DeepSeek

DeepSeek V3.2 Exp

deepseek/deepseek-v3.2-exp

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

DeepSeek V3.2 Exp

reasoning open weights tools

DeepSeek deepseek/deepseek-v3.2-exp

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...

Input $/1M: $0.27
Output $/1M: $0.41
Context: 164K
Max output: 66K
Released: Sep 29, 2025
Modalities: text

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs DeepSeek V3.2 Exp
targets:
  - id: deepseek-v3-2-exp
    kind: llm
    name: DeepSeek V3.2 Exp
    metadata:
      model: deepseek/deepseek-v3.2-exp          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 163840
    cost:
      usd_per_1k_tokens: 0.000340

Price among DeepSeek models

Input list price per million tokens; DeepSeek V3.2 Exp is the 7th cheapest of 13 listed.

More from DeepSeek

Other models by the same vendor in the catalogue.