AskARC API Reference

Build Your Own Model Stack

Use our curated models, your own custom models, or build a fully custom stack. Deploy on your infrastructure, route with our intelligence.

Keep Your Infrastructure

Deploy on your terms, route with intelligence

Point to your self-hosted models, fine-tuned instances, or specialized LLMs. Any OpenAI-compatible API works: vLLM, Ollama, custom deployments.

Technical Details

OpenAI-compatible endpoints supported
Custom fine-tuned model integration
Self-hosted LLM compatibility
VPC and on-premise deployment options

Example Configuration

{
  "custom_models": [{
    "name": "legal-gpt-4",
    "endpoint": "https://your-domain.com/v1",
    "api_key": "your_key"
  }]
}

Universal Compatibility

Works with OpenAI-compatible endpoints

Integrate seamlessly with any service using the OpenAI API standard. No custom adapters needed. If it speaks OpenAI, AskARC routes it.

Works With

vLLM - Self-hosted inference
Ollama - Local models
Together AI - Cloud inference
Replicate - Model hosting
Hugging Face - Inference endpoints
Your custom server - Any OpenAI-compatible API

Technical Note

Standard chat completions endpoint (/v1/chat/completions) with OpenAI-format requests and responses. Streaming supported.

Test Before You Commit

Evaluate new models in production context

A/B test custom models against established options. Compare fine-tuned variants. Run new releases in real workloads before they hit our stack.

Use Cases

Model performance benchmarking
Fine-tune comparison (GPT-4 vs your legal-GPT-4)
New release evaluation (test GPT-5 on day 1)
Cost optimization experiments

Technical Details

Traffic splitting by percentage
Unified logging across all models
Performance metrics dashboard
Automatic fallback on failure

Example Workflow

{
  "routing_strategy": "ab_test",
  "traffic_split": {
    "custom-legal-model": 20,
    "claude-sonnet-4.5": 80
  },
  "metrics": ["latency", "cost", "quality"]
}

Use Your Compliant Infrastructure

Bring your certified models, we handle routing

Already managing HIPAA, SOC2, or GDPR-compliant infrastructure? Integrate those models with AskARC. Your sensitive data stays in your environment. We only handle routing intelligence.

How It Works

Your Infrastructure: HIPAA/SOC2-certified models you control
AskARC Router: Handles routing metadata only (no PHI/PII)
Your Data: Never leaves your network or VPC
Your Certifications: You maintain compliance

Example Use Cases

Healthcare: Your HIPAA-compliant models in your VPC
Finance: Your SOC2-certified infrastructure
Government: Air-gapped deployments you control
EU: Your GDPR-compliant models in EU regions

What AskARC Provides

Intelligent routing (metadata only)
No access to your sensitive data
No storage of PHI/PII
Pass-through architecture

Need help getting started? Join our Discord community to connect with the team and other developers, or reach out directly.

Quick Start

Base URL

https://api.askarc.app

1

Login to Portal

Access the developer portal at askarc.app to manage your API keys and credits

2

Create API Key

Generate your API key from the developer portal. Keep it secure and never share it publicly

3

Make Your First Request

Use your API key to send messages to the FenxChat API and get AI-powered responses

4

Build & Scale

Integrate AI capabilities into your application and scale as your needs grow

Ready to Start Building?

Check out our transparent pricing and get your API key

View API Pricing Get API Key

Authentication

API Key Authentication

For external applications making API calls

Header Format:

X-API-Key: fxk_your_api_key_here

Alternative Format:

Authorization: Bearer fxk_your_api_key_here

JWT Authentication

For portal management operations

Header Format:

Authorization: Bearer your_jwt_token

Usage:

Required for API key management, credit operations, and analytics

Portal Authentication

POST /api/v1/auth/login

Portal Login

Authenticate to access the portal and manage API keys

Request Body

email string Required

User email address

Example: "user@fenxlabs.ai"

password string Required

User password

Example: "SecurePassword123!"

