tokenstat
homepricingstatshelpsign in
tokenstat
DeepSeek

DeepSeek V3 (Turbo)

deepseek/deepseek-v3-turbo · rates as of · Benchmarks · Plans · Calculator

Fast DeepSeek model for efficient chat, coding help, and agent loops

Cheapest input
$0.4
$/MTok · models.dev
Cheapest output
$1.30
$/MTok
Context
64K
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/deepseek-v3-turboNovita AI$0.4$1.30$064K
LiteLLMdeepseek/deepseek-v3-turbo—$0.4$1.30$0.04—
LiteLLMdeepseek-v3-turbo—$0.4$1.30$0.04—
LiteLLMnovita/deepseek/deepseek-v3-turbo—$0.4$1.30$0.04—

Capabilities

  • Tool calling
  • Open weights
  • In: text
  • Out: text
Released: 2025-03-05

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