AI Desk · AI FingerprintingWithdrawn *

Thinking Machines: Inkling (batch)

thinkingmachines/inkling:batch · Thinking MachinesTokenizer lineage measured

Tokenizer lineage (measured): GPT
Entered catalogue: 17 July 2026
Measurement: Variant: inherits its base model’s measurement
Evidence confidence: Very high

Why very high: inherited from thinkingmachines/inkling: a serving variant shares its base model's tokenizer.

Evidence

✓ inherited from thinkingmachines/inkling: a serving variant shares its base model's tokenizer

Compare with Thinking Machines: Inkling

Report a correction

This entry is a serving variant of Thinking Machines: Inkling. A variant shares its base model's tokenizer by construction, so the measurement lives on the base record and this page inherits it.

Identity statement

Thinking Machines: Inkling (batch) is Thinking Machines's model. Its measured tokenizer sits with the GPT group, which is evidence that it builds on the GPT tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Thinking Machines's authorship of the model itself.

What we checked

Four different kinds of evidence, and what each one showed

We checked	What we found	Where it came from
How it counts tokens	Not measured yet	we measured it
How its API is set up	A combination of settings no other listing in the catalogue uses	api_a3b65589
How much it can read and write	Reads up to 524,288 tokens at onceOpenRouter's listing shows 471,859 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum.	its own listing
Whether it thinks before answering	Reasons when asked to, at max, high, medium, low, minimal, none, high by default	its own listing

Declared record

What the catalogue claims about this model

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,...

Modalities: text+image+audio->text
Declared tokenizer: Other
Prompt price: $1.00 / M tokens
Completion price: $4.05 / M tokens

Supported parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltystoptemperaturetool_choicetoolstop_ktop_p

defaults: {"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}

Catalogue entry Weights on Hugging Face

History

Every observation, kept as taken

17 July 2026Enters the OpenRouter catalogue with no declared family.

* Thinking Machines: Inkling (batch) no longer appears in the OpenRouter catalogue, first absent from the snapshot of 5 October 2026. The record stays because the measurements above were real when they were taken and this address has been published.