Llama 4 Scout
Meta developed Llama 4 Scout as a mixture-of-experts language model designed to process both text and image inputs. It features a very large context window of over 1.3 million tokens and supports tool calling for interactive tasks.
Llama 4 Scout specs and pricing
- Provider: Meta
- Released: April 5, 2025
- Context window: 1.3M tokens
- Max output: 16K tokens
- Input: text, images
- Output: text
- Price: $0.10 input / $0.30 output per 1M tokens
- Tool calling: yes
What Llama 4 Scout is good at
- Analyzing large documents or datasets
- Multimodal tasks involving text and images
- Building applications that require tool integration
To-dos to try with Llama 4 Scout
- Upload a series of technical diagrams and ask the model to summarize the differences between them.
- Paste a massive codebase and ask the model to identify potential security vulnerabilities.
- Provide a collection of project logs and ask the model to extract specific action items for the team.
FAQ
- What kind of data can I provide to Llama 4 Scout? This model supports native multimodal input, meaning you can provide both text and images for it to process.
- Who is the developer of Llama 4 Scout? Llama 4 Scout is a language model developed by Meta.
- How much does Llama 4 Scout cost? Llama 4 Scout costs $0.10 per million input tokens and $0.30 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.32 credits ($1 = 100 credits).
- What is the context window of Llama 4 Scout? Llama 4 Scout can read up to 1.3M tokens at once and write up to 16K tokens in one reply.
- Can I use Llama 4 Scout without coding? Yes. In todo.is you pick Llama 4 Scout 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.