Skip to content

DeepSeek V3.2 Exp

deepseek/deepseek-v3.2-exp

context
164K
modalities
text → text
capabilities
Tool use, Reasoning, Structured output, Low cost

Overview

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Providers

Access method depends on provider and account setup.

Pricing

  • AtlasCloud

    input / 1M
    $0.1344
    output / 1M
    $0.2016
  • Novita

    input / 1M
    $0.27
    output / 1M
    $0.41
  • SiliconFlow

    input / 1M
    $0.27
    output / 1M
    $0.41

Use this model through Nautili

Route requests to DeepSeek V3.2 Exp through your Nautili gateway using a supported SDK or the Nautili SDK.

Connect your stack to Nautili

Route across supported providers through one control layer.