tokenstat
tokenstat
302ai

Deepseek-Reasoner

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

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

Cheapest input
$0.14
$/MTok · models.dev
Cheapest output
$0.28
$/MTok
Context
1M
tokens
Offers
7
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-reasonerDeepSeek$0.14$0.28$0.00281M
LiteLLMdeepseek-reasoner$0.28$0.42$0.028
LiteLLMdeepseek/deepseek-reasoner$0.28$0.42$0.028
models.devdeepseek-reasoner302.AI$0.29$0.43$0128K
models.devdeepseek-reasonerNanoGPT$0.4$1.70$064K
models.devdeepseek/deepseek-reasonerOrcaRouter$0.435$0.87$0.0281M
models.devdeepseek-reasonerHelicone$0.56$1.68$0.07128K

Capabilities

  • Reasoning
  • Tool calling
  • Attachments
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2024-07Released: 2025-01-20Family: deepseek-thinking

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