AITextGen API Documentation
Introduction
The AITextGen API provides advanced AI-powered text generation capabilities. This documentation covers all aspects of integrating and using the API in your applications.
Authentication
To use the AITextGen API, you need to include your API key in the Authorization header of your requests:
Authorization: Bearer YOUR_API_KEY
Base URL
All API requests should be made to:
https://api.cryptid.finance/v1/aitextgen
Endpoints
1. Generate Text
POST /generate
Generate text based on a given prompt.
Request Body
Parameter | Type | Description |
---|---|---|
prompt | string | The input text to start the generation from (required) |
max_length | integer | The maximum length of the generated text (optional, default: 50) |
temperature | float | Controls randomness in generation (optional, 0.0 to 1.0, default: 0.7) |
top_p | float | Nucleus sampling parameter (optional, 0.0 to 1.0, default: 0.9) |
Response
{
"generated_text": "The generated text based on the prompt",
"tokens_generated": 42,
"generation_time": 0.8765
}
Example Request
curl -X POST https://api.cryptid.finance/v1/aitextgen/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"prompt": "Once upon a time",
"max_length": 100,
"temperature": 0.8
}'
2. Fine-tune Model
POST /finetune
Fine-tune the text generation model on custom data.
Request Body
Parameter | Type | Description |
---|---|---|
training_data | array of strings | Array of text samples to fine-tune the model on (required) |
epochs | integer | Number of training epochs (optional, default: 3) |
learning_rate | float | Learning rate for fine-tuning (optional, default: 5e-5) |
Response
{
"status": "success",
"model_id": "ft_model_12345",
"training_time": 180.5
}
Rate Limits
The AITextGen API has the following rate limits:
- 100 requests per minute
- 5000 requests per day
If you exceed these limits, you'll receive a 429 Too Many Requests response.
Error Handling
The API uses standard HTTP response codes to indicate the success or failure of requests.
Code | Description |
---|---|
200 | OK - Request successful |
400 | Bad Request - Invalid parameters |
401 | Unauthorized - Invalid API key |
429 | Too Many Requests - Rate limit exceeded |
500 | Internal Server Error - Something went wrong on our end |
Webhooks
For long-running operations like fine-tuning, you can set up webhooks to receive notifications when the process is complete.
To set up a webhook, use the following endpoint:
POST /webhooks/create
{
"url": "https://your-app.com/webhook",
"events": ["finetune.completed", "finetune.failed"]
}
SDKs and Libraries
We provide official SDKs for popular programming languages to make integration easier:
Support
If you need any assistance or have questions, please don't hesitate to contact our support team:
- Email: [email protected]
- Discord: Join our community