{"data":{"slug":"deepseek-v3","etype":"model","name":"DeepSeek-V3","cat":"Language","subtitle":"671B parameters, $5.6M disclosed final-run cost — the efficiency shock.","summary":"DeepSeek-V3 (December 2024) is a 671B-parameter MoE activating 37B per token, trained on 14.8T tokens across 2,048 H800 GPUs with a disclosed final training-run cost of about $5.576M (excluding research and prior runs — a caveat often dropped in retellings). Multi-head latent attention, FP8 training and multi-token prediction made it the most-studied efficiency result in the field; weights are open. V3.1 (August 2025) added hybrid thinking; V3.2-Exp cut long-context costs with sparse attention.","attrs":[{"b":"Published paper","g":"Overview","l":"Training","v":"14.8T tokens · 2,048 × H800 · ~2.79M GPU-hours (disclosed)"},{"b":"Published paper","g":"Overview","l":"Disclosed cost","v":"$5.576M final run only — excludes research, ablations, data and hardware"}],"kf":{"params":"671B (37B active)","context":"128K","weights":"Open","modality":"Text","rel_date":"2024-12","developer":"DeepSeek"},"aliases":["DeepSeek V3","V3.1","V3.2"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":"Prior generation","region":null,"asof":"2026-08-31","sources":[{"url":"https://arxiv.org/abs/2412.19437","label":"DeepSeek-V3 technical report"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T03:39:22+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}