GLM-4.6 · deepinfra

Compared with GLM-4.5, GLM-4.6 brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks. Superior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages. Advanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability. More capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks. Refined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.

Modèle de baseTous les modèles de cette baseTous les modèles du fournisseurvers le fournisseur

À lire aussi : Prix de l'API GLM : GLM-5.3, GLM-5.3 Flash et GLM-5.2 chez tous les fournisseurs

Tous les modèles Zhipu GLM chez tous les fournisseurs

Entrée, $/1M $0.50

Sortie, $/1M $2.00

Contexte 202 752

Sortie max. 131 072

Accepte texte

Dernière vérification 04.11.2026 12:00:14 UTC

Source —