Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...
thinkingmachines/inklingInkling is an API model from thinkingmachines, released on Jul 17, 2026, with a context window of 524,288 tokens, pricing of $1 per million input tokens and $4.05 per million output tokens, the apache-2.0 license, 63,319 Hugging Face downloads in the last 30 days. It accepts audio, image, text input and produces text output.
At listed prices, a request with 10,000 input tokens and 1,000 output tokens costs about $0.014.
Specs are sourced from OpenRouter and were last checked on Oct 16, 2026. Always confirm current pricing and limits with the provider before production use.
Inkling supports a context window of 524,288 tokens.
Inkling is listed at $1 per million input tokens and $4.05 per million output tokens on OpenRouter.
Inkling was published on Jul 17, 2026.
Inkling accepts audio, image, text input and produces text output.