Thinking Machines Unveils Inkling Model with Multimodal Reasoning.

@LiorOnAI· July 15, 2026 View original

Summary

Thinking Machines has launched a new model, Inkling, featuring full weights availability, native reasoning across text, image, and audio, and a 1M-token context window. Built with a Mixture-of-Experts architecture, Inkling supports fine-tuning on Tinker and offers strong agentic coding and tool use capabilities.

Thinking Machines has announced the release of its new AI model, Inkling, which comes with its full weights openly available. This model is designed with a Mixture-of-Experts architecture, boasting 975 billion total parameters with 41 billion active, and offers native reasoning capabilities across text, images, and audio data. A key feature is its expansive context window, supporting up to one million tokens, alongside a controllable reasoning effort mechanism. Inkling is engineered for efficiency, promising lower token usage while maintaining comparable performance. It supports fine-tuning from its launch day via the Tinker platform and is noted for its robust agentic coding and tool-use functionalities. The model is compatible with major inference platforms, and a smaller version, Inkling-Small, is anticipated in the future, all trained from scratch by Thinking Machines.

Why it matters

This new open-weight, multimodal model provides developers with a powerful and flexible foundation for building advanced AI applications, potentially reducing development costs and accelerating innovation in agentic systems and diverse data processing.

How to implement this in your domain

  1. 1Access the full weights to integrate Inkling into custom AI development projects.
  2. 2Utilize Inkling's multimodal reasoning for applications requiring understanding of text, images, and audio.
  3. 3Experiment with the Mixture-of-Experts architecture to optimize performance for specific tasks.
  4. 4Leverage Inkling's agentic coding and tool-use features to automate complex workflows.

Who benefits

Software DevelopmentAI ResearchMedia & EntertainmentRoboticsData Science

Key takeaways

  • Inkling is a new open-weight, multimodal AI model from Thinking Machines.
  • It features a Mixture-of-Experts architecture and a 1M-token context window.
  • The model supports native reasoning across text, image, and audio data.
  • Inkling offers strong agentic coding and tool-use capabilities for developers.

Original post by @LiorOnAI

"New model from Thinking Machines: - Full weights available - Native text, image, and audio reasoning - 975B total parameters, 41B active - Mixture-of-Experts architecture - Up to 1M-token context window - Controllable reasoning effort - Lower token use at similar performance - Fi…"

View on X

Originally posted by @LiorOnAI on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses