Average Ratings 0 Ratings

Total
ease
features
design
support

No User Reviews. Be the first to provide a review:

Write a Review

Average Ratings 1 Rating

Total
ease
features
design
support

Description

The Nex-N2-mini represents an innovative open-source agentic model centered on Agentic Thinking, specifically designed for practical productivity applications where rapid instruction adherence, immediate tool execution, and economical large-scale deployment are crucial. As a member of the Nex-N2 series, it aims to convert cognitive processes into actionable items that can be executed, verified, and refined, avoiding the compartmentalization of reasoning, tool usage, and environmental interaction. Utilizing the same cohesive Agentic Thinking framework found in Nex-N2-Pro, Nex-N2-mini seamlessly integrates the components of requirement comprehension, task strategizing, code execution, feedback from the environment, assessment, troubleshooting, and ongoing refinement into a singular, cohesive loop. This approach ensures that its cognitive methodology remains uniform across various tasks, including search activities, coding, and agentic tool interactions, by adhering to principles like goal breakdown, status monitoring, strategic modifications, and self-assessment. Furthermore, this cohesive framework enhances the model's performance in complex scenarios where coding is frequently combined with searching and tool utilization, making it exceptionally versatile and efficient.

Description

SWE-1.7 is Cognition’s most capable software engineering model, built to push frontier coding performance while reducing the cost of high-quality agentic rollouts. The model is designed for real-world software development tasks that require extended reasoning, codebase understanding, terminal use, debugging, feature work, migrations, and careful validation. It was trained from a Kimi K2.7 base and improved through Cognition’s reinforcement learning pipeline, including more stable training, stronger infrastructure, better data curation, and long-horizon task techniques. SWE-1.7 is especially optimized for asynchronous software engineering, where an agent needs to work through large projects over longer sessions instead of simply answering short prompts. Its self-compaction capabilities allow the model to summarize its working state and resume from that summary, helping it operate beyond the raw context window on multi-hour tasks. The model is also trained to balance task success with efficiency, using concise reasoning when possible while preserving deeper exploration for harder problems. SWE-1.7 tends to investigate codebases more thoroughly than its base model, reading files, running searches, probing edge cases, and experimenting before making changes. It is available in Devin through web, desktop, and CLI interfaces, with Cerebras serving support at 1000 TPS. SWE-1.7 gives developers and engineering teams a high-performance coding model for complex software projects at a more practical cost.

API Access

Has API No 

API Access

Has API No 

Screenshots View All

Screenshots View All

Integrations

.NET No 
C No 
Cerebras No 
Dart No 
Go No 
JSON No 
JavaScript No 
Kotlin No 
Kubernetes No 
Lua No 
MATLAB No 
Objective-C No 
PHP No 
Python No 
R No 
Rust No 
SQL No 
Scala No 
Terraform No 
XML No 

Integrations

.NET Yes 
C Yes 
Cerebras Yes 
Dart Yes 
Go Yes 
JSON Yes 
JavaScript Yes 
Kotlin Yes 
Kubernetes Yes 
Lua Yes 
MATLAB Yes 
Objective-C Yes 
PHP Yes 
Python Yes 
R Yes 
Rust Yes 
SQL Yes 
Scala Yes 
Terraform Yes 
XML Yes 

Pricing Details

Free
Free Trial No 
Free Version Yes 

Pricing Details

$20/month
Free Trial No 
Free Version Yes 

Deployment

Web-Based Yes 
On-Premises No 
iPhone App No 
iPad App No 
Android App No 
Windows No 
Mac No 
Linux No 
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 Yes 

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

Nex-AGI

Founded

2025

Country

China

Website

nex-agi.com

Vendor Details

Company Name

Cognition

Founded

2023

Country

United States

Website

cognition.com

Product Features

Product Features

Alternatives

MiniMax M2.5 Reviews

MiniMax M2.5

MiniMax

Alternatives

Nex-N2-Pro Reviews

Nex-N2-Pro

Nex-AGI
MiniMax M3 Reviews

MiniMax M3

MiniMax
SWE-2 Reviews

SWE-2

Cognition
Ring 2.6 Reviews

Ring 2.6

Ant Group
GPT-5.6 Sol Reviews

GPT-5.6 Sol

OpenAI