DeepSeek V3.2 API Pricing

DeepSeek V3.2 pricing by provider

20 listings across 10 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

What DeepSeek V3.2 costs in practice

1,000 requests with 2,000 input and 500 output tokens each

100 long-document requests with 100,000 input and 2,000 output tokens each

DeepSeek V3.2 features

• Function calling
• Parallel tool calls
• Structured output
• Reasoning
• Prompt caching

Use DeepSeek V3.2 with LiteLLM

Call DeepSeek V3.2 through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

from litellm import completion

response = completion(
    model="deepseek/deepseek-v3.2",
    messages=[{"role": "user", "content": "Hello!"}],
)

model_list:
  - model_name: deepseek-v3.2
    litellm_params:
      model: deepseek/deepseek-v3.2
      api_key: os.environ/DEEPSEEK_API_KEY

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "deepseek-v3.2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

DeepSeek V3.2 FAQ

More DeepSeek models

• DeepSeek V3 2 251201Free
• DeepSeek V3 Turbo$0.40 / $1.30 per 1M tokens
• DeepSeek V3.2 Speciale$0.58 / $1.68 per 1M tokens
• DeepSeek V3.2 Exp$0.27 / $0.41 per 1M tokens
• DeepSeek V3.1 Terminus$0.27 / $1 per 1M tokens
• DeepSeek V3.1Free
• DeepSeek V3$0.27 / $1.10 per 1M tokens
• DeepSeek V4.1 Flash Fast$0.60 / $2.40 per 1M tokens