Mixtral 8x22B · deepinfra

This is the instruction fine-tuned version of Mixtral-8x22B - the latest and largest mixture of experts large language model (LLM) from Mistral AI. This state of the art machine learning model uses a mixture 8 of experts (MoE) 22b models. During inference 2 experts are selected. This architecture allows large models to be fast and cheap at inference.

Базовая модельВсе модели этой базовойВсе модели провайдерак провайдеру

Все модели Mistral у всех провайдеров

Вход, $/1M $0.65

Выход, $/1M $0.65

Контекст 65 536

Принимает —

Последняя проверка 04.11.2026 12:00:14 UTC

Источник —