All models
DeepSeekFlagship·Open weights: MITAvailable

DeepSeek R1

deepseek/deepseek-r1-0528

License: MIT

Step-by-step reasoning for hard problems

reasoningcode
Try in chat Get API key
Input
53 pts
per 1M tokens
Output
226 pts
per 1M tokens
Typical reply
≈ 0.17 pts
1k tokens in, 500 out
Context
160K
Context
Speed
45 tok/s
*
Time to first token
2.4 s
*

* Speed and latency are approximate.

How charges are rounded: each request is charged for the tokens it actually processes at the model's listed price, converted at 100 Points = USD 1 and rounded up to the nearest 0.0001 Point. Prices on this page are rounded for display.

How to use

Use the model ID in the model field of any OpenAI-compatible request.

curl https://taldermont.com/v1/chat/completions \
  -H "Authorization: Bearer sk-taldermont-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-r1-0528",
    "messages": [{"role": "user", "content": "Hello! What can you do?"}]
  }'

Replace sk-taldermont-YOUR_KEY with your key from the API keys page.

Similar models

  • Moonshot AI · Flagship

    Kimi K2.6

    Strong open model for agents and code

    79 pts/ 368 pts

    Input / 1M · Output / 1M

    Context 256K55 tok/s

  • Z.ai · Flagship

    GLM-4.7

    Reasoning and coding with tool use

    42 pts/ 184 pts

    Input / 1M · Output / 1M

    Context 200K60 tok/s