Menu

#DeepSeek

400 posts

Feed·
20 of 400 posts
Strata walkthrough is live: why DeepSeek vanished and stars doubled anyway
📰
0Read More

Strata walkthrough is live: why DeepSeek vanished and stars doubled anyway

DEV Community: github·InApp·about 15 hours ago
#MjLDKe3b
#devtogithub#technology#devto#dev#repo

I spent last weekend staring at GitHub star graphs instead of sleeping. When DeepSeek's repo went...

15s
How to Run DeepSeek Privately on Your Android Phone in 2026 (R1 Distill GGUF, Instead of the DeepSeek App)
📰
0Read More

How to Run DeepSeek Privately on Your Android Phone in 2026 (R1 Distill GGUF, Instead of the DeepSeek App)

DEV Community: android·Mohammed Ali Chherawalla·4 days ago
#ky7MBXjy
#devtoandroid#devto#dev#deepseek#phone

DeepSeek's app stores chats in China and trains on them. Run the MIT-licensed R1 distills on your Android phone instead, offline, with no account.

15s
DeepSeek Opens Its App's Search, Files and Voice to Developers, With Search at 75 Cents per 1,000 Queries
🖼️
0Read More

DeepSeek Opens Its App's Search, Files and Voice to Developers, With Search at 75 Cents per 1,000 Queries

#webpronews#news#deepseek#search#speech

DeepSeek put the search, file parsing, link reading and speech features of its consumer app into its API on Friday. Its web search fee is less than a tenth of what OpenAI and Anthropic list.

15s
DeepSeek V4.1 Flash API: Clean and Tag 10,000 Comments, and What It Costs
🖼️
0Read More

DeepSeek V4.1 Flash API: Clean and Tag 10,000 Comments, and What It Costs

DEV Community: datascience·EveryInfra·11 days ago
#C5W1yZ58
#devtodatascience#science#devto#dev#comments

We pulled 907 real comments and ran DeepSeek V4.1 Flash API on 602. Output is 74-83% of the model bill. Short codes and off-peak hours cut it by 72-79%.

15s
DeepSeek API Pricing in 2026: What Cache Hits and 1M Context Really Cost
📰
0Read More

DeepSeek API Pricing in 2026: What Cache Hits and 1M Context Really Cost

DEV Community: api·Lee Jiang·11 days ago
#NZNW7xmj
#devtoapi#devto#dev#deepseek#cache

A production cost model for DeepSeek Flash and Pro, with peak-hour math, cache optimization, OpenAI-compatible setup, and routing checks.

15s
How to Use DeepSeek Through an OpenAI-Compatible API
📰
0Read More

How to Use DeepSeek Through an OpenAI-Compatible API

DEV Community: api·Lee Jiang·11 days ago
#MMS6PYk1
#devtoapi#devto#dev#model#openai

Python and Node.js setup, model routing, failure checks, and production safeguards for calling DeepSeek through an OpenAI-compatible gateway.

15s
DeepSeek V4.1 Flash 1017 Ultrafast now available on AI Gateway - Vercel
📰
0Read More

DeepSeek V4.1 Flash 1017 Ultrafast now available on AI Gateway - Vercel

Vercel News·Jerilyn Zheng·12 days ago
#EovRWIxH
#vercel#deepseek#flash#ultrafast#gateway

Call DeepSeek V4.1 Flash 1017 Ultrafast through Vercel AI Gateway with one API key, no provider account, spend tracking, and request traces

15s
AI Gateway adds DeepSeek Search and Fetch tools - Vercel
📰
0Read More

AI Gateway adds DeepSeek Search and Fetch tools - Vercel

Vercel News·Jerilyn Zheng·13 days ago
#vJ4YBbnp
#vercel#search#deepseek#fetch#model

AI Gateway now supports DeepSeek Search and Fetch. Search the web and retrieve page content with any tool-calling model and one API key.

15s
Can You Run Inkling 2 Small Locally? 17B Active, but Plan on 200 GB
🖼️
0Read More

Can You Run Inkling 2 Small Locally? 17B Active, but Plan on 200 GB

DEV Community: opensource·Alan West·13 days ago
#tMgxNuG2
#devtoopensource#devto#dev#inkling#small

One 128 GB DGX Spark won't hold the 594B weights due next week, and DeepSeek's 552B model, out now, beats it on eight of the nine coding benchmarks they share.

15s
Llama vs Qwen vs DeepSeek: How Much VRAM Do You Need to Self-Host?
📰
0Read More

Llama vs Qwen vs DeepSeek: How Much VRAM Do You Need to Self-Host?

DEV Community: ai·Thea Lauren·14 days ago
#kWfWxuSp
#devtoai#devto#dev#model#vram

A practical VRAM and GPU sizing guide for hosting Llama 3, Qwen 3 and DeepSeek V3/R1 on bare-metal servers.

15s
0Read More

DeepSeek open-sources a super-agent coding prototype: one Router, many Workers, minimal human attention

On October 31, the DeepSeek Harness team published a design essay, Exploring Super-agent Design: Towards a More Autonomous Agent System, alongside an MIT-licensed research prototype called dsh-superagent-prototype. The idea is not a new foundation model.…

15s
The Cheap Half of Reading
📰
0Read More

The Cheap Half of Reading

DEV Community: api·NIA·17 days ago
#BUaWkgqK
#devtoapi#devto#dev#deepseek#model

DeepSeek's new model is built around the fact that agents read far more than they write, and priced around a rule that has nothing to do with the architecture

15s
DeepSeek Super-agent: A Proactive Open-Source Coding Agent Prototype — What It Actually Is, and What It Is Not Yet
📰
0Read More

DeepSeek Super-agent: A Proactive Open-Source Coding Agent Prototype — What It Actually Is, and What It Is Not Yet

DEV Community: deeplearning·Paul Lovelace·18 days ago
#lKPnzwl8
#devtodeeplearning#education#devto#dev#agent

On 31 October 2026, DeepSeek's Harness team published dsh-superagent, an open-source research...

15s
DeepSeek wants to steal Claude Code and Codex’s lunch with an AI Super Agent that does not wait around
🖼️
0Read More

DeepSeek wants to steal Claude Code and Codex’s lunch with an AI Super Agent that does not wait around

#digitaltrends#technology#code#deepseek#agent

DeepSeek’s new Super-Agent aims to spot coding problems and suggest solutions without waiting for developers to prompt it, putting it in the same conversation as Claude Code and OpenAI Codex.

15s