# Thinking Machines Lab launches Inkling, a 975B-parameter open model

> Thinking Machines Lab released Inkling, a 975B-parameter open-weights model, on 15 July.

*Mira Murati's start-up pitches its first open-weights release as a base for fine-tuning, not a frontier leader.*

By Behzad Hosseini · FeaturedDaily
Canonical: https://featureddaily.com/news/thinking-machines-lab-launches-inkling-a-975b-parameter-open-model

**What happened:** Thinking Machines Lab, founded by former OpenAI CTO Mira Murati after a $2 billion seed round, has released its first open-weights model, [Inkling](https://thinkingmachines.ai/news/introducing-inkling). Weights are on Hugging Face.

**The numbers:** Inkling is a mixture-of-experts transformer with 975 billion total parameters, 41 billion active per token, 256 routed experts per MoE layer with 6 active at a time. It handles up to 1 million tokens of context and was trained on 45 trillion tokens of text, images, audio and video.

**The details:** A smaller variant, Inkling-Small, runs 12 billion active parameters (276 billion total); its full weights will follow once testing finishes. On the lab's own benchmarks, Inkling scored 63.8% on Terminal Bench 2.1, 97.1% on AIME 2026, 87.2% on GPQA Diamond, 77.6% on SWE-bench Verified and 78.0% on the FORTRESS adversarial safety test. The lab says it hits those reasoning scores at roughly a third of competitors' token cost.

**Who's affected:** Inkling is available through Thinking Machines' Tinker fine-tuning platform, currently at a 50% discount, and via APIs from Together AI, Fireworks, Modal, Databricks and Baseten.

**Why it matters:** Thinking Machines isn't claiming the top spot. It's pitching Inkling as raw material for companies to customise.

**In their words:** "Inkling is not the strongest overall model available today, open or closed. Instead, a combination of qualities makes it a good open-weights base for customization," the lab said in its launch post.

**The rivals:** The release lands the same week as Moonshot's 2.8-trillion-parameter Kimi K3, as open-weights models from both the US and China keep narrowing the gap with closed frontier systems.

**What's next:** Watch for Inkling-Small's full weights once Thinking Machines finishes testing it.

## Key takeaways

- Inkling has 975B total, 41B active parameters, 1M-token context
- Available via Tinker, Together AI, Fireworks, Modal, Databricks, Baseten
- Launch coincides with Moonshot's 2.8-trillion-parameter Kimi K3

## Sources

- [Inkling: our open-weights model](https://thinkingmachines.ai/news/introducing-inkling) — Thinking Machines Lab, 2026-07-15