GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a natively multimodal model (text, image, and video input, 1M-token context, up to 128K output) with legal mid-training and reinforcement learning in environments modeled on real legal workflows. It targets legal research, contract review, cross-document consistency checks, and drafting, with thinking always on, tool and MCP support, and the same price as base FlashX.
コスト率
0.3x
コンテキスト
1M
リリース
2026年11月2日
入力
TextImageVideo
出力
Text
対応
推論ツール呼び出し構造化出力