DeepSeek: getting started

What is DeepSeek?

DeepSeek is a family of large language models known for strong reasoning and coding abilities. It includes general-purpose chat models and specialized reasoning models that work through step-by-step thinking.

Through an LLM API aggregator, you can call DeepSeek models alongside others like Claude, GPT, and Qwen using a single API key. This simplifies integration and billing.

Why use DeepSeek?

• Strong reasoning: DeepSeek models handle complex logic, math, and multi-step problems well.
• Coding assistance: They perform well on code generation, debugging, and explanation tasks.
• Cost-effective: DeepSeek is often more affordable than some proprietary models, and aggregator pricing adds a transparent markup.
• OpenAI-compatible API: You can use existing OpenAI SDKs and tools with minimal changes.

Getting started

1. Create an account on the aggregator platform.
2. Top up with USDC on Base — no KYC required.
3. Generate an API key from your dashboard.
4. Call the API using the OpenAI-compatible endpoint.

Minimal code example

Below is a Python example using the OpenAI SDK. Replace YOURAPIKEY with your actual key and adjust the base URL if needed.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.aggregator.com/v1"  # Replace with actual base URL
)

response = client.chat.completions.create(
    model="deepseek-chat",  # or another DeepSeek model identifier
    messages=[
        {"role": "user", "content": "Explain the concept of recursion in simple terms."}
    ]
)

print(response.choices[0].message.content)

Understanding pricing and credits

The aggregator charges official price × 1.3 for usage. This markup covers infrastructure, billing, and access to multiple models.

If you contribute a key (bring your own API key from a provider), you receive credits at official price × 1.1 (or × 1.2 for premium keys) in USDC. This means you can offset costs by sharing your keys.

All transactions are settled in USDC on Base, providing fast and low-cost payments.

Best practices

• Start with small requests to test model behavior and latency.
• Use system prompts to guide the model's tone and format.
• Monitor usage via the dashboard to manage costs.
• Leverage key contribution if you have existing provider keys to earn credits.

Next steps

Explore other models available through the aggregator, such as Claude, GPT, and Qwen. The unified API lets you switch models by changing just the model parameter.