DeepSeek R1 0528

DeepSeek R1 0528 is a reasoning-focused checkpoint of DeepSeek's R1 line, trained with reinforcement learning to produce long chain-of-thought traces before answering. It is competitive with frontier reasoning models on math, coding, and logic benchmarks, and is open-weight. Use it for problems where step-by-step deliberation improves accuracy: math proofs, complex debugging, scientific Q&A, and structured planning.

Quick start

Use any OpenAI-compatible client. Just change base_url and your key.

from openai import OpenAI

client = OpenAI(
    api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.thalam.ai/v1",
)

response = client.chat.completions.create(
    model="deepseek/deepseek-r1-0528",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

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