Back to Models

DeepSeek 3.2 Speciale

DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance

Thinking Mode
Parameters
685000000000 B
Context
163,840 tokens
Released
Jan 12, 2025

Leaderboards

Performance vs. Industry Average

Intelligence

DeepSeek 3.2 Speciale is of higher intelligence compared to average (4.1), with an intelligence score of 4.1.

Price

DeepSeek 3.2 Speciale is cheaper compared to average ($4.91 per 1M Tokens) with a price of $0.47 per 1M Tokens.

Latency

DeepSeek 3.2 Speciale has a higher average latency compared to average (120.77s), with an average latency of 310.39s.

P99 Latency

DeepSeek 3.2 Speciale has a higher P99 latency compared to average (354.03s), taking 832.67s to receive the first token at P99 (TTFT).

Context Window

DeepSeek 3.2 Speciale has a smaller context window than average (347k tokens), with a context window of 164k tokens.

DeepSeek 3.2 Speciale - AutoBench