DeepSeek V3.1 is a unified hybrid reasoning open-weight model that powers agentic workflows—FP8 training, strong post-training for tool/function calling (non-thinking), Anthropic API support, and big SWE-Bench gains. In this video I unpack pricing and token efficiency, benchmark V3.1 vs R1 and Claude Sonnet 4, and show how to use it for coding agents without wasting tokens.

LINKS:
https://api-docs.deepseek.com/news/news250821
https://huggingface.co/deepseek-ai/DeepSeek-V3.1

Website: https://engineerprompt.ai/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 DeepSeek V3.1
00:31 Hybrid Inference Model Explained
01:04 Performance and Efficiency Improvements
05:02 Token Efficiency and Cost Implications
08:03 API and Hosting Considerations
13:23 Testing

DeepSeek V3.1: Bigger Than You Think!

Deepseek just released R1-0528, an upgrade to their previous R1 model. This is (potentially) based on the upgrade V3. 

Try it here: https://chat.deepseek.com/
Benchmarks: https://livecodebench.github.io/leaderboard.html
Huggingface: https://huggingface.co/deepseek-ai/DeepSeek-R1-0528

Website: https://engineerprompt.ai/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

New DeepSeek R1 is Really, Really Good Coder

DeepSeek just dropped a powerful update to V3, and it might be the best open-source LLM for developers yet. In this video, I test its coding abilities with real-world prompts—like building a full landing page in one shot and solving reasoning challenges. If you're a developer looking for the best AI model for coding, DeepSeek V3 is worth your attention.


LINKS:
https://chat.deepseek.com/
https://openrouter.ai/
https://huggingface.co/spaces/clem/deepseek-ai-DeepSeek-V3-0324
https://huggingface.co/deepseek-ai/DeepSeek-V3-0324
https://x.com/TheXeophon/status/1904225899957936314/photo/1
https://x.com/AkemiMadoka/status/1904111806693671123/photo/1
https://api-docs.deepseek.com/quick_start/pricing
https://ai.google.dev/gemini-api/docs/document-processing?lang=python

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

DeepSeek Just Updated—The Best Coding Model Yet?

Thanks to SambaNova for sponsoring the video check them out: https://fnf.dev/3WVZshS

Learn how to build a RAG system that is supercharged by the DeepSeek's reasoning model. Reasoning models can really help with the accuracy of retrieval and generation because of the inherent chain of thought. Learn how to use the SambaNova Cloud to get incredibly fast inference speed for powering Agents and RAG system. 


📌 Which model do you think is better? Let me know your thoughts in the comments!

💬 Subscribe for more AI comparisons, deep dives, and hands-on tutorials!

LINKS:
SambaNova Cloud: https://fnf.dev/3WVZshS
Github Repo: https://github.com/PromtEngineer/RAG_with_DeepSeek_R1


RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

💡 Don't forget to Like, Subscribe & Hit the Bell 🔔 for more AI deep dives!

Supercharge Your RAG Pipeline with DeepSeq R1: A Step-by-Step Guide


00:00 RAG with DeepSeek R1
00:23 Components of the RAG Pipeline
01:13 Code Walkthrough: Indexing and Retrieval
04:45 Retrieval Process and Query Handling
07:10 SambaNova Cloud and DeepSeek R1 Performance
09:13 Example Queries and Reasoning Model Insights
11:37 Re-ranking with Reasoning Models

Supercharge Your RAG with DeepSeek's Reasoning Model

OpenAI has launched GPT-4.5! While it's not a frontier model, it significantly boosts computational efficiency and offers better performance than GPT-4. However, it's 30 times more expensive and less competitive against state-of-the-art models. Designed for creative tasks with a focus on emotional intelligence, GPT-4.5 is set to be a robust base for future reasoning models. Tune in to learn more about its features, pricing, and the evolving landscape of AI models.


LINKS:
https://x.com/deepseek_ai/status/1895688300574462431
https://github.com/deepseek-ai/open-infra-index/blob/main/202502OpenSourceWeek/day_6_one_more_thing_deepseekV3R1_inference_system_overview.md
https://x.com/deedydas


RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0


00:00 Introduction to DeepSeek's Open Source Announcement
00:19 Inference System Overview
01:24 Day Six Announcement Breakdown
02:52 Capacity and Cost Analysis
04:07 Revenue and Profit Margins

DeepSeek’s 500% Profit Margin—How Are They Doing It?

SambaNova Cloud: https://fnf.dev/3WVZshS

Learn how to build a RAG system that is supercharged by the DeepSeek's reasoning model. Reasoning models can really help with the accuracy of retrieval and generation because of the inherent chain of thought. Learn how to use the SambaNova Cloud to get incredibly fast inference speed for powering Agents and RAG system. 


📌 Which model do you think is better? Let me know your thoughts in the comments!

