Ring-2.6-1T: Free inclusionAI Thinking Model on Kilo Code

LinkKilo CodeTool

inclusionAI has released Ring-2.6-1T, a 1T-parameter-scale thinking model featuring 63 billion active parameters. Optimised for coding agents, the model is accessible free of charge via Kilo Code and OpenRouter.

Key points

  1. 1T-parameter scale architecture with 63B active parameters tailored for agent workflows
  2. Extensive context window of 262,144 tokens and up to 65,536 completion tokens
  3. Features function calling, tool choice, structured JSON outputs, and reasoning tokens
  4. Offered at zero cost ($0.00 per 1M input and output tokens) with content moderation disabled
  5. Usable via Kilo Code across VS Code, JetBrains IDEs, and command-line interfaces

Why it matters

Developers gain access to an extended-thinking model with a wide context window for agentic software development without incurring API costs.

Analysis

By deploying 63B active parameters within a 1T-scale footprint, Ring-2.6-1T is designed to deliver extended reasoning while maintaining operational efficiency for tool use and coding tasks. While its structural allowances—such as a 65k token completion limit—are substantial, community performance rankings across Kilo Code's operational modes are still pending.

Mentioned links

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Link:kilo.ai

    Kilo: Open Source AI Coding Agent for IDEs, CLI, and Cloud

    Kilo is an MIT-licensed, open-source AI coding assistant designed to operate across VS Code, JetBrains IDEs, CLI environments, and cloud agents. It provides access to over 500 models at cost without inference markup, supporting bring-your-own-keys and local models.

    AI & LLMs· Tool

  • Link:Poolside

    Laguna-S-2.1: Open-Source MoE Model by Poolside for Agentic Coding

    Poolside has released Laguna-S-2.1, a Mixture-of-Experts language model featuring 118B total parameters with approximately 8B activated parameters per token. Targeted at software engineering and long-horizon agentic workflows, the model is available under the permissive OpenMDW-1.1 license.

    AI & LLMs· Tool

  • Article:Thinking Machines Lab

    Thinking Machines Lab Releases Open-Weights Model Inkling

    Thinking Machines Lab has introduced Inkling, an open-weights Mixture-of-Experts model featuring 975B total parameters (41B active) and a 1M token context window. It is built as a generalist foundation optimized for customization via the Tinker platform.

    AI & LLMs· Announcement

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.