How to Access DeepSeek‑R1 671B Model for Free via Tencent Cloud

This guide shows how to obtain a free API key from Tencent Cloud's Knowledge Engine, configure OpenAI SDK or a chat client, and call the full‑size 671B DeepSeek‑R1 model without local hardware constraints, with step‑by‑step instructions and sample code.

Programmer DD
Programmer DD
Programmer DD
How to Access DeepSeek‑R1 671B Model for Free via Tencent Cloud

DeepSeek‑R1's impressive reasoning has attracted many users, but the free web version suffers from high traffic and occasional attacks, and the official API service has been paused for recharging.

To use the model more smoothly, you can deploy DeepSeek yourself or, more conveniently, obtain free access to the full 671B parameters through Tencent Cloud's Knowledge Engine.

Get a Free API Key

1. Create a Tencent Cloud account and open the Knowledge Engine (LKE) console: https://console.cloud.tencent.com/lkeap

2. The DeepSeek series (including deepseek‑v3 and deepseek‑r1) is currently offered for free on a limited‑time basis.

3. Click “Open Large Model Knowledge Engine”.

4. Choose the appropriate call method to obtain the API KEY. Use the OpenAI‑compatible key for chat‑type clients, or the native key for custom code.

Note: Save the key after creation!

Calling the Model with OpenAI SDK

If you obtained the OpenAI‑compatible key, you can use the OpenAI SDK as follows:

from openai import OpenAI

# Construct client
client = OpenAI(
    api_key="sk-xxxxxxxxxxx",  # Knowledge Engine APIKey
    base_url="https://api.lkeap.cloud.tencent.com/v1",
)

s_value = True  # streaming
chat_completion = client.chat.completions.create(
    model="deepseek-r1",
    messages=[{"role": "user", "content": "你是谁"}],
    stream=s_value,
)

if s_value:
    for chunk in chat_completion:
        if hasattr(chunk.choices[0].delta, 'reasoning_content'):
            print(f"{chunk.choices[0].delta.reasoning_content}", end="")
        if hasattr(chunk.choices[0].delta, 'content'):
            if chunk.choices[0].delta.content is not None and len(chunk.choices[0].delta.content) != 0:
                print(chunk.choices[0].delta.content, end="")
else:
    result = chat_completion.choices[0].message.content

Calling the Model with a Chat Client

After obtaining the API KEY, configure a chat client with these key elements:

Use the OpenAI API call method.

Set the API KEY and endpoint to https://api.lkeap.cloud.tencent.com/v1.

Specify the DeepSeek model name, e.g., deepseek-r1 or deepseek-v3.

Conclusion

If you frequently need DeepSeek and encounter service congestion, this free entry allows usage until 2025‑02‑25 23:59:59, after which a low‑cost paid plan is available for long‑term or backup use.

APIDeepSeekTencent CloudOpenAI SDKFree Access
Programmer DD
Written by

Programmer DD

A tinkering programmer and author of "Spring Cloud Microservices in Action"

0 followers
Reader feedback

How this landed with the community

Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.