Responses

200 Login successful

{
  "success": true,
  "data": {
    "token": "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9...",
    "user": {
      "email": "user@fenxlabs.ai",
      "credits": 1000
    }
  }
}

401 Invalid credentials

{
  "success": false,
  "error": "Invalid email or password"
}

Code Examples

curl -X POST https://api.askarc.app/api/v1/auth/login \
  -H "Content-Type: application/json" \
  -d '{
    "email": "user@fenxlabs.ai",
    "password": "SecurePassword123!"
  }'

const response = await fetch('https://api.askarc.app/api/v1/auth/login', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    email: 'user@fenxlabs.ai',
    password: 'SecurePassword123!'
  })
});

const data = await response.json();
console.log(data);

import requests

response = requests.post(
    'https://api.askarc.app/api/v1/auth/login',
    json={
        'email': 'user@fenxlabs.ai',
        'password': 'SecurePassword123!'
    }
)

data = response.json()
print(data)

Message API

POST /api/v1/messages

Send Message

Send a message and receive an AI-generated response

Request Body

message string Required

The message content to send to the AI

Example: "What is the capital of France?"

model string

Optional: Specify a model (auto-selects if not provided)

Options: "gpt-4", "claude-3", "gemini-pro", "mistral-large"

temperature number

Optional: Controls randomness (0.0 to 1.0)

Default: 0.7

Responses

200 Message sent successfully

{
  "success": true,
  "data": {
    "id": "msg_abc123",
    "response": "The capital of France is Paris.",
    "model": "gpt-4",
    "credits_used": 10,
    "timestamp": "2025-10-12T10:30:00Z"
  }
}

401 Unauthorized

{
  "success": false,
  "error": "Invalid or missing API key"
}

Code Examples

curl -X POST https://api.askarc.app/api/v1/messages \
  -H "Content-Type: application/json" \
  -H "X-API-Key: fxk_your_api_key_here" \
  -d '{
    "message": "What is the capital of France?",
    "temperature": 0.7
  }'

const response = await fetch('https://api.askarc.app/api/v1/messages', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'X-API-Key': 'fxk_your_api_key_here'
  },
  body: JSON.stringify({
    message: 'What is the capital of France?',
    temperature: 0.7
  })
});

const data = await response.json();
console.log(data.data.response);

import requests

response = requests.post(
    'https://api.askarc.app/api/v1/messages',
    headers={
        'Content-Type': 'application/json',
        'X-API-Key': 'fxk_your_api_key_here'
    },
    json={
        'message': 'What is the capital of France?',
        'temperature': 0.7
    }
)

data = response.json()
print(data['data']['response'])

Available Models

GET /api/v1/models

List Available Models

Retrieve a list of all available AI models and their capabilities

Responses

200 Models retrieved successfully

{
  "success": true,
  "data": {
    "models": [
      {
        "id": "gpt-4",
        "name": "GPT-4",
        "provider": "OpenAI",
        "description": "Most capable GPT-4 model"
      },
      {
        "id": "claude-3",
        "name": "Claude 3",
        "provider": "Anthropic",
        "description": "Advanced reasoning and analysis"
      },
      {
        "id": "gemini-pro",
        "name": "Gemini Pro",
        "provider": "Google",
        "description": "Multimodal understanding"
      },
      {
        "id": "mistral-large",
        "name": "Mistral Large",
        "provider": "Mistral AI",
        "description": "High performance language model"
      }
    ]
  }
}

Code Examples

curl -X GET https://api.askarc.app/api/v1/models \
  -H "X-API-Key: fxk_your_api_key_here"

const response = await fetch('https://api.askarc.app/api/v1/models', {
  headers: {
    'X-API-Key': 'fxk_your_api_key_here'
  }
});

const data = await response.json();
console.log(data.data.models);

import requests

response = requests.get(
    'https://api.askarc.app/api/v1/models',
    headers={
        'X-API-Key': 'fxk_your_api_key_here'
    }
)

data = response.json()
print(data['data']['models'])

Ready to Transform Your Application?

Start building with AskARC's multi-model AI routing today. Check out our transparent pricing or try the user-friendly chat interface.

View Pricing Plans Try AskARC App Learn More

AskARC API

Build Your Own Model Stack

Keep Your Infrastructure

Technical Details

Universal Compatibility

Works With

Technical Note

Test Before You Commit

Use Cases

Technical Details

Use Your Compliant Infrastructure

How It Works

Example Use Cases

What AskARC Provides

Quick Start

Base URL

Login to Portal

Create API Key

Make Your First Request

Build & Scale

Ready to Start Building?

Authentication

API Key Authentication

Header Format:

Alternative Format:

JWT Authentication

Header Format:

Usage:

Portal Authentication

Portal Login

Request Body

Responses

Code Examples

Message API

Send Message

Request Body

Responses

Code Examples

Available Models

List Available Models

Responses

Code Examples

Questions About Our API?

Ready to Transform Your Application?