Quickstart

Create an API key, verify your model list, and send your first AIOHub API request.

Before you start

You need an AIOHub account with a positive balance. For the first test, use the OpenAI-compatible API, then switch formats when a client requires Claude Messages, Responses, or Gemini API endpoints.

First request in four steps

1. Open the console

   Sign in to the AIOHub Console. Confirm that your account has a positive balance in wallet management. If you need to add funds, see Add funds.

2. Create an API key

   Open API key management and create an API key that starts with sk-. Use one API key per tool when you want separate limits and usage logs.

   API keys are secrets. Do not share them or commit them to source control.
3. Verify available models

   Request the model list first. This confirms that your API key, balance, and group access are valid.

   curl https://api.aiohub.org/v1/models \
     -H "Authorization: Bearer sk-your-api-key"
   

   A successful response returns the models visible to the groups assigned to the current API key.

4. Send a chat request

   Send your first basic chat request with the OpenAI-compatible API.

   cURL

   curl https://api.aiohub.org/v1/chat/completions \
     -H "Authorization: Bearer sk-your-api-key" \
     -H "Content-Type: application/json" \
     -d '{
       "model": "gpt-4o",
       "messages": [{"role": "user", "content": "Hello!"}]
     }'
   

Choose an API format

Use case	Base URL	Endpoint
OpenAI SDK / general tools	https://api.aiohub.org/v1	POST /chat/completions
Codex CLI	https://api.aiohub.org/v1	POST /responses
Anthropic SDK / Claude Code	https://api.aiohub.org	POST /v1/messages
Gemini CLI	https://api.aiohub.org	POST /v1beta/models/{model}:generateContent
Gemini REST / Google SDK	https://api.aiohub.org/v1beta	POST /models/{model}:generateContent

If you are unsure which format a client needs, start with the matching client guide. If you are writing API code directly, start with OpenAI Chat Completions.

Next steps

Choose a client

Configure Claude Code, Codex CLI, Gemini CLI, OpenAI-compatible apps, or chat clients.

Understand groups

Confirm that the groups assigned to your API key can access the target model.

Read the API overview

Compare formats, auth headers, and supported endpoint families.

Troubleshoot errors

Fix authentication failures, insufficient balance, network issues, and model availability errors.