API Documentation

Complete reference for the OMA-AI API. OpenAI-compatible, privacy-first, powered by Venice.

Overview

OMA-AI provides access to 38 AI models through a simple REST API. The API is OpenAI-compatible, making it easy to switch from other providers.

Key Features

• OpenAI-compatible endpoints
• Zero data retention on private models
• Built-in web search with citations
• Uncensored mode available
• Cost tracking in every response

Authentication

All API requests require an API key in the Authorization header:

Authorization: Bearer oma_your_api_key

Get your API key from the dashboard.

Quick Start

# Simple chat completion
curl https://oma-ai.com/api/llm \
  -H "Authorization: Bearer oma_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3.2",
    "prompt": "Hello, world!"
  }'

Chat Completions

Create a chat completion with any of our 38 models.

Request Body

Model Aliases

Use these shortcuts instead of full model IDs:

Response

{
  "success": true,
  "response": "The AI response text...",
  "model": "deepseek-v3.2",
  "model_id": "deepseek-v3.2",
  "privacy": "private",
  "tier": "standard",
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 156,
    "total_tokens": 168
  },
  "cost": {
    "input_usd": "0.000005",
    "output_usd": "0.000156",
    "total_usd": "0.000161"
  },
  "timestamp": 1709123456789
}

List Models

Get a list of all available models with pricing and capabilities.

Response

{
  "success": true,
  "total": 38,
  "models": [
    {
      "id": "deepseek-v3.2",
      "model_id": "deepseek-v3.2",
      "privacy": "private",
      "tier": "standard",
      "pricing": {
        "input": 0.40,
        "output": 1.00,
        "unit": "per 1M tokens"
      },
      "context": 160000,
      "best_for": "Best value, excellent quality"
    }
  ],
  "aliases": { ... },
  "default_model": "deepseek-v3.2"
}

Web Search

Enable real-time web search with citations on any model:

curl https://oma-ai.com/api/llm \
  -H "Authorization: Bearer oma_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3.2",
    "prompt": "What are the latest developments in AI?",
    "web_search": true
  }'

Responses will include citations from web sources when relevant.

Uncensored Mode

Disable content filters for unrestricted generation:

curl https://oma-ai.com/api/llm \
  -H "Authorization: Bearer oma_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "venice-uncensored",
    "prompt": "Write an unfiltered analysis...",
    "uncensored": true
  }'

Pricing

Pricing is per 1 million tokens. Input and output tokens are priced separately.

Every API response includes exact cost calculation in the cost field.