Thinking Machines

thinking-machines/ · 1 model

Access 1 Thinking Machines model through AnonRouter's privacy-first gateway, including Inkling. Compare pricing, context windows, and capabilities across Thinking Machines's text routes — every request anonymized, with no payload logging.

Models

Modalities

Text

From (input)

$2.3375

per 1M tokens

Max context

Private routes

1 / 1

not anonymous-only

Catalog by modality

1 routes

Text1

Thinking Machines models1

Inkling

thinking-machines/inkling

Private

Inkling is a general-purpose multimodal model from Thinking Machines Lab that accepts text, image, and audio inputs and generates text. It is a 66-layer sparse MoE (975B total / 41B active) with hybrid local/global attention, 1M context, and variable thinking effort — suited for chat, coding, tool use, and agentic workflows. Video input is not supported on Venice.

Private|1M context|$2.3375/M input|$5.85/M output