To prevent any potential harm, we reiterate that is our sole official account on Twitter/X.
Any accounts:
- representing us
- using identical avatars
- using similar names
are impersonations.
Please stay vigilant to avoid being misled!
DeepSeek
DeepSeek
164 posts
DeepSeek
@deepseek_ai
Unravel the mystery of AGI with curiosity. Answer the essential question with long-termism.
DeepSeek’s posts
DeepSeek-R1 is here!
Performance on par with OpenAI-o1
Fully open-source model & technical report
MIT licensed: Distill & commercialize freely!
Website & API are live now! Try DeepThink at chat.deepseek.com today!
1/n
Day 0: Warming up for #OpenSourceWeek!
We're a tiny team exploring AGI. Starting next week, we'll be open-sourcing 5 repos, sharing our small but sincere progress with full transparency.
These humble building blocks in our online service have been documented,
Excited to see everyone’s enthusiasm for deploying DeepSeek-R1! Here are our recommended settings for the best experience:
• No system prompt
• Temperature: 0.6
• Official prompts for search & file upload: bit.ly/4hyH8np
• Guidelines to mitigate model bypass Introducing NSA: A Hardware-Aligned and Natively Trainable Sparse Attention mechanism for ultra-fast long-context training & inference!
Core components of NSA:
• Dynamic hierarchical sparse strategy
• Coarse-grained token compression
• Fine-grained token selection
With
Introducing DeepSeek-V3.1: our first step toward the agent era!
Hybrid inference: Think & Non-Think — one model, two modes
Faster thinking: DeepSeek-V3.1-Think reaches answers in less time vs. DeepSeek-R1-0528
Stronger agent skills: Post-training boosts tool use and
Hybrid inference: Think & Non-Think — one model, two modes
Faster thinking: DeepSeek-V3.1-Think reaches answers in less time vs. DeepSeek-R1-0528
Stronger agent skills: Post-training boosts tool use and
Introducing DeepSeek-V3!
Biggest leap forward yet:
60 tokens/second (3x faster than V2!)
Enhanced capabilities
API compatibility intact
Fully open-source models & papers
1/nGIF
DeepSeek-V3-0324 is out now!
Major boost in reasoning performance
Stronger front-end development skills
Smarter tool-use capabilities
For non-complex reasoning tasks, we recommend using V3 — just turn off “DeepThink”
API usage remains unchanged
Models are
GIF
Day 5 of #OpenSourceWeek: 3FS, Thruster for All DeepSeek Data Access
Fire-Flyer File System (3FS) - a parallel file system that utilizes the full bandwidth of modern SSDs and RDMA networks.
6.6 TiB/s aggregate read throughput in a 180-node cluster
3.66 TiB/min
Day 1 of #OpenSourceWeek: FlashMLA
Honored to share FlashMLA - our efficient MLA decoding kernel for Hopper GPUs, optimized for variable-length sequences and now in production.
BF16 support
Paged KV cache (block size 64)
3000 GB/s memory-bound & 580 TFLOPS
DeepSeek-R1-0528 is here!
Improved benchmark performance
Enhanced front-end capabilities
Reduced hallucinations
Supports JSON output & function calling
Try it now: chat.deepseek.com
No change to API usage — docs here: api-docs.deepseek.com/guides/reasoni
GIF
Day 6 of #OpenSourceWeek: One More Thing – DeepSeek-V3/R1 Inference System Overview
Optimized throughput and latency via:
Cross-node EP-powered batch scaling
Computation-communication overlap
Load balancing
Statistics of DeepSeek's Online Service:
73.7k/14.8k Day 2 of #OpenSourceWeek: DeepEP
Excited to introduce DeepEP - the first open-source EP communication library for MoE model training and inference.
Efficient and optimized all-to-all communication
Both intranode and internode support with NVLink and RDMA
Replying to
DeepSeek has not issued any cryptocurrency. Currently, there is only one official account on the Twitter platform. We will not contact anyone through other accounts.Please stay vigilant and guard against potential scams.
Off-Peak Discounts Alert!
Starting today, enjoy off-peak discounts on the DeepSeek API Platform from 16:30–00:30 UTC daily:
DeepSeek-V3 at 50% off
DeepSeek-R1 at a massive 75% off
Maximize your resources smarter — save more during these high-value hours!
Introducing DeepSeek-V3.2-Exp — our latest experimental model!
Built on V3.1-Terminus, it debuts DeepSeek Sparse Attention(DSA) for faster, more efficient training & inference on long context.
Now live on App, Web, and API.
API prices cut by 50%+!
1/n Day 3 of #OpenSourceWeek: DeepGEMM
Introducing DeepGEMM - an FP8 GEMM library that supports both dense and MoE GEMMs, powering V3/R1 training and inference.
Up to 1350+ FP8 TFLOPS on Hopper GPUs
No heavy dependency, as clean as a tutorial
Fully Just-In-Time compiled
Day 4 of #OpenSourceWeek: Optimized Parallelism Strategies
DualPipe - a bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.
github.com/deepseek-ai/Du
EPLB - an expert-parallel load balancer for V3/R1.
Replying to
DeepSeek-R1: Technical Highlights
Large-scale RL in post-training
Significant performance boost with minimal labeled data
Math, code, and reasoning tasks on par with OpenAI-o1
More details: github.com/deepseek-ai/De
4/n
Replying to
License Update!
DeepSeek-R1 is now MIT licensed for clear open access
Open for the community to leverage model weights & outputs
API outputs can now be used for fine-tuning & distillation
3/n DeepSeek-V3.1 → DeepSeek-V3.1-Terminus
The latest update builds on V3.1’s strengths while addressing key user feedback.
What’s improved?
Language consistency: fewer CN/EN mix-ups & no more random chars.
Agent upgrades: stronger Code Agent & Search Agent performance. DeepSeek-R1-Lite-Preview is now live: unleashing supercharged reasoning power!
o1-preview-level performance on AIME & MATH benchmarks.
Transparent thought process in real-time.
Open-source models & API coming soon!
Try it now at chat.deepseek.com
#DeepSeek
Introducing DeepSeek App!
Powered by world-class DeepSeek-V3
FREE to use with seamless interaction
Now officially available on App Store & Google Play & Major Android markets
Download now: download.deepseek.com/app/
1/3
Replying to
This is a typical impersonation account. Please do not trust any information from this account.
Replying to
API Access & Pricing
Use DeepSeek-R1 by setting model=deepseek-reasoner
$0.14 / million input tokens (cache hit)
$0.55 / million input tokens (cache miss)
$2.19 / million output tokens
API guide: api-docs.deepseek.com/guides/reasoni
5/n
Replying to
Bonus: Open-Source Distilled Models!
Distilled from DeepSeek-R1, 6 small models fully open-sourced
32B & 70B models on par with OpenAI-o1-mini
Empowering the open-source community
Pushing the boundaries of **open AI**!
2/n
DeepSeek-V2.5-1210: The Grand Finale
Internet Search is now live on the web! Visit chat.deepseek.com and toggle “Internet Search” for real-time answers. 
(1/3)
GIF