Llama-3.3-70B-Instruct · deepinfra

Llama 3.3-70B is a multilingual LLM trained on a massive dataset of 15 trillion tokens, fine-tuned for instruction-following and conversational dialogue. The model is designed to be helpful, safe, and flexible, with a focus on responsible deployment and mitigating potential risks such as bias, toxicity, and misinformation. It achieves state-of-the-art performance on various benchmarks, including conversational tasks, language translation, and text generation.

Modelo baseTodos los modelos de esta baseTodos los modelos del proveedoral proveedor

Lea también: Precios de la API de Llama: Llama 4 Maverick, Scout y Llama 3.3 70B en cada proveedor

Todos los modelos de Meta Llama en todos los proveedores

Entrada, $/1M $0.23

Salida, $/1M $0.40

Contexto 131 072

Acepta —

Última comprobación 04.11.2026 12:00:14 UTC

Fuente —