Inkling 2 Mini

Inkling 2 Mini

Thinking Machines Lab
SWE-2 Flash

SWE-2 Flash

Cognition
5.0 out of 5 stars
Inkling 2 Mini SWE-2 Flash

Related Products

  • LTX
    4.4 out of 5 stars 182 Ratings
    Visit Website for LTX
  • Gemini platform
    4.3 out of 5 stars 1,178 Ratings
    Visit Website for Gemini platform
  • IONOS Cloud GPU Servers
    4.6 out of 5 stars 45,816 Ratings
    Visit Website for IONOS Cloud GPU Servers
  • RaimaDB
    4.8 out of 5 stars 12 Ratings
    Visit Website for RaimaDB
  • Nexo
    4.4 out of 5 stars 18,841 Ratings
    Visit Website for Nexo
  • 10Duke
    4.8 out of 5 stars 8 Ratings
    Visit Website for 10Duke
  • Google Cloud Speech-to-Text
    4.5 out of 5 stars 446 Ratings
    Visit Website for Google Cloud Speech-to-Text
  • RetailEdge
    4.8 out of 5 stars 201 Ratings
    Visit Website for RetailEdge
  • Compute with Hivenet
    5.0 out of 5 stars 4 Ratings
    Visit Website for Compute with Hivenet
  • Careerminds
    4.9 out of 5 stars 46 Ratings
    Visit Website for Careerminds
Inkling 2 Mini:

About

Inkling 2 Mini is an open-weight artificial intelligence model developed by Thinking Machines Lab for advanced reasoning, autonomous coding, tool use, and efficient local inference. The model uses a looped Mixture-of-Experts transformer architecture with 26.4 billion total parameters and 3.4 billion active parameters, repeatedly processing information through its middle layers to improve reasoning performance. Its optimized architecture enables the model to complete complex tasks using fewer reasoning tokens while maintaining computational efficiency. Inkling 2 Mini supports agentic software development, web research, visual understanding, document analysis, and multistep problem-solving workflows. With a memory footprint of approximately 20GB, the model can operate locally on compatible laptops and desktop computers, including Macs with at least 32GB of RAM.
SWE-2 Flash:

About

SWE-2 Flash is an AI coding model developed by Cognition to provide fast, cost-efficient software engineering capabilities for autonomous development agents. Built on Thinking Machines' Inkling-Small foundation model, it uses mid-training and reinforcement learning to improve coding performance, reasoning, and task execution. The model supports software development activities such as code generation, code reviews, feature development, documentation updates, and automated engineering workflows. SWE-2 Flash generates approximately 200 tokens per second, making it three times faster and five times less expensive than the larger SWE-2 model. Its 276-billion-parameter mixture-of-experts architecture activates approximately 12 billion parameters during inference to balance performance and computational efficiency. SWE-2 Flash is available through Devin Desktop and CLI, with Cognition also developing a secure model-weight sharing program for trusted research and enterprise partners.
Inkling 2 Mini:

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported
SWE-2 Flash:

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported
Inkling 2 Mini:

Audience

AI developers, machine learning engineers, software engineers, AI researchers, autonomous agent developers, and organizations seeking open-weight reasoning models for local inference, agentic coding, tool integration, and customizable AI applications
SWE-2 Flash:

Audience

Software developers, AI coding assistant users, software engineering teams, DevOps professionals, autonomous agent developers, AI researchers, enterprise development organizations, and cybersecurity researchers seeking fast, cost-efficient AI coding, automated code reviews, feature implementation, software maintenance, technical reasoning, and agentic development workflows
Inkling 2 Mini:

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported
SWE-2 Flash:

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported
Inkling 2 Mini:

API

Offers API Supported
SWE-2 Flash:

API

Offers API Not Supported
Inkling 2 Mini:

Screenshots and Videos

SWE-2 Flash:

Screenshots and Videos

Inkling 2 Mini:

Pricing

$0.15 per 1M input tokens
$0.15 per 1M input tokens, $0.50 per 1M output tokens, and $0.015 per 1M cache hit tokens
Free Version Not Supported
Free Trial Not Supported
SWE-2 Flash:

