Llama 3.1 70B Instruct
Meta developed Llama 3.1 70B Instruct as a versatile model optimized for high-quality dialogue and complex interactions. It supports a large context window of 131,072 tokens and includes native tool-calling capabilities. This model is designed to handle text-based inputs and outputs efficiently.
Llama 3.1 70B Instruct specs and pricing
- Provider: Meta
- Released: July 23, 2024
- Context window: 131K tokens
- Max output: 8K tokens
- Input: text
- Output: text
- Price: $0.72 input / $0.72 output per 1M tokens
- Tool calling: yes
What Llama 3.1 70B Instruct is good at
- Engaging in nuanced, multi-turn conversations
- Integrating AI into applications requiring tool use
- Processing and analyzing large text documents
To-dos to try with Llama 3.1 70B Instruct
- Summarize a 100-page technical report and extract key action items
- Draft a series of customer support responses based on a provided knowledge base
- Use tool-calling to query a database and format the results into a text report
FAQ
- Who created Llama 3.1 70B Instruct? This model was developed and released by Meta.
- Can this model interact with external tools? Yes, the model is built with native tool-calling capabilities to assist in executing specific tasks.
- How much does Llama 3.1 70B Instruct cost? Llama 3.1 70B Instruct costs $0.72 per million input tokens and $0.72 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 2.12 credits ($1 = 100 credits).
- What is the context window of Llama 3.1 70B Instruct? Llama 3.1 70B Instruct can read up to 131K tokens at once and write up to 8K tokens in one reply.
- Can I use Llama 3.1 70B Instruct without coding? Yes. In todo.is you pick Llama 3.1 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.