Inkling
Open weights, ready to tinker
Inkling is an open-weight multimodal mixture-of-experts model release from Thinking Machines Lab, with 975B total parameters and 41B active parameters. It supports text, image, and audio inputs and up to a 1M-token context window.
Pricing
Serverless inference beta, 256K context; currently beta and not recommended for intensive production use. Training/sampling pricing is separately listed: 64K Inkling prefill $1.87 (cached $0.374), sample $4.68, train $5.61 per 1M tokens; 256K train $11.23.
Official Thinking Machines Lab pricing pages list Inkling serverless inference (beta) at $1.00 per 1M input tokens, $0.17 per 1M cached input tokens, and $4.05 per 1M output tokens. The pricing page dates these rates October 19, 2026. This records inference pricing, not training/sampling rates.
Model Intelligence
Recent stories
Thinking Machines released Inkling-Small, a 276B-parameter MoE with 12B active parameters, multimodal inputs, and a 1M-token context window. Providers added day-zero vLLM, SGLang, Modal, and gateway support.
Inkling's 1-bit GGUF ran in llama.cpp at 30–40 TPS, and TokenSpeed added day-zero support with a flat KV cache pool. Arena posts put Inkling #10 among open models in frontend code and text, while docs drew scrutiny.
Thinking Machines released Inkling with Apache 2.0 weights, 975B parameters, 41B active parameters, text/image/audio support, and up to 1M context. vLLM, SGLang, Modal, Databricks, and Vercel added day-zero support.