Hub/Models/deepseek/deepseek-v3.2-exp
deepseektext → text

DeepSeek: DeepSeek V3.2 Exp

Canonical ID: deepseek/deepseek-v3.2-exp

Compare ModelOpen on OpenRouter →

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...

Artificial Analysis Benchmarks

Verified
No standardized Artificial Analysis benchmark scores recorded for this variant yet.

Token Pricing & Economics

Prompt Input (1M Tokens)
$0.27
Input
Completion Output (1M Tokens)
$0.41
Output
Prompt KV-Cache Read (1M Tokens)
$0.00
Cached
Context Window Capacity
160k tokens
Context

Supported Parameters & Features

frequency_penaltyinclude_reasoningmax_tokensreasoningresponse_formatstructured_outputstemperaturetool_choicetoolstop_ktop_p