Pricing

$20/month
Free Version Supported
Free Trial Not Supported
Inkling 2 Mini:

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software
SWE-2 Flash:

Reviews/Ratings

Overall 5.0 / 5
ease 5.0 / 5
features 5.0 / 5
design 5.0 / 5
support 5.0 / 5
SWE-2 Flash:

Pros & Cons from Real Users

Pros

  • This is the kind of model I would use all day for normal engineering work. It is fast enough that it does not feel like I am waiting on the model, but it is still strong enough for feature work, code review, docs, automations, and debugging. The speed is probably the biggest win. Cognition says it runs at around 200 tokens per second versus about 60 for SWE-2, and that difference matters a lot once an agent starts iterating through files and tools. The cost-performance balance is also really good. It is one-fifth the price of SWE-2, while scoring 45.5 on FrontierCode 1.1 Main, 60.1 on DeepSWE 1.1, and 89.9 on SWE-Bench Pro v2 Hard.

Cons

  • My main complaint is that it is not the model I would choose for the hardest repo-wide work. SWE-2 still has a noticeable edge on some tougher benchmarks, so I would move up when the task really needs it.
Inkling 2 Mini:

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported
SWE-2 Flash:

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported
Inkling 2 Mini:

Company Information

Thinking Machines Lab
Founded: 2025
United States
thinkingmachines.ai/
SWE-2 Flash:

Company Information

Cognition
Founded: 2023
United States
cognition.com
Inkling 2 Mini:

Alternatives

GPT-6 Luna

GPT-6 Luna

OpenAI
5.0 out of 5 stars
SWE-2 Flash:

Alternatives

Gemini 4 Neon

Gemini 4 Neon

Google
5.0 out of 5 stars
Inkling 2 Mini:
SWE-2 Flash:
GPT-6.2 Astra

GPT-6.2 Astra

OpenAI
5.0 out of 5 stars
Inkling 2 Mini:
Kimi K3.1 Pro

Kimi K3.1 Pro

Moonshot AI
5.0 out of 5 stars
SWE-2 Flash:
GPT-6.2 Sol

GPT-6.2 Sol

OpenAI
5.0 out of 5 stars
Inkling 2 Mini:
Inkling 2 Small

Inkling 2 Small

Thinking Machines Lab
SWE-2 Flash:
MAI Code 2 Flash

MAI Code 2 Flash

Microsoft AI
Inkling 2 Mini:
Inkling-Small

Inkling-Small

Thinking Machines Lab
5.0 out of 5 stars
SWE-2 Flash:
Inkling 2 Mini

Inkling 2 Mini

Thinking Machines Lab
Inkling 2 Mini:

Categories

SWE-2 Flash:

Categories

AI Coding Models Supported
AI Models Supported
Inkling 2 Mini:

Integrations

.NET Not Supported
C# Not Supported
Devin Desktop Not Supported
Go Not Supported
HTML Not Supported
JSON Not Supported
JavaScript Not Supported
Kotlin Not Supported
MATLAB Not Supported
Model Context Protocol (MCP) Supported
Objective-C Not Supported
PHP Not Supported
Ruby Not Supported
SQL Not Supported
Scala Not Supported
Solidity Not Supported
Terraform Not Supported
Tinker Supported
TypeScript Not Supported
XML Not Supported
SWE-2 Flash:

Integrations

.NET Supported
C# Supported
Devin Desktop Supported
Go Supported
HTML Supported
JSON Supported
JavaScript Supported
Kotlin Supported
MATLAB Supported
Model Context Protocol (MCP) Not Supported
Objective-C Supported
PHP Supported
Ruby Supported
SQL Supported
Scala Supported
Solidity Supported
Terraform Supported
Tinker Not Supported
TypeScript Supported
XML Supported
Inkling 2 Mini:
Claim Inkling 2 Mini and update features and information
Claim Inkling 2 Mini and update features and information
SWE-2 Flash:
Claim SWE-2 Flash and update features and information
Claim SWE-2 Flash and update features and information