All models
DeepSeekAll-rounder·Open weights: MITAvailable

DeepSeek V3.2

deepseek/deepseek-v3.2

License: MIT

Newer DeepSeek with cheaper output

reasoningcodelong context
Try in chat Get API key
Input
28 pts
per 1M tokens
Output
40 pts
per 1M tokens
Typical reply
≈ 0.048 pts
1k tokens in, 500 out
Context
160K
Context
Speed
62 tok/s
*
Time to first token
1.4 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-v3.2",
    "messages": [{"role": "user", "content": "Hello! What can you do?"}]
  }'

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

Similar models

  • DeepSeek · All-rounder

    DeepSeek V3.1

    Flagship quality at a budget price

    27 pts/ 100 pts

    Input / 1M · Output / 1M

    Context 160K58 tok/s

  • Alibaba · All-rounder

    Qwen3 235B

    Large all-rounder at a small-model price

    9.5 pts/ 58 pts

    Input / 1M · Output / 1M

    Context 256K75 tok/s