💬 Subscribe for more AI comparisons, deep dives, and hands-on tutorials!

LINKS:
Samba Nova Cloud: https://fnf.dev/3WVZshS
Github Repo: 


RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

💡 Don't forget to Like, Subscribe & Hit the Bell 🔔 for more AI deep dives!

00:00 Why RAG with Reasoning
01:45 RAG without Frameworks
06:35 Setting up LLM with SambaNova
08:25 How Reasoning Helps with RAG

Are you wondering which AI model performs better: OpenAI’s O3 Mini or DeepSeek R1? In this head-to-head showdown, we put both models through real-world coding and reasoning tests, comparing their accuracy, speed, cost, context window, and overall performance.

🚀 What You’ll Learn in This Video:
✅ Coding Performance – Can these models generate functional, complex JavaScript code in a single pass?
✅ Reasoning Benchmarks – Which AI handles logical and problem-solving tasks better?
✅ Cost & Context Window – O3 Mini is twice as expensive as DeepSeek R1. Is it worth it?
✅ Misguided Attention Tests – Can these models correctly analyze tricky logic puzzles?
✅ API Reliability – Which model offers a more stable experience for developers?


📌 Which model do you think is better? Let me know your thoughts in the comments!

💬 Subscribe for more AI comparisons, deep dives, and hands-on tutorials!

LINKS:
https://github.com/cpldcpu/MisguidedAttention
https://openai.com/index/openai-o3-mini/
https://x.com/deedydas/status/1885440582103031940/photo/1
https://azure.microsoft.com/en-us/blog/deepseek-r1-is-now-available-on-azure-ai-foundry-and-github/
https://community.aws/content/2sJofoAecl6jVdDwVqglbZwKz2E/hosting-deepseek-r1-on-amazon-eks


RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

💡 Don't forget to Like, Subscribe & Hit the Bell 🔔 for more AI deep dives!

#O3Mini #AI #OpenAI #DeepSeekR1 #ArtificialIntelligence #GPT4 #AIBenchmarks #CodingAI #MachineLearning #AIComparison #LLM #ReasoningAI #AIResearch #O1Mini #AIEvolution #AIReview

OpenAI’s O3 Mini vs. DeepSeek R1: Which One Wins?

<p>Are you wondering which AI model performs better: OpenAI’s O3 Mini or DeepSeek R1? In this head-to-head showdown, we put both models through real-world coding and reasoning tests, comparing their accuracy, speed, cost, context window, and overall performance. 🚀 What You’ll Learn in This Video: ✅ Coding Performance – Can these models generate functional, complex JavaScript code in a single pass? ✅ Reasoning Benchmarks – Which AI handles logical and problem-solving tasks better? ✅ Cost &amp; Context Window – O3 Mini is twice as expensive as DeepSeek R1. Is it worth it? ✅ Misguided Attention Tests – Can these models correctly analyze tricky logic puzzles? ✅ API Reliability – Which model offers a more stable experience for developers? 📌 Which model do you think is better? Let me know your thoughts in the comments! 💬 Subscribe for more AI comparisons, deep dives, and hands-on tutorials! LINKS: https://github.com/cpldcpu/MisguidedAttention https://openai.com/index/openai-o3-mini/ https://x.com/deedydas/status/1885440582103031940/photo/1 https://azure.microsoft.com/en-us/blog/deepseek-r1-is-now-available-on-azure-ai-foundry-and-github/ https://community.aws/content/2sJofoAecl6jVdDwVqglbZwKz2E/hosting-deepseek-r1-on-amazon-eks RAG Beyond Basics Course: https://prompt-s-site.thinkific.com/courses/rag Let's Connect: 🦾 Discord: https://discord.com/invite/t4eYQRUcXB ☕ Buy me a Coffee: https://ko-fi.com/promptengineering |🔴 Patreon: https://www.patreon.com/PromptEngineering 💼Consulting: https://calendly.com/engineerprompt/consulting-call 📧 Business Contact: engineerprompt@gmail.com Become Member: http://tinyurl.com/y5h28s6h 💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off). Signup for Newsletter, localgpt: https://tally.so/r/3y9bb0 💡 Don't forget to Like, Subscribe &amp; Hit the Bell 🔔 for more AI deep dives! #O3Mini #AI #OpenAI #DeepSeekR1 #ArtificialIntelligence #GPT4 #AIBenchmarks #CodingAI #MachineLearning #AIComparison #LLM #ReasoningAI #AIResearch #O1Mini #AIEvolution #AIReview</p>

Deepseek

Curriculum

Related Courses

Data Analytics For Beginners

Simple Ways to Automate Your Job using ChatGPT

ChatGPT course for beginners

Learning AI Agents in Hindi

Select a lesson to begin

Study Notes

Need Help?