Mistralai
Mistral: Mixtral 8x22B Instruct
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...
| Specifications | |
|---|---|
| Provider | Mistralai |
| Input pricing | $2.00/M tokens |
| Output pricing | $6.00/M tokens |
| Context length | 66K tokens |
| Input modalities | textfile |
| Output modalities | text |
| Tokenizer | Mistral |
| Knowledge cutoff | 2024-01-31 |
| Content moderated | No |
| HuggingFace | mistralai/Mixtral-8x22B-Instruct-v0.1 |
Supported Parameters
frequency_penaltymax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p