Inkling Small

About

Inkling Small is Thinking Machines’ open-weight multimodal mixture-of-experts model, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family. The model accepts text, image, and audio inputs and produces text. Listed capabilities include vision, reasoning, and tools. Its context window is 524,288 tokens, and it can generate up to 262,144 tokens. Pricing is USD 0.45 per 1M input tokens and USD 1.2 per 1M output tokens. Inkling Small was released on 2026-07-30. Its Hugging Face identifier is thinkingmachines/Inkling-Small, and its model ID is thinkingmachines/inkling-small. The listed family is thinkingmachines; Thinking Machines is its maker and lab. The combination of open weights, multimodal inputs, and tool support gives product teams concrete factors to assess when considering it for reasoning or tool-using workflows.

Who it is for

Inkling Small suits teams considering an open-weight model for reasoning or tool-using workflows. Its text, image, and audio inputs may also fit projects that need multimodal input, with listed per-token prices for budgeting.

Details

Lab

Thinking Machinesopenrouter.ai · 3 Oct 2026

Context

524Kopenrouter.ai · 3 Oct 2026

Input price

$0.45 / 1Mopenrouter.ai · 3 Oct 2026

Output price

$1.2 / 1Mopenrouter.ai · 3 Oct 2026

Max output

262,144 tokensopenrouter.ai · 3 Oct 2026

Inputs

text, image, audioopenrouter.ai · 3 Oct 2026

Open weights

Yesopenrouter.ai · 3 Oct 2026

Listed on Inferse

• Newest Models in 2026466 listed
• Longest-Context Models in 2026466 listed
• Cheapest Language Models in 2026444 listed
• Models with Tool Calling in 2026398 listed
• Reasoning Models in 2026332 listed
• Vision Language Models in 2026295 listed
• Open-Weight Models in 2026178 listed
• Thinking Machines Models: Pricing per 1M Tokens and Context (2026)4 listed

Sources

• openrouter.ai/thinkingmachines/inkling-small· checked 3 Oct 2026