DEV Community

#deepseek

DeepSeek is a Chinese artificial intelligence company that has developed an open-source AI model, DeepSeek-R1, which rivals leading models like OpenAI's o1 in performance, yet was created in under two months at a cost of less than $6 million, significantly lower than its competitors.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
How I Tested Every Major Multimodal AI Model in 2026 — And Which One Actually Saved My Wallet

How I Tested Every Major Multimodal AI Model in 2026 — And Which One Actually Saved My Wallet

Comments
6 min read
I Tested DeepSeek V4 Flash and GPT-4o Side by Side — Here's the p99 Latency Truth

I Tested DeepSeek V4 Flash and GPT-4o Side by Side — Here's the p99 Latency Truth

Comments
7 min read
The Indie Hacker's Guide to Picking a Multimodal AI in 2026 (Without Going Broke)

The Indie Hacker's Guide to Picking a Multimodal AI in 2026 (Without Going Broke)

1
Comments
9 min read
Quick Tip: Benchmark AI Model Speeds in Under 10 Minutes

Quick Tip: Benchmark AI Model Speeds in Under 10 Minutes

1
Comments
8 min read
How I Broke Free from OpenAI’s Walled Garden — A Practical Guide for 2026

How I Broke Free from OpenAI’s Walled Garden — A Practical Guide for 2026

1
Comments
5 min read
Unlocking Agentic Workflows: Harnessing the Power of Local LLMs

Unlocking Agentic Workflows: Harnessing the Power of Local LLMs

Comments
3 min read
I Replaced GPT-5.5 with DeepSeek V4 Flash and Cut My API Bill by 97%

I Replaced GPT-5.5 with DeepSeek V4 Flash and Cut My API Bill by 97%

Comments
5 min read
The Developer's Guide to Slashing Your AI API Bill by 95%

The Developer's Guide to Slashing Your AI API Bill by 95%

1
Comments 1
7 min read
DeepSeek vs Qwen vs Kimi vs GLM: My 6-Month Stress Test on 4 Chinese AI Giants

DeepSeek vs Qwen vs Kimi vs GLM: My 6-Month Stress Test on 4 Chinese AI Giants

1
Comments
8 min read
DeepSeek's new open models give everyone a million-word memory by default

DeepSeek's new open models give everyone a million-word memory by default

Comments 1
3 min read
Enterprise vs Startup AI APIs — The Architectural Decision Nobody Talks About

Enterprise vs Startup AI APIs — The Architectural Decision Nobody Talks About

Comments
3 min read
400 Million Tokens Burned Overnight

400 Million Tokens Burned Overnight

Comments
4 min read
I Run DeepSeek on Claude Code — How I Swap Models by Changing Only One File

I Run DeepSeek on Claude Code — How I Swap Models by Changing Only One File

Comments
2 min read
DeepSeek's DSpark Brings Speculative Decoding Back Into the Spotlight — Here's What Developers Need to Know

DeepSeek's DSpark Brings Speculative Decoding Back Into the Spotlight — Here's What Developers Need to Know

1
Comments 1
4 min read
The Developer's Guide to Trimming AI API Costs Without Crying

The Developer's Guide to Trimming AI API Costs Without Crying

6
Comments 2
7 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.