All AI models · LLM benchmarks · Methodology

DeepSeek

DeepSeek V3.2 Exp

DeepSeek chat model for instruction following, coding, and analysis

Model facts

Context window
164K tokens
Maximum output
66K tokens
Cheapest paid input
$0.22 per 1M tokens
Cheapest paid output
$0.33 per 1M tokens
Open weights
yes
Providers
9

Capabilities and modalities

reasoning, tool calling, structured output, temperature control, open weights, text.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
Reasoning25.9not measured87.7not measured
Non-reasoning21.7not measured57.7not measured

Observed price history

  • 2026-08-24: $0.22 input / $0.33 output per 1M tokens

API providers

  • iFlow — model id deepseek-v3.2; free input / free output per 1M tokens; provider documentation
  • ZenMux — model id deepseek/deepseek-v3.2-exp; $0.22 input / $0.33 output per 1M tokens; provider documentation
  • Meganova — model id deepseek-ai/DeepSeek-V3.2-Exp; $0.27 input / $0.4 output per 1M tokens; provider documentation
  • Kilo Gateway (DeepSeek) — model id deepseek/deepseek-v3.2-exp; $0.27 input / $0.41 output per 1M tokens; provider documentation
  • NovitaAI — model id deepseek/deepseek-v3.2-exp; $0.27 input / $0.41 output per 1M tokens; provider documentation
  • OpenRouter — model id deepseek/deepseek-v3.2-exp; $0.27 input / $0.41 output per 1M tokens; provider documentation
  • NanoGPT — model id deepseek-ai/deepseek-v3.2-exp; $0.28 input / $0.42 output per 1M tokens; provider documentation
  • Alibaba (China) — model id deepseek-v3-2-exp; $0.287 input / $0.431 output per 1M tokens; provider documentation
  • Qiniu — model id deepseek/deepseek-v3.2-exp; not published input / not published output per 1M tokens; provider documentation