نماذج Zhipu AI

Z

GLM 5.1

مدخل:$0.8/M

الإخراج:$3.2/M

GLM-5.1 (أُطلق في أبريل 2026)، مُصمَّم خصيصًا للمهام الذاتية طويلة الأمد. وعلى عكس النماذج التقليدية المُحسَّنة للتفاعلات القصيرة، يتفوّق GLM-5.1 في الحفاظ على مواءمة الأهداف، والحدّ من انجراف الاستراتيجية، وتقديم نتائج بمستوى الإنتاج على مدى فترات ممتدة — تصل إلى 8 ساعات من العمل الذاتي المتواصل على مهمة معقدة واحدة. ويمثل قفزة كبرى في هندسة الوكلاء، إذ يحوّل التقييم من الذكاء أحادي الجولة إلى التنفيذ المستدام في العالم الحقيقي.

Z

GLM 5 Turbo

سياق:200k

مدخل:$0.96/M

الإخراج:$3.264/M

GLM-5 Turbo هو نموذج جديد من Z.ai، صُمم للاستدلال السريع والأداء القوي في البيئات المعتمدة على الوكلاء مثل سيناريوهات OpenClaw.

Z

GLM 5

مدخل:$0.8/M

الإخراج:$3.2/M

<think>**Considering user feedback options** I need to respond to the user's message about "GLM-5 is Z.ai's flagship..." They might want feedback or a rewrite, but they haven't specified a question. I could suggest refining the copy by tightening it, reducing buzzwords, and focusing on concrete benefits. I could propose alternatives like concise one-liners, summaries, or comparisons to other models. Offering options for different formats such as FAQ or social copy would be helpful, but I’ll keep formatting minimal. Let's clarify their needs!**Clarifying complex system design terms** I need to emphasize terms like "complex systems design," "long-horizon agent workflows," and "iterative self-correction." Examples could be microservices refactoring or MLOps. I should be cautious with claims, especially about “rivaling closed-source models,” and suggest they add their own benchmarks instead of hallucinating metrics. They didn't explicitly ask for a review, but since it's product copy, I can propose a punchier version tailored to a specific channel and provide tightened options along with crisp rewrites, summaries, and bullet points.**Refining user content** I need to clarify the user's target audience and preferred channel for their content. Quick improvements involve using fewer adjectives, showcasing unique capabilities, and mentioning key specifications like model size and context window without inventing details. Instead, I can use placeholders for them to fill in. The "Final answer structure and style guidelines" will guide me in creating a header like "Tighten + Options" with 4–6 bullet points. I can also propose four rewrite variants and a one-sentence tagline with three bullet value propositions, while leaving out unnecessary code blocks.**Creating concise rewrites** I want to deliver succinct rewrites while also asking one or two clarifying questions. First, I see that the original text is buzzword-heavy, lacks concrete claims, and could be shortened for clarity. Terms like "autonomous execution" might raise safety concerns, and "agentic planning" feels repetitive. I should ask the user to define their audience. I can propose rewrites for a website hero and a technical description, ensuring to be careful with any vague claims, and I’ll include proof points with placeholders for metrics. I’ll provide a bullet list of claims to avoid too. Lastly, I want to tailor the message, starting with an acknowledgment.**Generating content variants** I need to provide four content variants of varying lengths. First, a 1-liner tagline: "Open-source model for building full systems—plans, codes, tests, ships. Crisp." Next, I’ll create a 25-word version, followed by a 50-word version. Then, I’ll focus on a technical blurb. After that, I’ll create bullet points for "What to tighten" with four items and "Where metrics would help" with five placeholders. I want to ask three questions about the audience, tone, and claims allowed. Keeping everything concise and friendly is key. Finally, I’ll offer a few options and ask the user if they want adjustments tailored for a specific purpose.</think> Want this tightened? Here are a few sharper variants you can drop into a site or deck: 1) Hero (punchy) Open-source model for building full systems—not just code. GLM-5 plans, writes, tests, and ships complex software with long-horizon agent workflows. 2) Product page (direct) GLM-5 is an open-source foundation model for complex systems design and long‑horizon agents. Built for expert developers, it plans across multi-step tasks, writes and refactors large codebases, and iteratively self-corrects—delivering production-grade performance on large-scale programming work. 3) Technical (developer-focused) GLM-5 pairs advanced agent planning with deep reasoning and iterative self-checks to move beyond snippet generation into full-system construction and autonomous execution. It handles multi-repo changes, tool use, and long-running workflows, rivaling top closed models in real programming workloads. 4) Enterprise (outcomes) From roadmap to running services, GLM-5 executes complex builds with reliability and control. Open-source, production-grade, and designed for long-horizon agent orchestration across large codebases and toolchains. What to tighten or add - Replace abstractions with specifics: supported tools (e.g., repo ops, test runners, CI), codebase scale, context/window, and safety/guardrails. - Add proof points: latency, pass@1 on coding suites, multi-file refactor success, long-horizon step depth, cost per task (even ranges help). - Clarify “autonomous execution” boundaries (human-in-the-loop vs. fully automated). - If you claim “rivaling closed models,” anchor it to benchmarks or real workloads. Want me to tailor this for a landing page hero, a one-liner tagline, or a longer datasheet blurb?

