Thinking Machines Launches Inkling Multimodal MoE Models on OpenRouter
soumithchintala · x · 2026-08-22
Thinking Machines Lab has released Inkling and Inkling Small on OpenRouter, available for free use within agentic harnesses. Both are open-weight Mixture-of-Experts (MoE) models featuring native text, image, and audio input with a 1M context window.
- Inkling Small: 276B total parameters (12B active), optimized for efficiency in reasoning, coding, and RAG.
- Inkling: 975B total parameters (41B active), designed for general-purpose reasoning, agent systems, and multimodal analysis.
More from coding & agent
- Architects vs gardeners: developer argues AI's plan-maxxing obsession hurts good work — nptacek · 2026-10-16
- OpenRouter launches Armor beta to block out-of-policy agent tool calls before execution — dfinke · 2026-10-16
- Meta's coding-optimized open-weight Muse Spark Open lands on Modal with 1M context — AAAzzam · 2026-10-16
- Google rewrites its SRE book for the 10th anniversary, adding agentic-era guidance — RealGeneKim · 2026-10-16
- GRPO post-training collapses model distributions, clashing with long-horizon agents — zsakib_ · 2026-10-16
- Dev uses Claude to draw animated mascot GIFs frame-by-frame in code until usage runs out — jeremy_goldberg · 2026-10-16