API Gateway & Router Service

​

Overview

​

What is Alter Router?

• 10+ AI model providers (OpenAI, Gemini, Claude, Mistral, etc.)
• 92+ individual AI models
• Simplified authentication and billing
• Easy model switching without code changes

​

Key Features

• OpenAI-compliant endpoint supporting chat completions and model listing
• Centralized billing through your Alter account
• Access to all models from external applications or custom code
• Seamless integration with existing OpenAI-compatible tools and SDKs
• Flexible model selection across all providers

​

Getting Started

​

1. Generate API Key

1. Open Alter Settings (⌘ , or Settings menu)
2. Go to Router tab
3. Under “Alter API Keys” section, click “Add New Key” to generate a new API key
4. Copy your key (starts with sk-)

​

2. Get the Endpoint

https://alterhq.com/api

https://alterhq.com/api/v1

​

3. List Available Models

curl https://alterhq.com/api/models \
  -H "Authorization: Bearer YOUR_API_KEY"

​

Model Naming Convention

<Provider>#<Model-name>

​

Examples:

• OpenAI#gpt-5 - Latest GPT-5
• OpenAI#gpt-5-nano - Lightweight GPT
• Claude#claude-sonnet-4-6 - Latest Claude
• Gemini#gemini-2.5-pro - Latest Gemini
• Mistral#mistral-small-latest - Mistral model
• Alter#best - Alter’s best model

​

Usage Methods

​

For Third-Party Applications

1. Set base URL: https://alterhq.com/api (or /v1)
2. Enter your API key
3. Use Provider#Model-name format when selecting models

​

For Custom Development

​

Python (with OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://alterhq.com/api/v1"
)

response = client.chat.completions.create(
    model="OpenAI#gpt-5",
    messages=[
        {"role": "user", "content": "What is machine learning?"}
    ]
)

print(response.choices[0].message.content)

​

JavaScript (with OpenAI SDK)

import OpenAI from 'openai';

const openai = new OpenAI({
    apiKey: "YOUR_API_KEY",
    baseURL: "https://alterhq.com/api/v1",
    dangerouslyAllowBrowser: true
});

const completion = await openai.chat.completions.create({
    model: "OpenAI#gpt-5",
    messages: [
        {"role": "user", "content": "Hello!"}
    ]
});

console.log(completion.choices[0].message.content);

​

LangChain (Python)

from langchain_openai import ChatOpenAI

chat = ChatOpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://alterhq.com/api/v1",
    model="OpenAI#gpt-5"
)

response = chat.invoke("What is AI?")
print(response.content)

​

Direct cURL

curl https://alterhq.com/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "OpenAI#gpt-5",
    "messages": [
      {"role": "user", "content": "What is machine learning?"}
    ]
  }'

​

Model Selection Guide

​

For Speed

• Alter#light - Lightweight model
• OpenAI#gpt-5-nano - Lightweight GPT
• Gemini#gemini-2.5-flash-lite - Fast Gemini

​

For Quality

• Alter#best - Best available
• OpenAI#gpt-5 - Most capable GPT
• Gemini#gemini-2.5-pro - Powerful Gemini
• Claude#claude-sonnet-4-6 - Latest Claude

​

For Vision/Images

• OpenAI#gpt-5 - Advanced multimodal
• Gemini#gemini-2.5-pro - Strong vision
• Mistral#pixtral-large-latest - Vision capable

​

For Coding

• OpenAI#gpt-5 - Excellent code
• Mistral#codestral-2501 - Code specialist
• Claude#claude-sonnet-4-6 - Strong coding

​

For Cost

• Alter#fair - Cost-effective
• Alter#light - Cheapest
• OpenAI#gpt-5-nano - Budget GPT

​

For Web Search

• Perplexity#sonar - Web-aware
• Perplexity#sonar-pro - Advanced search

​

Supported Parameters

• model - Model ID (required)
• messages - Chat messages (required)
• temperature - 0.0-2.0 (default: 1.0)
• max_tokens - Maximum response length
• top_p - Nucleus sampling
• frequency_penalty - Penalize repetition
• presence_penalty - Encourage new topics

​

Popular Use Cases

​

Third-Party App Integration

• SillyTavern - Roleplaying chat
• NovelCrafter - Creative writing
• Other OpenAI-compatible tools

​

Custom Application Backend

• Internal tools needing AI
• Customer support automation
• Content generation systems
• Data analysis workflows

​

Model Comparison & A/B Testing

for model_id in ["OpenAI#gpt-5", "Claude#claude-sonnet-4-6", "Gemini#gemini-2.5-pro"]:
    # Run same prompt on different models
    # Compare outputs

​

Cost Optimization

​

Configuration

​

API Key Management

• Generate and manage API keys through Settings > Router
• Keep API keys secure—never share them publicly
• Rotate keys regularly for security
• Use different keys for different environments (dev/prod)

​

Usage Limits

• Daily Limit: 200 requests per day under fair use
• Throttling: After exceeding daily limit, requests throttle to 1 per 10 minutes
• Budget Top-up: “Top up” your budget for consistent access beyond fair use limits

​

Troubleshooting

​

Models Not Listed

• Manually specify the model using Provider#Model-name format
• Verify your API key is correct
• Check that the application supports model listing endpoint

​

Authentication Errors

• Verify your API key is correctly entered
• Ensure you’re using correct endpoint: https://alterhq.com/api or https://alterhq.com/api/v1
• Check that your Alter account is active and in good standing

​

Connection Issues

• Verify the application supports OpenAI-compatible endpoints
• Ensure you’re using the latest version of Alter
• Check network connectivity to alterhq.com

​

High Latency

• Try a faster model (e.g., OpenAI#gpt-5-nano)
• Check your network connection
• Use streaming for long responses

​

Best Practices

1. Secure your API key - Use environment variables, never hardcode
2. Monitor usage - Track API calls and set alerts
3. Choose appropriate models - Match model capability to task complexity
4. Handle errors gracefully - Implement retry logic with backoff
5. Optimize costs - Use faster/cheaper models for routine tasks

​

Related Docs

• Choosing Your Model
• Settings - Router Configuration
• Settings - API Keys