Mistral: Mixtral 8x7B Instruct
mistralai
Mixtral 8x7B Instruct is a pretrained generative Sparse Mixture of Experts, by Mistral AI, for chat and instruction use. Incorporates 8 experts (feed-forward networks) for a total of 47 billion...
- Context window
- 32,768 tokens
- Input cost
- $0.54 / 1M
- Output cost
- $0.54 / 1M
- Latency (p50)
- —