tokenstat
tokenstat
302ai

DeepSeek V3

302ai/deepseek-chat · rates as of · Benchmarks · Plans · Calculator

DeepSeek chat model for instruction following, coding, and analysis

Cheapest input
$0.14
$/MTok · models.dev
Cheapest output
$0.28
$/MTok
Context
1M
tokens
Offers
10
3 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-chatDeepSeek$0.14$0.28$0.00281M
models.devdeepseek/deepseek-chatOrcaRouter$0.14$0.28$0.0281M
LiteLLMopenrouter/deepseek/deepseek-chat$0.14$0.28$0.014
models.devdeepseek-chatNanoGPT$0.25$0.7$0128K
OpenRouterdeepseek/deepseek-chatOpenRouter$0.2574$1.03$0164K
models.devdeepseek/deepseek-chatZenMux$0.28$0.42$0.03128K
LiteLLMdeepseek-chat$0.28$0.42$0.028
LiteLLMdeepseek/deepseek-chat$0.28$0.42$0.028
models.devdeepseek-chat302.AI$0.29$0.43$0128K
models.devdeepseek/deepseek-chatKilo Gateway$0.4$1.30$0128K

Capabilities

  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: pdf
  • Out: text
Knowledge cutoff: 2024-07Released: 2024-11-29Family: 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