": "spark-1",
"messages": [
{
"role": "user",
"content": "Hello, how are you?"
}
],
"max_tokens": 1000,
"temperature": 0.7,
"stream": true
}
Response
{
"id": "chat-abc123",
"object": "chat.completion",
"created": 1234567890,
"model": "spark-1",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! I'm doing great. How can I help you today?"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 12,
"completion_tokens": 18,
"total_tokens": 30
}
}
Example (cURL)
curl https://api.sparkaistream.com/v1/chat \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "spark-1",
"messages": [{"role": "user", "content": "Hello!"}],
"stream": true
}'
Example (Python)
import requests
response = requests.post(
"https://api.sparkaistream.com/v1/chat",
headers={
"Authorization": "Bearer YOUR_API_KEY",
"Content-Type": "application/json"
},
json={
"model": "spark-1",
"messages": [{"role": "user", "content": "Hello!"}],
"stream": True
}
)
print(response.json())
Example (JavaScript)
const response = await fetch('https://api.sparkaistream.com/v1/chat', {
method: 'POST',
headers: {
'Authorization': 'Bearer YOUR_API_KEY',
'Content-Type': 'application/json'
},
body: JSON.stringify({
model: 'spark-1',
messages: [{ role: 'user', content: 'Hello!' }],
stream: true
})
});
const data = await response.json();
console.log(data);
Available Models
| Model | Description | Max Tokens | Price |
|---|---|---|---|
spark-1 |
Balanced model for most tasks | 4,096 | $0.0003/1K tokens |
spark-turbo |
Optimized for speed | 4,096 | $0.0006/1K tokens |
spark-pro |
Enhanced reasoning & analysis | 8,192 | $0.0012/1K tokens |
Rate Limits
| Plan | Requests/min | Tokens/min |
|---|---|---|
| Starter | 30 | 15,000 |
| Pro | 90 | 75,000 |
| Enterprise | Custom | Custom |
Error Handling
The API uses standard HTTP response codes:
| Code | Description |
|---|---|
200 | Success |
400 | Bad Request - Invalid parameters |
401 | Unauthorized - Invalid API key |
429 | Too Many Requests - Rate limit exceeded |
500 | Server Error |
Official SDKs
We'll provide official SDKs for popular languages:
Python
pip install sparkaistream
Coming Soon
JavaScript/Node.js
npm install sparkaistream
Coming Soon
PHP
composer require sparkaistream/sdk
Coming Soon