Thinking Machines Lab has released Inkling, its first open-weights foundation model, giving developers and companies full access to customize and deploy it. Inkling is available now for fine-tuning through Tinker, while its complete weights can be downloaded as original and NVFP4 checkpoints for NVIDIA Blackwell systems.
Inkling is a Mixture-of-Experts transformer with 975 billion total parameters and 41 billion active during inference. It supports context windows of up to one million tokens and was pretrained from scratch on 45 trillion tokens spanning text, images, audio, and video. The model processes text, image, and audio inputs natively, with capabilities covering reasoning, coding, tool use, instruction following, visual analysis, speech transcription, and long-form audio understanding.
Developers can control Inkling’s thinking effort between 0.2 and 0.99 to balance output quality, latency, and token consumption. Thinking Machines says Inkling can match Nemotron 3 Ultra on Terminal Bench 2.1 while using roughly one-third as many generated tokens. The company positions it as a broad base for custom models rather than the highest-scoring general-purpose model overall.
Inkling scored 77.6% on SWE-bench Verified, 97.1% on AIME 2026, 87.2% on GPQA Diamond, and 73.5% on MMMU Pro. It can operate inside coding-agent harnesses, use changing tool schemas, and produce applications, structured artifacts, and longer projects through repeated refinement.
Tinker offers Inkling with 64K and 256K context options and a temporary 50% discount. The Inkling Playground provides a chat interface with integrated agentic web search, free for a limited period. API access is also available through Together, Fireworks, Modal, Databricks, and Baseten, with inference support across SGLang, vLLM, TokenSpeed, llama.cpp, and Hugging Face Transformers.
Thinking Machines is also previewing Inkling-Small, a 276-billion-parameter Mixture-of-Experts model with 12 billion active parameters. It approaches or surpasses Inkling on several reasoning, instruction-following, vision, and audio tests while targeting lower-cost and lower-latency workloads. Its full weights will follow after testing is completed.
Thinking Machines Lab is an AI research and product company founded by former OpenAI CTO Mira Murati. Inkling extends the company’s Tinker customization platform and is intended to serve as the reasoning layer behind its previously previewed real-time voice and vision systems. The release marks the start of a planned family of customizable models across multiple sizes.