Ling 3.0 Flash VL · deepinfra

The multimodal version built on Ling-3.0-flash — 124B total / ~5.5B active per token, with native text, image, and video understanding. It’s mainly designed for multimodal agentic workflows, long-context understanding, and multi-step reasoning.

Modelo baseTodos os modelos desta baseTodos os modelos do provedorao provedor

Todos os modelos inclusionAI Ling em todos os provedores

Entrada, $/1M $0.06

Saída, $/1M $0.18

Contexto 131 072

Aceita —

Última verificação 04.11.2026 12:00:14 UTC

Fonte —