Zhipu AI modeller

Z

GLM 5.1

Indtast:$0.8/M

Output:$3.2/M

GLM-5.1 (udgivet april 2026), formålsbygget til autonome opgaver med lang tidshorisont. I modsætning til traditionelle modeller, der er optimeret til korte interaktioner, udmærker GLM-5.1 sig ved at fastholde overensstemmelse med målene, reducere afdrift i strategien og levere resultater i produktionskvalitet over længere perioder — op til 8 timers kontinuerligt autonomt arbejde på en enkelt kompleks opgave. Det repræsenterer et markant spring inden for agentbaseret ingeniørarbejde og flytter evalueringen fra intelligens i enkeltinteraktioner til vedvarende udførelse i den virkelige verden.

Z

GLM 5 Turbo

Kontekst:200k

Indtast:$0.96/M

Output:$3.264/M

GLM-5 Turbo er en ny model fra Z.ai designet til hurtig inferens og høj ydeevne i agentdrevne miljøer såsom OpenClaw-scenarier.

Z

GLM 5

Indtast:$0.8/M

Output:$3.2/M

<think>**Considering user request** I need to respond to the user about their statement on GLM-5. They didn’t ask a specific question, which makes me wonder if they want a rewrite, summary, or feedback on it. Since it’s just a single paragraph, I might suggest options like summarizing, marketing copy, or proofreading. I’ll provide numbered choices for clarity. Also, I should be careful about any claims made while providing suggestions to refine the copy.**Revising user content** I think it’s a good idea to provide a tightened version with alternative tones like concise, technical, product-focused, and SEO-friendly. I’ll suggest 2-3 variations without heavy formatting and minimal bullet points. I'll offer options such as a punchy version, a README version, or key bullets. I’ll also keep in mind to avoid repetition and emphasize unique features, while suggesting placeholders for metrics. I want to encourage the user to fill in those metrics carefully and ask for their preferred style!**Creating editing options** I see that the editing constraints allow ASCII only—got it! I think it could be useful to suggest comparisons to models like Llama 3.1, CodeLlama, DeepSeek Coder V2, and GPT-4o, but I’ll be cautious about it. Instead, I’ll focus on creating a tagline and bullet list for features. I’ll draft three variations: 1) a punchy version, 2) a technical tone, and 3) a product website tagline with bullets. I'll keep the formatting minimal and concise!**Formulating suggestions** I think to strengthen the content, I should quantify performance, highlight agentic features, and mention licensing, system requirements, SDKs, security, and inference. It’s also important to ask the user which variant they prefer and provide appropriate metrics, benchmarks, and target audience details. The guidelines say headers are optional, and I’ll keep formatting minimal with bullet points. I want to ensure accuracy, avoiding any claims beyond the user’s text, so I'll develop three variants with concise suggestions while possibly including a README snippet for a "pip install" command, but I’ll refrain from details I’m unsure about. Let's get started!</think> Want this tightened or tailored? Here are a few punchier variants plus quick suggestions. **Concise** GLM-5 is Z.ai’s open-source foundation model for complex systems design and long-horizon agents. Built for expert developers, it delivers production-grade performance on large-scale programming, with agentic planning, deep backend reasoning, and iterative self-correction for full‑system construction and autonomous execution. **Technical** GLM-5 is Z.ai’s open-source foundation model optimized for complex systems design and long-horizon agent workflows. It combines advanced planning, tool-use orchestration, and iterative self-correction to move beyond code generation into full-system construction and autonomous execution. Designed for expert developers, it targets production-grade performance on large-scale programming tasks and rivals leading closed-source models. **Website/README** Build full systems, not just code. GLM-5 is Z.ai’s open-source model for long‑horizon, production agent workflows. - Advanced agentic planning and tool orchestration - Deep backend reasoning across large codebases - Iterative self-correction loops for reliability - Production-grade performance on large programming tasks Suggestions to strengthen - Quantify claims: add benchmarks (e.g., SWE-bench, HumanEval+, long-horizon tasks), hardware/time. - Clarify licensing and usage scope (commercial? model sizes?). - Name concrete agent features (planner, executor, tool API, memory, eval harness). - Add a clear call to action (links to weights, docs, quickstart). - If “rivals closed-source models,” cite specific head-to-head metrics. Want me to adapt this for a README hero, a press note, or docs intro? If you have benchmarks, license, and model sizes, I can fold them in.

Z

GLM 4.6

Kontekst:200,000

Indtast:$0.96/M

Output:$3.84/M

Zhipus nyeste flagskibsmodel GLM-4.6 lanceret: samlede parametre 355B, aktive parametre 32B. De samlede kernekapaciteter overgår GLM-4.5. Kodning: På niveau med Claude Sonnet 4, bedst i Kina. Kontekst: Udvidet til 200K (oprindeligt 128K). Inferens: Forbedret, understøtter Tool-kald. Søgning: Optimeret Tool- og agentrammeværk. Skrivning: Bedre afstemt med menneskelige præferencer, skrivestil og rollespil. Flersproget: Forbedret oversættelseseffekt.

Z

GLM-4.7

Kontekst:200K

Indtast:$0.96/M

Output:$3.84/M

GLM-4.7 er Z.AI’s nyeste flagskibsmodel, med opgraderinger på to centrale områder: forbedrede programmeringsevner og mere stabil flertrinsræsonnering og udførelse. Den demonstrerer betydelige forbedringer i udførelsen af komplekse agentopgaver, samtidig med at den leverer mere naturlige samtaleoplevelser og overlegen front-end-æstetik.

Z

glm-4.5-x

Z

glm-4.5-x

Indtast:$3.2/M

Output:$12.8/M

Højtydende, stærk inferens, ekstremt hurtig responsmodel, optimeret til scenarier, der kræver ultrahurtig inferenshastighed og kraftfulde logiske kapaciteter, og leverer en oplevelse med responstid på millisekundniveau.

Z

glm-4.5-flash

Z

glm-4.5-flash

Indtast:$0.16/M

Output:$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

Indtast:$1.6/M

Output:$6.4/M

Letvægts, højtydende model med ultrahurtig responstid, som perfekt kombinerer Airs omkostningsfordele og X's hastighedsfordele, et ideelt valg til at balancere ydeevne og effektivitet.

Z

glm-4.5-air

Z

glm-4.5-air

Indtast:$0.16/M

Output:$1.0672/M

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

Z

glm-4.5

Z

glm-4.5

Indtast:$0.96/M

Output:$3.84/M

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