tokenstat
tokenstat

DeepSeek V3.1

deepseek-ai/DeepSeek-V3.1 · rates as of · Benchmarks · Plans · Calculator

Legacy model retained for compatibility with older integrations

Cheapest input
$0.2
$/MTok · models.dev
Cheapest output
$0.7
$/MTok
Context
164K
tokens
Offers
10
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-V3.1NanoGPT$0.2$0.7$0128K
models.devdeepseek-ai/DeepSeek-V3.1Submodel$0.2$0.8$075K
models.devdeepseek-ai/DeepSeek-V3.1Meganova$0.27$1$0164K
models.devdeepseek-ai/DeepSeek-V3.1SiliconFlow$0.27$1$0164K
LiteLLMdeepseek-ai/DeepSeek-V3.1$0.27$1$0.216
models.devdeepseek-ai/DeepSeek-V3.1Baseten$0.5$1.50$0.05164K
models.devdeepseek-ai/DeepSeek-V3.1Weights & Biases$0.55$1.65$0.55161K
models.devdeepseek-ai/DeepSeek-V3-1Together AI$0.6$1.70$0131K
LiteLLMdeepseek-ai/deepseek-v3.1$0.672$2.02$0.0672
LiteLLMwandb/deepseek-ai/DeepSeek-V3.1$55000$165000$5500

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: pdf
  • Out: text
Knowledge cutoff: 2025-08Released: 2025-08-25Family: 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