Reflection-Llama-3.1-70B · deepinfra

Reflection Llama-3.1 70B is trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course. The model was trained on synthetic data.

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

Entrada, $/1M $0.35

Salida, $/1M $0.40

Contexto 8 192

Acepta —

Última comprobación 04.11.2026 12:00:14 UTC

Fuente —