Inkling 2 Mini
Inkling 2 Mini is a multimodal model developed by Thinking Machines Lab. It utilizes a looped transformer architecture to process both text and image inputs while supporting reasoning and tool-calling capabilities.
Inkling 2 Mini specs and pricing
- Provider: Thinking Machines
- Released: November 21, 2026
- Context window: 1M tokens
- Max output: 66K tokens
- Input: text, images
- Output: text
- Price: $0.075 input / $0.30 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Inkling 2 Mini is good at
- Analyzing complex documents or images
- Tasks requiring logical reasoning
- Applications needing integrated tool usage
To-dos to try with Inkling 2 Mini
- Upload a series of technical diagrams and ask the model to explain the differences between them
- Provide a long text document and use tool calling to extract specific data points into a structured format
- Ask the model to reason through a multi-step logic puzzle based on provided text and image context
FAQ
- What types of media can Inkling 2 Mini process? The model accepts both text and image inputs and generates text-based outputs.
- Who developed Inkling 2 Mini? It was created by Thinking Machines Lab as an open-weight multimodal model.
- How much does Inkling 2 Mini cost? Inkling 2 Mini costs $0.075 per million input tokens and $0.30 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.25 credits ($1 = 100 credits).
- What is the context window of Inkling 2 Mini? Inkling 2 Mini can read up to 1M tokens at once and write up to 66K tokens in one reply.
- Can I use Inkling 2 Mini without coding? Yes. In todo.is you pick Inkling 2 Mini as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.