One API key for every model

Why One Key for Many Models?

Managing separate API keys for each AI provider is tedious. You need multiple accounts, billing setups, and code changes to switch between models. An LLM API aggregator solves this by providing a single API key that works across many models.

With one key, you can:

• Access Claude, GPT, DeepSeek, Qwen, GLM, Kimi, and more.
• Use a unified endpoint that follows the OpenAI API format.
• Switch models by simply changing the model parameter in your request.
• Pay with USDC on Base, no KYC required.
• Top up once and use the same balance for all models.

This simplifies development and lets you experiment with different models without signing up for each provider.

The OpenAI-Compatible Endpoint

Most aggregators offer an endpoint that mimics the OpenAI Chat Completions API. This means you can reuse existing OpenAI SDKs or HTTP clients with minimal changes.

Example Request

Here's a typical request using curl:

curl https://api.aggregator.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-3-opus",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Replace YOURAPIKEY with the key from your aggregator account and set the model field to the model you want to use.

Using SDKs

If you use the OpenAI Python SDK, you can point it to the aggregator's base URL:

from openai import OpenAI

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

response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Similarly, the Node.js SDK works with a custom baseURL.

Switching Models

Changing the model is as simple as updating the model field in your request. For example:

{
  "model": "deepseek-chat",
  "messages": [{"role": "user", "content": "Explain quantum computing"}]
}

To use Qwen, change to "qwen-max"; for GLM, use "glm-4"; for Kimi, use "kimi" (exact model names depend on the aggregator's supported list).

This flexibility allows you to:

• Compare responses from different models easily.
• Route tasks to the most suitable model (e.g., use a cheaper model for simple queries).
• Fall back to another model if one is unavailable.

Pricing and Billing

The aggregator charges a markup on the official API prices. You pay the official price multiplied by 1.3. For example, if a model costs $1 per million tokens officially, you pay $1.30 per million tokens through the aggregator.

If you contribute keys to the aggregator, you earn credits. For each API call using your key, you receive the official price multiplied by 1.1 (or 1.2 for premium keys) in USDC. This is a reward for sharing your API access.

All payments are made in USDC on the Base network, and no KYC is required. You can top up your balance by sending USDC to the provided address.

Getting Started

1. Sign up on the aggregator's website (no KYC).
2. Top up your balance with USDC on Base.
3. Generate an API key.
4. Use the OpenAI-compatible endpoint with your chosen model.
5. Switch models anytime by changing the model field.

Conclusion

A single API key for all major AI models simplifies development and billing. By using an OpenAI-compatible endpoint, you can integrate once and access Claude, GPT, DeepSeek, Qwen, GLM, Kimi, and more. The USDC-based payment system with no KYC makes it accessible worldwide. Start building with one key today.