Moondream 3.1
Moondream 3.1 is a vision-language model from Moondream that accepts text and images and produces text. It supports reasoning, visual question answering, image captioning, and OCR.
Moondream 3.1 specs and pricing
- Provider: Moondream
- Released: October 15, 2026
- Context window: 32K tokens
- Max output: 4K tokens
- Input: text, images
- Output: text
- Price: $0.30 input / $2.50 output per 1M tokens
- Reasoning: yes
What Moondream 3.1 is good at
- Answering questions about images
- Writing image captions
- Extracting text from images
To-dos to try with Moondream 3.1
- Describe what is visible in this image.
- Read and transcribe the text in this image.
- Answer my question about the contents of this image.
FAQ
- Can Moondream 3.1 read images? Yes. It accepts images and can answer questions about them, write captions, and extract text.
- Does Moondream 3.1 support tool calling? No, Moondream 3.1 does not support tool calling.
- How much does Moondream 3.1 cost? Moondream 3.1 costs $0.30 per million input tokens and $2.50 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.19 credits ($1 = 100 credits).
- What is the context window of Moondream 3.1? Moondream 3.1 can read up to 32K tokens at once and write up to 4K tokens in one reply.
- Can I use Moondream 3.1 without coding? Yes. In todo.is you pick Moondream 3.1 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.