Skip to main content

​
Overview

The Unbound Security AI Gateway provides a RESTful API that allows you to integrate AI capabilities into your applications while maintaining enterprise-grade security, cost control, and compliance. The API is compatible with OpenAI’s Chat Completions API format, making it easy to migrate existing integrations.

​
Base URL

All API requests should be made to: 
https://api.getunbound.ai/v1

​
Authentication

The Unbound API uses Bearer token authentication. Include your API key in the Authorization header: 
Authorization: Bearer YOUR_API_KEY
Your API key can be found in your Unbound application dashboard under the Overview tab.

​
Chat Completions

Create a completion for the provided chat messages.

​
Endpoint

POST /v1/chat/completions

​
Request Headers

HeaderTypeRequiredDescription
AuthorizationstringYesBearer token with your API key
Content-TypestringYesMust be application/json

​
Request Body

ParameterTypeRequiredDescription
modelstringYesThe model to use for completion
messagesarrayYesArray of message objects
max_tokensintegerNoMaximum tokens to generate (default: 1000)
temperaturenumberNoSampling temperature (0.0 to 2.0, default: 1.0)
streambooleanNoWhether to stream the response (default: false)

​
Message Object

ParameterTypeRequiredDescription
rolestringYesRole of the message sender (user, assistant, system)
contentstringYesContent of the message

​
Example Request

curl -X POST 'https://api.getunbound.ai/v1/chat/completions' \
  -H "Authorization: Bearer 4922c*****cd9b9" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": "Help me plan meals for the week."
      }
    ]
  }'

​
Example Response

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Here's a balanced meal plan for the week:\n\n**Monday:**\n- Breakfast: Oatmeal with berries and nuts\n- Lunch: Grilled chicken salad\n- Dinner: Salmon with quinoa and vegetables\n\n**Tuesday:**\n- Breakfast: Greek yogurt with granola\n- Lunch: Turkey and avocado wrap\n- Dinner: Pasta with marinara sauce and side salad\n\n**Wednesday:**\n- Breakfast: Scrambled eggs with toast\n- Lunch: Quinoa bowl with chickpeas and vegetables\n- Dinner: Grilled chicken with sweet potato and broccoli\n\n**Thursday:**\n- Breakfast: Smoothie bowl with fruits\n- Lunch: Lentil soup with whole grain bread\n- Dinner: Baked cod with rice and green beans\n\n**Friday:**\n- Breakfast: Pancakes with maple syrup\n- Lunch: Chicken Caesar salad\n- Dinner: Pizza night with vegetable toppings\n\n**Saturday:**\n- Breakfast: French toast with berries\n- Lunch: Grilled cheese and tomato soup\n- Dinner: Steak with roasted vegetables\n\n**Sunday:**\n- Breakfast: Waffles with fruit\n- Lunch: Leftovers or simple sandwich\n- Dinner: Roast chicken with mashed potatoes and gravy\n\nThis plan provides variety, balanced nutrition, and includes both healthy options and some comfort foods for the weekend."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 245,
    "total_tokens": 260
  }
}

​
List Models

Retrieve a list of available models for your application.

​
Endpoint

GET /models

​
Request Headers

HeaderTypeRequiredDescription
AuthorizationstringYesBearer token with your API key

​
Example Request

curl -X GET 'https://api.getunbound.ai/models' \
  -H "Authorization: Bearer 4922c*****cd9b9"

​
Example Response

{
    "anthropic/claude-opus": {
        "maxTokens": "32000",
        "contextWindow": "200000",
        "cacheReadPrice": "1.500000",
        "supportsImages": true,
        "cacheWritePrice": "18.750000",
        "inputTokenPrice": "15.000000",
        "outputTokenPrice": "75.000000",
        "supportsWebSearch": true,
        "supportsComputerUse": true,
        "supportsPromptCaching": true,
        "supportsExtendedThinking": true
    },
}
Model availability depends on your Unbound application configuration and routing rules. Use the /models endpoint to get the current list of available models for your application.

​
Advanced Examples

​
Multi-turn Conversation

curl -X POST 'https://api.getunbound.ai/v1/chat/completions' \
  -H "Authorization: Bearer 4922c*****cd9b9" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful coding assistant."
      },
      {
        "role": "user",
        "content": "How do I create a REST API in Python?"
      },
      {
        "role": "assistant",
        "content": "I can help you create a REST API in Python using Flask or FastAPI. Which framework would you prefer?"
      },
      {
        "role": "user",
        "content": "Let's use FastAPI"
      }
    ],
    "max_tokens": 1000,
    "temperature": 0.7
  }'

​
Streaming Response

curl -X POST 'https://api.getunbound.ai/v1/chat/completions' \
  -H "Authorization: Bearer 4922c*****cd9b9" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": "Write a Python function to calculate fibonacci numbers"
      }
    ],
    "stream": true
  }'

Create Application

Set up your Unbound application to get API access

Set Up Guardrails

Configure security guardrails for your API requests