Inkling Small
Inkling Small is a multimodal model developed by Thinking Machines Lab that processes text, images, and audio. It features a large context window and built-in reasoning capabilities, designed to offer an efficient alternative to larger AI systems.
Inkling Small specs and pricing
- Provider: Thinking Machines
- Released: July 30, 2026
- Context window: 524K tokens
- Max output: 262K tokens
- Input: text, images, audio
- Output: text
- Price: $0.45 input / $1.20 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Inkling Small is good at
- Analyzing long documents and media files
- Complex reasoning tasks requiring tool usage
- Efficient processing of multimodal data inputs
To-dos to try with Inkling Small
- Transcribe and summarize the key action items from this 30-minute audio meeting recording.
- Analyze these ten product images and identify which ones contain safety compliance labels.
- Read this 400-page technical manual and explain the troubleshooting steps for the error code provided.
FAQ
- What types of media can Inkling Small process? The model accepts text, images, and audio as input, though it only generates text as output.
- Does this model support external tools? Yes, Inkling Small is equipped with tool-calling capabilities to assist with complex tasks.
- How much does Inkling Small cost? Inkling Small costs $0.45 per million input tokens and $1.20 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.43 credits ($1 = 100 credits).
- What is the context window of Inkling Small? Inkling Small can read up to 524K tokens at once and write up to 262K tokens in one reply.
- Can I use Inkling Small without coding? Yes. In todo.is you pick Inkling Small 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.