Introduction
What AI Nexus is, which endpoints it supports, and what API keys, balance and billing mean.
What is AI Nexus
This service is provided for learning and research purposes only. Please follow each model provider's usage policies.
AI Nexus is a model API gateway for developers: with one account and one API key you can call leading AI models through OpenAI-compatible endpoints and the Claude-native endpoint (Anthropic Messages), and manage access, usage and balance in a single console.
As a developer you only need to remember these:
| Item | Value |
|---|---|
| Console | https://ai.myaiexp.com |
| Base URL (OpenAI SDK / OpenAI-compatible clients) | https://ai.myaiexp.com/v1 |
| Base URL (Anthropic SDK / Claude Code) | https://ai.myaiexp.com (no /v1) |
| Authentication | Header Authorization: Bearer <your API key> |
Available models
One API key works with the models listed on the model square; pick one with the model field of your request. More models are added over time. The current list and per-model prices are on the model square; you can also call GET /v1/models with your API key.
Supported endpoints
| Endpoint | Path | Use it for |
|---|---|---|
| OpenAI Chat Completions | POST /v1/chat/completions | OpenAI SDKs and most third-party tools |
| Claude-native Messages | POST /v1/messages | Anthropic SDKs and Claude Code, see Claude-native API |
| OpenAI Responses | POST /v1/responses | Clients that use the Responses format (such as Codex CLI), see Responses API |
| List models | GET /v1/models | See which models your API key can call |
Endpoint support varies by model: /v1/chat/completions is the general OpenAI-compatible endpoint; /v1/messages works with models that support the Claude-native format; /v1/responses works with models that support the Responses API. The available models and the endpoints each one supports are listed on the model square.
Key concepts
API keys (tokens)
An API key is what you send when calling the API: a string starting with sk-, sometimes also called a "token". You can create several keys for different projects or teammates. Each key can have its own:
- Quota limit (or unlimited quota)
- Expiry time
- Allowed models
- IP allowlist
If a key leaks, you can disable or delete just that one without affecting the others. See API Keys.
Balance and quota
Your account balance is shown in USD and is shared by all of your API keys; each key can also carry its own quota limit to cap spending for a single project or tool.
A few endpoints (for example the one that reports key usage) show the platform's internal billing unit, "quota". The conversion is 500,000 quota = 1 USD. The console shows amounts in USD by default, so you normally don't need to convert. See Wallet.
Billing
You are billed for the tokens each request actually uses. Model prices are synced daily from each vendor's official public list price, in USD per 1M tokens; current prices are on the model square.
Next step
Follow the Quickstart to make your first call.
Overview
One API key for leading AI models, through OpenAI-compatible and Claude-native endpoints. Get connected in minutes.
Quickstart
Sign up, create an API key, make your first call and check the usage logs in a few minutes.
This service is provided for learning and research purposes only. Please follow each model provider's usage policies.