Mixtral 8x22B Instruct
Mixtral 8x22B Instruct is a model developed by Mistral that uses a mixture-of-experts architecture to balance performance and efficiency. It is designed to handle text and file inputs for tasks including coding, mathematical problem-solving, and tool-based operations.
Mixtral 8x22B Instruct specs and pricing
- Provider: Mistral
- Released: April 17, 2024
- Context window: 66K tokens
- Max output: 52K tokens
- Input: text, files
- Output: text
- Price: $2.00 input / $6.00 output per 1M tokens
- Tool calling: yes
What Mixtral 8x22B Instruct is good at
- Complex mathematical calculations
- Writing and debugging code
- Tasks requiring external tool integration
To-dos to try with Mixtral 8x22B Instruct
- Analyze a provided technical document and extract all mathematical formulas.
- Write a Python script to automate data processing from an uploaded file.
- Use tool-calling capabilities to retrieve specific information from a connected database.
FAQ
- Who developed Mixtral 8x22B Instruct? The model was developed and released by Mistral.
- What kind of data can this model process? It accepts both text and file inputs, producing text-based outputs.
- How much does Mixtral 8x22B Instruct cost? Mixtral 8x22B Instruct costs $2.00 per million input tokens and $6.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 6.44 credits ($1 = 100 credits).
- What is the context window of Mixtral 8x22B Instruct? Mixtral 8x22B Instruct can read up to 66K tokens at once and write up to 52K tokens in one reply.
- Can I use Mixtral 8x22B Instruct without coding? Yes. In todo.is you pick Mixtral 8x22B 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.