Thinking Machines: Inkling
- by thinkingmachines
- thinkingmachines/inkling
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,...
What the numbers mean
- Context window524,288 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 390,000 words, or 786 pages.
- Max output471,859 tokens
- The longest single reply it can write: about 350,000 words.
- Input price$1 per million tokens
- What you pay for everything the model reads. A 1,000-word prompt costs less than a cent.
- Output price$4.05 per million tokens
- What you pay for everything the model writes. Output usually costs more than input. A 500-word answer costs less than a cent.
- Modalitiestext, image, audio in, text out
- The kinds of content it accepts and the kinds it produces. A model that takes images in can read a screenshot; one that only puts text out cannot draw.
- Intelligence index12.5
- One score that combines several reasoning, knowledge and coding benchmarks. Higher is better. This model ranks 75 of the 96 scored models listed here.
Supported parameters
The settings you can pass with a request. A model that lists tools can call functions; one that lists structured_outputs can be held to a JSON schema.
frequency_penaltyinclude_reasoninglogit_bias