tokenstat
tokenstat

DeepSeek R1 Distill Llama 70B

alibaba-cn/deepseek-r1-distill-llama-70b · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0.03
$/MTok · models.dev
Cheapest output
$0.13
$/MTok
Context
131K
tokens
Offers
5
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-r1-distill-llama-70bHelicone$0.03$0.13$0128K
LiteLLMDeepSeek-R1-Distill-Llama-70B$0.2$0.6$0.02
models.devdeepseek-r1-distill-llama-70bAlibaba / Qwen$0.287$0.861$033K
models.devdeepseek-r1-distill-llama-70bDigitalOcean$0.99$0.99$0131K
LiteLLMdeepseek-r1-distill-llama-70b$0.99$0.99$0.099

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-01Released: 2025-01-01Family: 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