tokenstat
tokenstat
302ai

deepseek-v3.2

302ai/deepseek-v3.2 · rates as of · Benchmarks · Plans · Calculator

DeepSeek chat model for instruction following, coding, and analysis

Cheapest input
$0.18
$/MTok · models.dev
Cheapest output
$0.35
$/MTok
Context
164K
tokens
Offers
13
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. Free/$0 listings are hidden by default (3 omitted). Show free/$0 offers.

SourceProviderInputOutputCache readContext
models.devcheapestdeepseek-v3.2CrofAI$0.18$0.35$0.04164K
models.devdeepseek-v3.2LLM Gateway$0.26$0.38$0.13164K
models.devdeepseek-v3.2Cortecs$0.266$0.444$0164K
models.devdeepseek-v3.2Helicone$0.27$0.41$0164K
models.devdeepseek-v3.2Vivgrid$0.28$0.42$0128K
LiteLLMDeepSeek-V3.2$0.28$0.4$0.028
models.devdeepseek-v3.2302.AI$0.29$0.43$0128K
models.devdeepseek-v3.2Venice AI$0.33$0.48$0.16160K
models.devdeepseek-v3.2Azure$0.58$1.68$0128K
models.devdeepseek-v3.2Azure$0.58$1.68$0128K
LiteLLMdeepseek-v3.2$0.58$1.68$0.058
models.devdeepseek.v3.2Amazon Bedrock$0.62$1.85$0164K
LiteLLMdeepseek.v3.2$0.62$1.85$0.062

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: image
  • Out: text
Knowledge cutoff: 2024-12Released: 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