Llama 3.3 70B Instruct
Meta's Llama 3.3 70B Instruct is a multilingual, instruction-tuned large language model designed for text-based tasks. It supports a large context window of 131,072 tokens and includes built-in capabilities for tool calling.
Llama 3.3 70B Instruct specs and pricing
- Provider: Meta
- Released: December 6, 2024
- Context window: 131K tokens
- Max output: 115K tokens
- Input: text
- Output: text
- Price: $0.71 input / $0.71 output per 1M tokens
- Tool calling: yes
What Llama 3.3 70B Instruct is good at
- Complex text-based instruction following
- Multilingual content generation
- Applications requiring external tool integration
To-dos to try with Llama 3.3 70B Instruct
- Summarize a long document into a series of actionable steps
- Translate a technical manual into multiple languages
- Use tool calling to retrieve specific data and format it into a report
FAQ
- What is Llama 3.3 70B Instruct best at? It is designed to follow complex instructions and handle multilingual text generation tasks.
- Does this model support image processing? No, this is a text-only model that accepts and generates text input and output.
- How much does Llama 3.3 70B Instruct cost? Llama 3.3 70B Instruct costs $0.71 per million input tokens and $0.71 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 2.09 credits ($1 = 100 credits).
- What is the context window of Llama 3.3 70B Instruct? Llama 3.3 70B Instruct can read up to 131K tokens at once and write up to 115K tokens in one reply.
- Can I use Llama 3.3 70B Instruct without coding? Yes. In todo.is you pick Llama 3.3 70B Instruct 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.