tokenstat
tokenstat

DeepSeek R1

deepseek-ai/DeepSeek-R1 · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0.5
$/MTok · models.dev
Cheapest output
$2.18
$/MTok
Context
164K
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-ai/DeepSeek-R1SiliconFlow (China)$0.5$2.18$0164K
models.devdeepseek-ai/DeepSeek-R1SiliconFlow$0.5$2.18$0164K
models.devdeepseek-ai/DeepSeek-R1Hugging Face$0.7$2.50$064K
LiteLLMdeepseek-ai/DeepSeek-R1$0.7$2.40$0.07
models.devdeepseek-ai/DeepSeek-R1Abacus$3$7$0128K
models.devdeepseek-ai/DeepSeek-R1Together AI$3$7$0164K
LiteLLMdeepseek-ai/deepseek-r1$3.75$10$0.375

Capabilities

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

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.

Sources: Arena AI, Artificial Analysis. See /benchmarks.

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