AI-powered text tools: summarization, translation, rewriting, sentiment analysis, keyword extraction. Local AI, no data sharing. Free tier.
Welcome to the DevProToolkit API platform, where you can unlock the power of AI text generation with our GPT-powered content and completions API. In this article, we'll explore the features and benefits of our API, as well as provide a step-by-step guide on how to get started.
Our API is designed to help developers and businesses automate text generation tasks, such as content creation, chatbot development, and data extraction. With our API, you can generate high-quality text based on a given prompt, and even fine-tune the output to fit your specific needs.
An AI text generation API is a tool that uses artificial intelligence to generate human-like text based on a given prompt or input. Our API uses a GPT-powered model to generate text, which can be fine-tuned to fit specific use cases and applications.
There are many benefits to using a text generation API, including increased efficiency, improved accuracy, and enhanced creativity. With our API, you can automate text generation tasks, freeing up time and resources to focus on other areas of your business.
To get started with our API, simply sign up at api.commandsector.in/signup and obtain an API key. You can then use this key to authenticate your API requests and start generating text.
The following table outlines the parameters and options available for our API:
| Parameter | Description |
|---|---|
| prompt | The input text or prompt to generate text from |
| max_tokens | The maximum number of tokens to generate (1-4096) |
| temperature | The temperature or randomness of the generated text (0.0-2.0) |
| system_message | An optional system message to include in the generated text |
| model | The AI model to use for generation (default: gpt-4o-mini) |
Temperature and tokens are two important concepts to understand when using our API. Temperature refers to the randomness or creativity of the generated text, while tokens refer to the individual units of text that make up the output.
curl -X POST \
https://api.commandsector.in/api/ai/text/generate \
-H 'Content-Type: application/json' \
-H 'X-API-Key: YOUR_API_KEY' \
-d '{"prompt": "Hello, world!", "max_tokens": 100, "temperature": 0.5}'
import requests
api_key = "YOUR_API_KEY"
prompt = "Hello, world!"
max_tokens = 100
temperature = 0.5
response = requests.post(
"https://api.commandsector.in/api/ai/text/generate",
headers={"X-API-Key": api_key},
json={"prompt": prompt, "max_tokens": max_tokens, "temperature": temperature}
)
print(response.json())
const axios = require("axios");
const apiKey = "YOUR_API_KEY";
const prompt = "Hello, world!";
const maxTokens = 100;
const temperature = 0.5;
axios.post("https://api.commandsector.in/api/ai/text/generate", {
prompt,
maxTokens,
temperature
}, {
headers: {
"X-API-Key": apiKey
}
})
.then(response => {
console.log(response.data);
})
.catch(error => {
console.error(error);
});
Our API also supports advanced features such as system messages and chat context, which can be used to fine-tune the generated text and create more realistic conversations.
Our API can be used for a wide range of applications, including:
Temperature is a crucial parameter in the aitext-api that controls the level of randomness and creativity in the generated text. The temperature value ranges from 0.0 to 2.0, where 0.0 is deterministic, 0.7 is balanced, and 2.0 is highly creative.
A temperature of 0.0 means that the AI will always generate the same output given the same prompt, whereas a temperature of 2.0 will result in highly varied and sometimes unpredictable output.
| Temperature | Prompt | Output |
|---|---|---|
| 0.0 | Write a story about a character who learns a new skill. | Deterministic story about a character who learns a new skill. |
| 0.7 | Write a story about a character who learns a new skill. | Varied story about a character who learns a new skill, with some creative elements. |
| 2.0 | Write a story about a character who learns a new skill. | Highly creative and unpredictable story about a character who learns a new skill. |
Tokens are the basic units of text that the AI uses to generate output. The max_tokens parameter controls the maximum number of tokens that the AI can generate in a single response.
Token counting is important because it affects the length and coherence of the generated text. A higher max_tokens value allows for longer and more detailed responses, but may also increase the risk of repetitive or irrelevant content.
System messages are a powerful way to control the behavior of the AI and customize its responses to specific use cases.
Here are four examples of system messages, each with a full JSON request body:
// Customer support bot
{
"prompt": "I have a question about my order.",
"system_message": "You are a customer support agent. Respond with a helpful and friendly tone."
}
// Code reviewer
{
"prompt": "Review this code snippet.",
"system_message": "You are a code reviewer. Provide constructive feedback and suggestions for improvement."
}
// Translator
{
"prompt": "Translate this text from English to Spanish.",
"system_message": "You are a translator. Provide an accurate and fluent translation."
}
// Creative writer
{
"prompt": "Write a short story about a character who discovers a hidden world.",
"system_message": "You are a creative writer. Use your imagination to craft a compelling and engaging story."
}
Here is a complete Python example that demonstrates how to build a chatbot with conversation history using the aitext-api:
import requests
# Initialize conversation history
conversation_history = []
# Define a function to send a message to the AI
def send_message(prompt):
response = requests.post("https://api.commandsector.in/api/v1/aitext", json={"prompt": prompt, "conversation_history": conversation_history})
conversation_history.append(prompt)
conversation_history.append(response.json()["output"])
return response.json()["output"]
# Send a message to the AI
print(send_message("Hello, how are you?"))
# Send another message to the AI
print(send_message("I'm doing well, thanks. How about you?"))
# Print the conversation history
print(conversation_history)
This example shows how the messages array grows with each exchange, allowing the AI to maintain context and respond accordingly.
The aitext-api can return structured JSON output, which can be useful for extracting specific information from the generated text.
Here are a few examples of how to use the JSON mode:
// Extracting entities from text
{
"prompt": "Extract entities from this text.",
"json_mode": true,
"output_format": "entities"
}
// Generating product descriptions as JSON
{
"prompt": "Generate a product description.",
"json_mode": true,
"output_format": "product_description"
}
// Parsing unstructured data
{
"prompt": "Parse this unstructured data.",
"json_mode": true,
"output_format": "parsed_data"
}
| API | Free Tier | Models | Max Tokens | Streaming | Function Calling |
|---|---|---|---|---|---|
| DevProToolkit | Yes | Multiple models available | 2048 | Yes | Yes |
| OpenAI | No | Limited models available | 1024 | No | No |
| Anthropic | No | Limited models available | 512 | No | No |
| Google Gemini | No | Limited models available | 256 | No | No |
| Mistral | No | Limited models available | 128 | No | No |
We offer three pricing plans to fit your needs:
| Plan | Rate Limit | Price |
|---|---|---|
| Free | 100 requests/day | $0 |
| Pro | 10,000 requests/day | $9.99/mo |
| Enterprise | Unlimited requests | Contact us for custom pricing |
We currently support the gpt-4o-mini model, with additional models available in the future.
The token limits for each plan are as follows: Free (100 tokens), Pro (10,000 tokens), Enterprise (unlimited tokens).
Yes, we support streaming and real-time text generation for certain use cases. Please contact us for more information.
We take data privacy and security very seriously, and all data is encrypted and stored securely. Please see our terms of service for more information.
Yes, we offer fine-tuning options for certain use cases. Please contact us for more information.
Get your free API key and start making requests in minutes.
curl "http://147.224.212.116/api/..." \
-H "X-API-Key: YOUR_API_KEY"Get a free API key with 100 requests/day. No credit card required.
Get Free API Key