---
id: "2024-12-26-deepseek-v3"
url: "https://postcutoff.com/e/2024-12-26-deepseek-v3/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2024-12-26"
date_precision: day
category: open-source
importance: 5
confidence: high
status: [Confirmed]
sources: 2
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2024-12-26-deepseek-v3/

# DeepSeek-V3: frontier-level open model trained for ~$5.6M in GPU time

Chinese lab DeepSeek released DeepSeek-V3, a 671B-parameter mixture-of-experts model (37B active) with open weights that rivaled GPT-4o and Claude 3.5 Sonnet; its final training run reportedly used 2.788M H800 GPU-hours (~$5.6M).

## Key facts
- Released 26 December 2024; technical report arXiv 2412.19437
- 671B total parameters, 37B activated per token
- Pre-trained on 14.8 trillion tokens
- 2.788M H800 GPU-hours for full training (~$5.576M at $2/GPU-hour, excluding prior research)
- Innovations: multi-head latent attention, auxiliary-loss-free load balancing, FP8 training, multi-token prediction

## What happened

DeepSeek published open weights and an unusually detailed report showing frontier performance at a fraction of the reported compute of US labs, despite export controls.

## Why it matters

Upended assumptions about the cost of frontier AI and China's position; it was the base for DeepSeek-R1 weeks later.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [DeepSeek-V3 Technical Report (arXiv)](https://arxiv.org/abs/2412.19437) (arxiv.org, paper)
2. [deepseek-ai/DeepSeek-V3 (code & weights)](https://github.com/deepseek-ai/DeepSeek-V3) (github.com, code)

## Changes

- 2026-09-29 (filed): Created

## Related

- 2025-01-20: [DeepSeek-R1: open-weights reasoning model rivals o1 and shakes markets](https://postcutoff.com/e/2025-01-20-deepseek-r1/index.md)
- 2023-12-11: [Mistral AI releases Mixtral 8x7B, an open mixture-of-experts model](https://postcutoff.com/e/2023-12-11-mixtral/index.md)