← Blog

2026-11-14 · 5 min read

Provider Playbook for Air Inference — Credentials, PAYG Rates, and Best Practices

A comprehensive guide for providers on managing credentials, understanding PAYG rates, going live on Air Inference, and maintaining healthy listings in the marketplace.

Provider Playbook for Air Inference — Credentials, PAYG Rates, and Best Practices

Welcome to the Provider Playbook for Air Inference! This guide is designed to help you navigate the essential aspects of becoming a provider on our platform. We will cover everything from managing your credentials to understanding PAYG (Pay As You Go) rates, going live, and maintaining healthy listings in the marketplace. Whether you are an experienced developer or new to the AI inference space, this playbook will provide practical steps to ensure your success.

Understanding Air Inference

Before diving into the specifics, let’s briefly recap what Air Inference is. Air Inference is a two-sided marketplace that connects developers with providers of AI inference services. Developers can top up Air Credits and access OpenAI-compatible APIs, while providers can list their endpoints and receive payments off-platform. This setup allows for a seamless experience and promotes innovation in AI inference services.

Managing Credentials

Creating Your Provider Account

To start, you need to create a provider account on Air Inference. Here are the steps:

  1. Visit the Air Inference Website: Navigate to Air Inference and click on the "Sign Up" button.
  2. Fill Out the Registration Form: Provide your email, create a password, and complete any other required fields.
  3. Verify Your Email: Check your inbox for a verification email and confirm your account.
  4. Set Up Your Profile: Once logged in, complete your provider profile by adding relevant details such as your organization name, description, and contact information.

API Key Management

Your API key is crucial for authenticating your services on the Air Inference platform. Here’s how to manage it:

  1. Generate Your API Key: After setting up your profile, navigate to the API settings section to generate a new API key.
  2. Keep It Secure: Store your API key securely. Avoid sharing it publicly or hardcoding it into your applications.
  3. Regenerate If Compromised: If you suspect that your API key has been compromised, regenerate it immediately and update your applications accordingly.

Endpoint Configuration

To successfully list your endpoints on Air Inference, you need to ensure they are OpenAI-compatible and properly configured. Follow these best practices:

  • Use Standard Protocols: Ensure that your endpoints adhere to standard protocols such as REST or GraphQL.
  • Document Your API: Provide clear documentation for your endpoints, including request and response formats. This will help developers understand how to use your services effectively.
  • Set Up CORS: If applicable, configure Cross-Origin Resource Sharing (CORS) to allow requests from different origins.

Understanding PAYG Rates

As a provider on Air Inference, you’ll be paid based on a PAYG model. Here’s what you need to know:

Setting Your Rates

  1. Market Research: Before setting your rates, research similar services in the marketplace. Understanding the competitive landscape will help you position your offerings effectively.
  2. Cost Analysis: Calculate your operational costs, including infrastructure, maintenance, and any third-party services. Ensure that your rates cover these costs while remaining attractive to developers.
  3. Rate Structure: Choose a rate structure that works best for your services. You can opt for per-request pricing, subscription models, or tiered pricing based on usage.

Fee Structure

Air Inference charges approximately a 10% fee on transactions. Keep this in mind when setting your rates, as it will affect your overall earnings. For example, if you charge $1.00 per request, you will receive $0.90 after the fee.

Monitoring Usage

Once your services are live, it’s essential to monitor usage to understand how your pricing is performing. Use analytics tools to track:

  • Total requests
  • Peak usage times
  • User demographics

This data can help you refine your pricing strategy and identify opportunities for growth.

Going Live on Air Inference

After setting up your account, managing your credentials, and understanding your PAYG rates, it’s time to go live. Here’s how to prepare for launch:

Testing Your Endpoints

Before going live, conduct thorough testing of your endpoints. Ensure they are functioning as expected and can handle the anticipated load. Here are some testing strategies:

  • Unit Testing: Test individual components of your API to ensure they work correctly.
  • Integration Testing: Validate that your API interacts correctly with other systems.
  • Load Testing: Simulate multiple users accessing your API to assess its performance under stress.

Preparing Your Listing

Create an appealing listing for your services:

  1. Title and Description: Write a clear and concise title and description that highlights the key features and benefits of your service.
  2. Tags: Use relevant tags to help users find your listing easily.
  3. Pricing: Clearly display your PAYG rates and any additional costs.

Marketing Your Services

Once your listing is live, promote your services to attract developers:

  • Social Media: Share your listing on platforms like Twitter, LinkedIn, and relevant forums.
  • Content Marketing: Write blog posts or create videos demonstrating how to use your API effectively.
  • Networking: Connect with potential users and other providers in the AI community.

Maintaining Healthy Listings

Keeping your listings healthy is crucial for long-term success on Air Inference. Here are some best practices:

Regular Updates

  1. Monitor Performance: Regularly check the performance of your endpoints and resolve any issues promptly.
  2. Update Documentation: Keep your API documentation up to date with any changes to your services.

Customer Support

Providing excellent customer support can set you apart from the competition. Consider the following:

  • Prompt Response Times: Aim to respond to inquiries quickly to enhance user satisfaction.
  • Feedback Loop: Encourage users to provide feedback and use it to improve your services.

Continuous Improvement

Stay competitive by continuously improving your offerings. This can include:

  • Feature Enhancements: Regularly update your API with new features based on user requests.
  • Performance Optimization: Work on optimizing the performance of your endpoints to ensure fast response times.

Conclusion

Being a provider on Air Inference can be a rewarding experience, especially with the growing demand for AI inference services. By managing your credentials effectively, understanding PAYG rates, preparing for a successful launch, and maintaining a healthy listing, you’ll be well on your way to thriving in this marketplace.

Remember, success in this field requires ongoing effort and adaptation. Stay engaged with the developer community, keep an eye on industry trends, and continuously seek ways to improve your services. Welcome to Air Inference, and we wish you the best of luck as you embark on this exciting journey!