tokenstat
tokenstat

DeepSeek V3.1 Terminus

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

DeepSeek chat model for instruction following, coding, and analysis

Cheapest input
$0.25
$/MTok · models.dev
Cheapest output
$0.7
$/MTok
Context
164K
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-ai/DeepSeek-V3.1-TerminusNanoGPT$0.25$0.7$0128K
models.devdeepseek-ai/DeepSeek-V3.1-TerminusAbacus$0.27$1$0128K
models.devdeepseek-ai/DeepSeek-V3.1-TerminusSiliconFlow (China)$0.27$1$0164K
models.devdeepseek-ai/DeepSeek-V3.1-TerminusSiliconFlow$0.27$1$0164K
LiteLLMdeepseek-ai/DeepSeek-V3.1-Terminus$0.27$1$0.216

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Released: 2025-06-01Family: deepseek

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