tokenstat
tokenstat

DeepSeek: V3

deepseek/deepseek-chat · rates as of · Benchmarks · AI plans · Calculator

DeepSeek chat model for instruction following, coding, and analysis

Cheapest input
$0.1
$/MTok · models.dev
Cheapest output
$0.425
$/MTok
Context
1M
tokens
Sources
3
8 listings

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestdeepseek-chatNanoGPT$0.1$0.425$0.05128K
models.devdeepseek/deepseek-chatOrcaRouter$0.147$0.295$0.021M
models.devdeepseek/deepseek-chatEden AI$0.15$0.6$0.003131K
models.devdeepseek/deepseek-chatZenMux$0.28$0.42$0.03128K
LiteLLMdeepseek/deepseek-chatN/A$0.28$0.42$0.028N/A
LiteLLMdeepseek-chatN/A$0.28$0.42$0.028N/A
models.devdeepseek/deepseek-chatKilo Gateway$0.32$0.89$0164K
OpenRouterdeepseek/deepseek-chatOpenRouter$0.32$0.89$0.032164K

Capabilities

  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: pdf
  • Out: text
Knowledge cutoff: 2025-09Released: 2025-12-01Family: deepseek

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.