tokenstat
tokenstat

DeepSeek V3.2

deepseek/deepseek-v3.2 · rates as of · Benchmarks · Plans · Calculator

DeepSeek chat model for instruction following, coding, and analysis

Cheapest input
$0.269
$/MTok · models.dev
Cheapest output
$0.4
$/MTok
Context
164K
tokens
Offers
9
3 sources

Price changes

Cheapest list input/output only. Not a daily candle chart: rates move rarely, so this is an event log. Arrow down means cheaper.

Input $/MTok over sampled dates
Output $/MTok
  • ↑ riseOutput $0.38 → $0.4
  • ↑ riseInput $0.26 → $0.269

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-v3.2Kilo Gateway$0.269$0.4$0.1345164K
models.devdeepseek/deepseek-v3.2Novita AI$0.269$0.4$0.1345164K
OpenRouterdeepseek/deepseek-v3.2OpenRouter$0.269$0.4$0.1345164K
models.devdeepseek/deepseek-v3.2NanoGPT$0.28$0.42$0163K
models.devdeepseek/deepseek-v3.2Vercel AI Gateway$0.28$0.42$0.028128K
models.devdeepseek/deepseek-v3.2ZenMux$0.28$0.43$0128K
LiteLLMdeepseek/deepseek-v3.2$0.28$0.4$0.028
LiteLLMopenrouter/deepseek/deepseek-v3.2$0.28$0.4$0.028
models.devdeepseek/deepseek-v3.2TensorX$0.3$0.5$0.075164K

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: pdf
  • Out: text
Knowledge cutoff: 2024-07Released: 2025-12-01Family: 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