tokenstat
tokenstat

DeepSeek V3.1

deepseek/deepseek-chat-v3.1 · rates as of · Benchmarks · Plans · Calculator

DeepSeek chat model for instruction following, coding, and analysis

Cheapest input
$0.2
$/MTok · models.dev
Cheapest output
$0.8
$/MTok
Context
164K
tokens
Offers
6
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/deepseek-chat-v3.1TensorX$0.2$0.8$0.05164K
LiteLLMdeepseek/deepseek-chat-v3.1$0.2$0.8$0.02
LiteLLMopenrouter/deepseek/deepseek-chat-v3.1$0.2$0.8$0.02
LiteLLMdeepseek-chat-v3.1$0.2$0.8$0.02
OpenRouterdeepseek/deepseek-chat-v3.1OpenRouter$0.25$0.95$0.13164K
models.devdeepseek/deepseek-chat-v3.1Kilo Gateway$0.27$1$0.135164K

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-03-31Released: 2025-08-21Family: 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