Z

GLM 4.6

سياق:200,000

مدخل:$0.96/M

الإخراج:$3.84/M

تم إصدار نموذج Zhipu الرائد الأحدث GLM-4.6: إجمالي المعاملات 355B، والمعاملات النشطة 32B. تتفوق القدرات الأساسية الشاملة على GLM-4.5. البرمجة: يتماشى مع Claude Sonnet 4، الأفضل في الصين. السياق: مُدِّد إلى 200K (في الأصل 128K). الاستدلال: مُحسَّن، يدعم Tool calls. البحث: تم تحسين Tool وإطار الوكلاء. الكتابة: أكثر اتساقاً مع تفضيلات البشر وأسلوب الكتابة ولعب الأدوار. متعدد اللغات: تم تعزيز تأثير الترجمة.

Z

GLM-4.7

سياق:200K

مدخل:$0.96/M

الإخراج:$3.84/M

GLM-4.7 هو أحدث نموذج رائد من Z.AI، يقدّم ترقيات في مجالين رئيسيين: قدرات برمجية معززة وتفكير وتنفيذ متعدد الخطوات أكثر استقرارًا. ويُظهر تحسينات كبيرة في تنفيذ مهام الوكلاء المعقدة، مع تقديم تجارب محادثة أكثر طبيعية وجماليات واجهة أمامية متفوقة.

Z

glm-4.5-x

Z

glm-4.5-x

مدخل:$3.2/M

الإخراج:$12.8/M

نموذج عالي الأداء، ذو استدلال قوي واستجابة فائقة السرعة، مُحسّن للسيناريوهات التي تتطلب سرعة استدلال فائقة وقدرات منطقية قوية، ويوفّر تجربة استجابة على مستوى الميلي ثانية.

Z

glm-4.5-flash

Z

glm-4.5-flash

مدخل:$0.16/M

الإخراج:$0.64/M

GLM-4.5-Flash is an artificial intelligence model provided by ZhipuAI.

Z

glm-4.5-airx

Z

glm-4.5-airx

مدخل:$1.6/M

الإخراج:$6.4/M

نموذج خفيف الوزن، عالي الأداء، فائق السرعة في الاستجابة، يجمع بشكل مثالي بين مزايا التكلفة لـ Air ومزايا السرعة لـ X، وهو خيار مثالي لتحقيق التوازن بين الأداء والكفاءة.

Z

glm-4.5-air

Z

glm-4.5-air

مدخل:$0.16/M

الإخراج:$1.0672/M

GLM-4.5-Air is an artificial intelligence model provided by ZhipuAI.

Z

glm-4.5

Z

glm-4.5

مدخل:$0.96/M

الإخراج:$3.84/M

GLM-4.5 is an artificial intelligence model provided by ZhipuAI.