Inkling 2 Small

Thinking Machines Lab's 594B-parameter (17B active) MoE model with image input, on Tinker now and Apache 2.0 weights promised.

Thinking Machines Lab · Frontier/foundation models · model

Published in Feed

Overview

Inkling 2 Small is a mixture-of-experts model from Thinking Machines Lab announced on November 5, 2026, with 594B total and 17B active parameters, image input (no audio) and variable reasoning effort. It launched closed-weight through the company's Tinker platform, with full Apache 2.0 weights promised "next week" after external safety testing and red-teaming. Thinking Machines reports 31 on the Artificial Analysis Intelligence Index, 86.3% on SWE-Bench Pro v2 (Hard) and 81.6% on MMMU Pro; these are vendor-reported figures.

This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.

Key features

  • 594B total / 17B active parameter MoE with image input
  • Pretrained with up to 1M context; RL at 256K with compaction for longer tasks
  • Vendor-reported: AA Intelligence Index 31, SWE-Bench Pro v2 Hard 86.3%, DeepSWE v1.1 72.1%
  • Try in Tinker Playground; fine-tuning and sampling supported on Tinker
  • Apache 2.0 weights promised for the following week; other platforms "in the coming weeks"

Use cases

  • Fine-tuning a mid-size open-weight-bound model on Tinker
  • Agentic coding and long-horizon tasks with compaction
  • Vision-grounded reasoning (screenshots, design review)

Pricing

Per-token prices are on Tinker's pricing page (not stated in the announcement); weights to be free under Apache 2.0.

Pricing reflects the source record and may change. Confirm current terms with the provider.

Dates and sources

Released
5 Nov 2026
Record updated
6 Nov 2026
Record last checked
6 Nov 2026

Explore the Feed

Other entries filed under frontier/foundation models; inclusion does not imply equivalent features.

  • Muse Wonder

    Meta's most capable Muse models, with active memory and long-goal focus for agents, 1M context and $4/$20 per million tokens.

  • Rho-1

    Reka's 19B omni-reasoning model that handles text, images, video and robot actions in one network, in research preview.

  • Amazon Nova 3

    Amazon's third-generation Nova frontier model family, unveiled at an AWS keynote with a 1M-token context window and a dedicated agentic tool-use variant.

Browse the Feed