Back to Models

DeepSeek V3 0324

DeepSeek MoE model with 671B parameters (37B active) and 128K context for general tasks

Parameters
671 B
Context
128,000 tokens
Released
Mar 24, 2024

Leaderboards

Performance vs. Industry Average

Intelligence

DeepSeek V3 0324 is of lower intelligence compared to average (4.1), with an intelligence score of 3.9.

Price

DeepSeek V3 0324 is cheaper compared to average ($0.91 per 1M Tokens) with a price of $0.12 per 1M Tokens.

Latency

DeepSeek V3 0324 has a lower average latency compared to average (45.24s), with an average latency of 40.30s.

P99 Latency

DeepSeek V3 0324 has a higher P99 latency compared to average (172.60s), taking 199.71s to receive the first token at P99 (TTFT).

Context Window

DeepSeek V3 0324 has a smaller context window than average (246k tokens), with a context window of 128k tokens.

DeepSeek V3 0324 - AutoBench