Inkling
Inkling is an open-weight multimodal model developed by Thinking Machines Lab designed for general-purpose reasoning and coding tasks. It supports text, image, and audio inputs and features advanced capabilities for agentic workflows and tool use.
Inkling specs and pricing
- Provider: Thinking Machines
- Released: July 17, 2026
- Context window: 524K tokens
- Max output: 472K tokens
- Input: text, images, audio
- Output: text
- Price: $1.00 input / $4.05 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Inkling is good at
- Complex reasoning and problem-solving tasks
- Developing agentic and tool-integrated systems
- Multimodal analysis involving text, audio, and images
To-dos to try with Inkling
- Analyze a series of meeting audio recordings and summarize the key action items.
- Upload a complex architectural diagram and ask the model to generate a list of potential structural concerns.
- Provide a large codebase and use the tool-calling capability to identify and fix specific bugs.
FAQ
- What types of data can Inkling process? Inkling is a multimodal model that accepts text, images, and audio as input and provides text-based responses.
- What is Inkling primarily designed for? It is built for general-purpose reasoning, software coding, and supporting agentic systems that utilize external tools.
- How much does Inkling cost? Inkling costs $1.00 per million input tokens and $4.05 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 3.37 credits ($1 = 100 credits).
- What is the context window of Inkling? Inkling can read up to 524K tokens at once and write up to 472K tokens in one reply.
- Can I use Inkling without coding? Yes. In todo.is you pick Inkling 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.