Inception Platform

Welcome to Inception Platform

Inception Platform provides powerful AI capabilities through an OpenAI-compatible API interface. This means you can use existing OpenAI client libraries or direct REST calls to access our services.

Account Setup

Create an Inception Platform account or sign in directly if you already have one.

Navigate to Billing in your dashboard and add your payment information to activate your account.

Go to API Keys and create a new API key. Make sure to copy and securely store your API key - you won't be able to see it again.

Quick Start

import requests

response = requests.post(
    'https://api.inceptionlabs.ai/v1/chat/completions',
    headers={
        'Content-Type': 'application/json',
        'Authorization': 'Bearer INCEPTION_API_KEY'
    },
    json={
        'model': 'mercury',  
        'messages': [
            {'role': 'user', 'content': 'What is a diffusion model?'}
        ],
        'max_tokens': 1000
    }
)
data = response.json()

External Libraries Compatibility

Inception API is fully compatible with popular Python libraries:

from openai import OpenAI

client = OpenAI(
    api_key="INCEPTION_API_KEY",
    base_url="https://api.inceptionlabs.ai/v1"
)

response = client.chat.completions.create(
    model="mercury",
    messages=[{"role": "user", "content": "What is a diffusion model?"}],
    max_tokens=1000
)
print(response.choices[0].message.content)

Streaming and Diffusing

Inception API supports real-time output and diffusion effect modes:

Streaming: Get responses block-by-block for real-time feedback—ideal for chat and live applications.
Diffusing: Optionally visualize how noisy outputs are refined into final text, showcasing the model's iterative denoising process.

curl https://api.inceptionlabs.ai/v1/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer INCEPTION_API_KEY" \
    -d '{
      "model": "mercury",
      "messages": [
        {"role": "user", "content": "What is a diffusion model?"}
      ],
      "max_tokens": 1000,
      "stream": true
    }'

Tool Calling

Inception API supports tool calling for more complex responses on the chat completion endpoint.

from openai import OpenAI
import json

client = OpenAI(base_url="https://api.inceptionlabs.ai/v1", api_key="INCEPTION_API_KEY")

def get_weather(location: str, unit: str):
    return f"Getting the weather for {location} in {unit}..."
tool_functions = {"get_weather": get_weather}

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string", "description": "City and state, e.g., 'San Francisco, CA'"},
                "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
            },
            "required": ["location", "unit"]
        }
    }
}]

response = client.chat.completions.create(
    model="mercury",
    messages=[{"role": "user", "content": "What's the weather like in San Francisco?"}],
    tools=tools
)

tool_call = response.choices[0].message.tool_calls[0].function
print(f"Function called: {tool_call.name}")
print(f"Arguments: {tool_call.arguments}")
print(f"Result: {get_weather(**json.loads(tool_call.arguments))}")

Structured Outputs

Inception API supports structured outputs to ensure responses follow specific formats:

JSON: Use JSON schemas to enforce structured data output with specific properties, types, and constraints.
Choice: Present multiple options to choose from.
Regex: Constrain outputs to match specific regular expression patterns.

from openai import OpenAI
import json

client = OpenAI(base_url="https://api.inceptionlabs.ai/v1", api_key="INCEPTION_API_KEY")

response_schema = {
    "type": "object",
    "properties": {
        "sentiment": {
            "type": "string",
            "enum": ["positive", "negative", "neutral"]
        },
        "confidence": {
            "type": "number",
            "minimum": 0,
            "maximum": 1
        },
        "key_phrases": {
            "type": "array",
            "items": {"type": "string"}
        }
    },
    "required": ["sentiment", "confidence", "key_phrases"]
}

response = client.chat.completions.create(
    model="mercury-coder",
    messages=[
        {"role": "user", "content": "Analyze the sentiment of this text: 'I absolutely love this feature! It works perfectly and saves me so much time.'"}
    ],
    extra_body={"guided_json": response_schema},
    max_tokens=50,
)

result = json.loads(response.choices[0].message.content)
print(f"Sentiment: {result['sentiment']}")
print(f"Confidence: {result['confidence']}")
print(f"Key phrases: {result['key_phrases']}")

Documentation

Contents