tokenstat
tokenstat

DeepSeek Prover v2 671B

deepseek/deepseek-prover-v2-671b · rates as of · Benchmarks · Plans · Calculator

Flagship DeepSeek model for coding, reasoning, and agentic work

Cheapest input
$0.7
$/MTok · models.dev
Cheapest output
$2.50
$/MTok
Context
160K
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/deepseek-prover-v2-671bNovita AI$0.7$2.50$0160K
LiteLLMdeepseek/deepseek-prover-v2-671b$0.7$2.50$0.07
LiteLLMdeepseek-prover-v2-671b$0.7$2.50$0.07
LiteLLMnovita/deepseek/deepseek-prover-v2-671b$0.7$2.50$0.07
models.devdeepseek/deepseek-prover-v2-671bNanoGPT$1$2.50$0160K

Capabilities

  • Open weights
  • In: text
  • Out: text
Released: 2025-04-30Family: 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