tokenstat
tokenstat

DeepSeek V3.2 Speciale

deepseek/deepseek-v3.2-speciale · rates as of · Benchmarks · Plans · Calculator

DeepSeek chat model for instruction following, coding, and analysis

Cheapest input
$0.28
$/MTok · models.dev
Cheapest output
$0.42
$/MTok
Context
163K
tokens
Offers
5
2 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestdeepseek/deepseek-v3.2-specialeNanoGPT$0.28$0.42$0163K
models.devdeepseek-v3.2-specialeAzure$0.58$1.68$0128K
models.devdeepseek-v3.2-specialeAzure$0.58$1.68$0128K
LiteLLMdeepseek-v3.2-speciale$0.58$1.68$0.058
LiteLLMazure_ai/deepseek-v3.2-speciale$0.58$1.68$0.058

Capabilities

  • Reasoning
  • Attachments
  • Open weights
  • In: text
  • In: pdf
  • Out: text
Knowledge cutoff: 2024-07Released: 2025-12-02Family: deepseek

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash