tokenstat
tokenstat

DeepSeek V3.2

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

DeepSeek chat model for instruction following, coding, and analysis

Cheapest input
$0.56
$/MTok · models.dev
Cheapest output
$1.68
$/MTok
Context
164K
tokens
Offers
4
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-ai/deepseek-v3.2-maasGoogle Vertex AI$0.56$1.68$0.056164K
LiteLLMdeepseek-ai/deepseek-v3.2-maas$0.56$1.68$0.056
LiteLLMdeepseek-v3.2-maas$0.56$1.68$0.056
LiteLLMvertex_ai/deepseek-ai/deepseek-v3.2-maas$0.56$1.68$0.056

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • In: pdf
  • Out: text
Released: 2025-12-17Family: deepseek

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.

Sources: Arena AI, Artificial Analysis. See /benchmarks.

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