GLM-4.7 · deepinfra

GLM-4.7 is a state-of-the-art, multilingual Mixture-of-Experts (MoE) language model designed for complex reasoning, agentic coding, and tool use. Building on its predecessor GLM-4.6, it delivers significant improvements across key benchmarks, including multilingual SWE-bench, Terminal Bench, and reasoning-heavy evaluations like HLE. The model features advanced "Interleaved Thinking" and new "Preserved Thinking" modes, allowing it to reason before actions and maintain consistency across long, multi-turn tasks. With 358 billion parameters, GLM-4.7 excels in generating clean code, modern UI elements, and sophisticated reasoning outputs.

Modelo baseTodos os modelos desta baseTodos os modelos do provedorao provedor

Leia também: Preços da API GLM: GLM-5.3, GLM-5.3 Flash e GLM-5.2 em todos os provedores

Todos os modelos Zhipu GLM em todos os provedores

Entrada, $/1M $0.40

Saída, $/1M $1.75

Contexto 202 752

Saída máx. 16 384

Aceita texto

Última verificação 04.11.2026 12:00:14 UTC

Fonte —