Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Introducing DeepSeek-V3.2-Exp, our newest experimental model derived from V3.1-Terminus, featuring the innovative DeepSeek Sparse Attention (DSA) that enhances both training and inference speed for lengthy contexts. This DSA mechanism allows for precise sparse attention while maintaining output quality, leading to improved performance for tasks involving long contexts and a decrease in computational expenses. Benchmark tests reveal that V3.2-Exp matches the performance of V3.1-Terminus while achieving these efficiency improvements. The model is now fully operational across app, web, and API platforms. Additionally, to enhance accessibility, we have slashed DeepSeek API prices by over 50% effective immediately. During a transition period, users can still utilize V3.1-Terminus via a temporary API endpoint until October 15, 2025. DeepSeek encourages users to share their insights regarding DSA through our feedback portal. Complementing the launch, DeepSeek-V3.2-Exp has been made open-source, with model weights and essential technology—including crucial GPU kernels in TileLang and CUDA—accessible on Hugging Face. We look forward to seeing how the community engages with this advancement.
Description
Qwen3.8-Flash-Next represents an open-weight multimodal Mixture-of-Experts architecture and serves as an initial glimpse into the design intended for Qwen4. This model strategically enhances attention mechanisms, residual pathways, embeddings, and optimization techniques to boost its capabilities, improve computational efficiency, expand model capacity, and ensure training stability. Its innovative hybrid architecture merges Gated DeltaNet, which adeptly compresses past information, with Qwen Sparse Attention, enabling the selection of significant context at a micro-block level to lessen both attention and indexing costs associated with lengthy sequences. The Gated Residual feature broadens the residual pathway into four streams, dynamically managing the flow of information across different layers. Additionally, the N-gram Embedding integrates large-scale local-pattern memory with minimal added computation per token, and it can be transferred to host memory for further efficiency. The model is structured around a 125B-parameter main network supplemented by 51B parameters dedicated to N-gram embeddings, activating only 6B parameters for each token processed. This sophisticated framework highlights the ongoing advancements in machine learning architectures, setting a promising stage for future developments.
API Access
Has API
Yes
API Access
Has API
Yes
Integrations
Hugging Face
Yes
Alibaba Cloud
No
Alibaba Cloud Model Studio
No
Cherry Studio
No
Cline
No
ClinePass
No
DeepSeek
Yes
Happy Shrimp 1.0
No
Hermes Agent
No
Model Context Protocol (MCP)
No
Integrations
Hugging Face
Yes
Alibaba Cloud
Yes
Alibaba Cloud Model Studio
Yes
Cherry Studio
Yes
Cline
Yes
ClinePass
Yes
DeepSeek
No
Happy Shrimp 1.0
Yes
Hermes Agent
Yes
Model Context Protocol (MCP)
Yes
Pricing Details
Free
Open source
Free Trial
No
Free Version
Yes
Pricing Details
$2 per 1M (input)
Free Trial
No
Free Version
No
Deployment
Web-Based
Yes
On-Premises
Yes
iPhone App
No
iPad App
No
Android App
No
Windows
Yes
Mac
Yes
Linux
Yes
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
DeepSeek
Founded
2023
Country
China
Website
deepseek.com
Vendor Details
Company Name
Alibaba
Founded
1999
Country
China
Website
qwen.ai/blog