Llama 3.1 8B Instruct
Meta's Llama 3.1 8B Instruct is an efficient, instruction-tuned model released in July 2024. It is designed for fast text processing and supports tool calling within a 131,072-token context window.
Llama 3.1 8B Instruct specs and pricing
- Provider: Meta
- Released: July 23, 2024
- Context window: 131K tokens
- Max output: 16K tokens
- Input: text
- Output: text
- Price: $0.02 input / $0.04 output per 1M tokens
- Tool calling: yes
What Llama 3.1 8B Instruct is good at
- Rapid text-based instruction following
- Integrating AI into applications via tool calling
- Processing large documents within its extensive context window
To-dos to try with Llama 3.1 8B Instruct
- Summarize the key arguments from a long technical report
- Extract structured data from a raw text transcript
- Use tool calling to look up information from an external database
FAQ
- Who developed Llama 3.1 8B Instruct? This model was developed by Meta as part of their Llama 3.1 series.
- What types of data can this model process? The model is designed to accept text input and generate text output.
- How much does Llama 3.1 8B Instruct cost? Llama 3.1 8B Instruct costs $0.02 per million input tokens and $0.04 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.06 credits ($1 = 100 credits).
- What is the context window of Llama 3.1 8B Instruct? Llama 3.1 8B Instruct can read up to 131K tokens at once and write up to 16K tokens in one reply.
- Can I use Llama 3.1 8B Instruct without coding? Yes. In todo.is you pick Llama 3.1 8B 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.