Inkling 2 Mini is an open-weight multimodal looped transformer from Thinking Machines Lab, with 3.4B active parameters out of 26.4B total (MoE). Its middle layers run three times with shared...
With CoreAI, you can start chatting with Thinking Machines: Inkling 2 Mini instantly — no separate subscription needed. CoreAI lets you chat with Thinking Machines: Inkling 2 Mini alongside 300+ other AI models from Thinkingmachines and other providers like OpenAI, Anthropic, Google, Meta, and more.
Among the 423 chat models on CoreAI, Thinking Machines: Inkling 2 Mini ranks #51 by context window — 1.0M tokens, roughly 786,432 words or 1,573 pages of text in a single conversation. On price, it is the #54 cheapest of 147 budget-tier models by input cost. Released 2026-11-21, it is one of the 1 newest additions to the catalog. It supports step-by-step reasoning (thinking mode) and accepts image input.
Every model in this table is available on CoreAI — open the web app and run the same prompt through Thinking Machines: Inkling 2 Mini and Thinking Machines: Inkling 2 Small side by side to judge with your own eyes.
A typical question (about 1,000 tokens in, 500 out) runs $0.00022 on Thinking Machines: Inkling 2 Mini's raw per-token rates; a heavy session with a 50K-token document costs about $0.005. On CoreAI you don't juggle these numbers — one subscription covers Thinking Machines: Inkling 2 Mini and 300+ other models under a plan usage limit, with no API keys. See plans.
Thinking Machines: Inkling 2 Mini handles 1.0M tokens of context — roughly 786,432 words, or about 1,573 pages of text in one conversation.
Thinking Machines: Inkling 2 Mini's underlying rates are $0.075 per 1M input tokens and $0.3 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.
Yes — Thinking Machines: Inkling 2 Mini accepts image input, so you can attach screenshots, photos or diagrams and ask questions about them.
Yes. Thinking Machines: Inkling 2 Mini can work through problems step by step before answering; on CoreAI you can toggle thinking mode per message.
Open the CoreAI web app or the iOS/Android app, pick Thinking Machines: Inkling 2 Mini in the model selector, and chat — no API key, no per-token billing. One subscription covers Thinking Machines: Inkling 2 Mini and 300+ other models.
The closest alternatives on CoreAI are Thinking Machines: Inkling 2 Small, Tencent: Hy4 flash, inclusionAI: Ling 3.0 Tiny — similar capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.
Chat with Thinking Machines: Inkling 2 Mini and 300+ other AI models — all in one app.