← Blog

2026-10-12 · 5 min read

How Developers Can Effectively Use Air Credits to Access AI Inference

Explore how developers can purchase Air Credits, utilize them to call the /api/v1 chat completions endpoint, and navigate the Air Inference marketplace for AI models.

How Developers Can Effectively Use Air Credits to Access AI Inference

In the rapidly evolving landscape of artificial intelligence, developers are constantly seeking efficient ways to leverage AI models for their applications. Air Inference offers a unique two-sided marketplace that simplifies the process of accessing AI inference through a system of Air Credits. This article will guide you through the process of purchasing Air Credits, utilizing them to call the /api/v1 chat completions endpoint, and navigating the Air Inference marketplace to enable various AI models.

Understanding Air Credits

Air Credits are a form of digital currency within the Air Inference ecosystem. Developers can purchase these credits to access a range of AI inference services provided by various model providers. The flexibility of Air Credits allows developers to seamlessly integrate AI capabilities into their applications without the burden of managing complex payment systems or subscriptions.

Why Use Air Credits?

  1. Simplicity: Air Credits streamline the payment process for AI services. Instead of dealing with multiple payment gateways, developers can simply top up their Air Credits and use them as needed.

  2. Flexibility: With Air Credits, developers can experiment with different AI models and endpoints without committing to long-term contracts or expensive subscriptions.

  3. Marketplace Access: Air Inference connects developers with a variety of providers who list OpenAI-compatible endpoints, such as vLLM and llama.cpp wrappers. This diversity allows developers to choose the best model for their specific use case.

Purchasing Air Credits

To get started with Air Inference, developers first need to purchase Air Credits. Here’s a step-by-step guide:

Step 1: Create an Account

To buy Air Credits, you need to create an account on the Air Inference platform. This process is straightforward:

  • Visit the Air Inference website.
  • Click on the "Sign Up" button.
  • Fill out the registration form with your details and verify your email address.

Step 2: Top Up Air Credits

Once your account is set up, you can top up your Air Credits. Follow these steps:

  • Log in to your Air Inference account.
  • Navigate to the “Billing” or “Credits” section of your dashboard.
  • Select the amount of Air Credits you wish to purchase. The platform typically offers different packages to fit various budgets.
  • Complete the payment process using the available payment methods.

After successfully topping up your account, your Air Credits will be instantly available for use.

Navigating the Air Inference Marketplace

With your Air Credits in place, you can now explore the Air Inference marketplace. Here’s how to navigate this ecosystem effectively:

Step 1: Browse Available Models

In the marketplace, you will find a variety of AI models provided by different developers. Each entry typically includes information about the model, its capabilities, and its pricing in Air Credits. Take the time to review these options carefully:

  • Look for models that match your application’s requirements.
  • Check the documentation provided by each model for specific usage instructions.
  • Pay attention to user reviews or ratings if available.

Step 2: Select and Enable a Model

Once you have identified a suitable model, you can enable it for use in your application. This usually involves:

  • Clicking on the model entry in the marketplace.
  • Reviewing any additional configuration options or parameters that may be required.
  • Following the instructions to enable the model for your account.

Enabling a model will typically generate an API endpoint URL that you can use to access the model’s functionality.

Calling the /api/v1 Chat Completions Endpoint

With your Air Credits topped up and a model enabled, you are now ready to make API calls to the /api/v1 chat completions endpoint. This endpoint is crucial for generating interactive chat responses using your selected AI model.

Step 1: Prepare Your API Request

To call the /api/v1 endpoint, you will need to format your request correctly. Here’s a general structure for making a chat completion request:

  1. Endpoint URL: Use the endpoint URL generated when you enabled your model.
  2. Headers: Include necessary headers for authorization and content type.
  3. Body: Construct the body of your request with the required parameters, such as the input text or prompt.

Example API Call

Here’s a short example of what a cURL request might look like for calling the /api/v1 chat completions endpoint:

curl -X POST https://api.airinference.com/api/v1/chat/completions \
-H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
-H "Content-Type: application/json" \
-d '{
  "prompt": "Hello, how can I help you today?",
  "max_tokens": 150
}'

Replace YOUR_ACCESS_TOKEN with your actual access token and adjust the prompt and max_tokens values based on your requirements.

Step 2: Handle the Response

After making your API call, you will receive a response from the model. Typically, this response will include the generated text based on your input prompt. It’s important to handle the response appropriately:

  • Parse the JSON response to extract the generated text.
  • Implement error handling to manage any issues that may arise, such as rate limits or invalid requests.

Best Practices for Using Air Inference

To make the most out of your experience with Air Inference, consider the following best practices:

1. Experiment with Different Models

There are numerous AI models available in the marketplace, so don’t hesitate to experiment. Different models may perform better for specific tasks, so testing multiple options can help you find the best fit.

2. Monitor Your Air Credits Usage

Keep track of your Air Credits usage to avoid unexpected depletion. The Air Inference dashboard should provide insights into how many credits you have consumed and how many remain.

3. Optimize Your API Calls

When making API calls, especially to the /api/v1 endpoint, optimize your requests. For instance, use the max_tokens parameter wisely to control the length of the generated responses, which can help in conserving your Air Credits.

4. Stay Updated

AI technology is constantly evolving. Stay informed about new models and features added to the Air Inference marketplace. Regularly check the documentation and any announcements from Air Inference to leverage the latest advancements.

Conclusion

Air Inference provides developers with an accessible and efficient way to integrate AI inference capabilities into their applications. By purchasing Air Credits, exploring the marketplace, and utilizing the /api/v1 chat completions endpoint, developers can enhance their projects with powerful AI models.

With the steps outlined in this guide, you should now feel equipped to navigate the Air Inference ecosystem successfully. Whether you’re building chatbots, generating content, or developing innovative AI applications, Air Inference offers the tools and resources you need to succeed in your development journey.