Z.ai has 2 models in The AI Leaderboard directory: GLM-5.3, GLM-5.2. This provider hub compares their verified availability, licensing, context windows, pricing references and intended uses, with direct links to every model guide.
Quick answer: GLM-5.3 is the first Z.ai model to evaluate for its documented fit: agentic coding, long-horizon software engineering, vulnerability discovery and text-based tool use. Use the lineup table below to compare it with the provider’s other current, specialist, open-weight or migration-reference models.
Z.ai model lineup at a glance
Metric | Current directory value |
|---|---|
Models covered | 2 |
Currently ranked | None in the current top eight |
Open-weight models | 2 |
Restricted models | 0 |
Legacy or migration references | 0 |
Highest-ranked model | No current Overall rank assigned |
Last verified | September 2, 2026 |
Complete Z.ai model directory
Model names in this table link directly to their complete guides. Status and pricing can change, so confirm the active endpoint and provider terms before procurement or migration.
Model | Status | License | Context | Best fit |
|---|---|---|---|---|
Available; open weights | Open weights | 1 million tokens | long-horizon coding, automated research and open deployment | |
Available through Z.ai APIs and coding plans | Open weights | 1 million tokens | agentic coding, long-horizon software engineering, vulnerability discovery and text-based tool use |
How the Z.ai models differ
Model | Directory role | Modalities | Maximum output | Access |
|---|---|---|---|---|
GLM-5.2 | Open weights | Text input; text output | 128,000 tokens | Z.ai APIs, Coding Plan and downloadable weights |
GLM-5.3 | Open weights | Text input; text output | 128,000 tokens | Z.ai API, GLM Coding Plan, compatible coding agents and downloadable weights |
The labels above describe access and lifecycle, not a hidden capability ranking. Only models with a validated Overall record receive a rank on this site. Other guides remain unranked until comparable evidence is available.
Z.ai model pricing
Model | Pricing reference | Cost caveat |
|---|---|---|
GLM-5.2 | Open-weight self-hosting plus Z.ai plans from the published subscription tier | Self-hosting still incurs infrastructure and operations costs |
GLM-5.3 | Plan and API pricing varies; Z.ai does not publish one universal rate on the model overview | Self-hosting still incurs infrastructure and operations costs |
Token price is not cost per accepted result. Measure retries, tool calls, latency, infrastructure and reviewer time on the same task set.
Which Z.ai model should you choose?
Requirement | Starting point | Why |
|---|---|---|
Highest current rank | GLM-5.2 | No ranked model; start with the documented fit and test directly |
Open weights or self-hosting | GLM-5.3, GLM-5.2 | Review the exact license, checkpoint and hardware needs |
Restricted specialist work | No restricted model in this provider directory | Use generally available models and least-privilege controls |
Migration or reproduction | GLM-5.3 | Compare current versions using pinned snapshots |
Lowest operational cost | Measure two or three eligible models | Headline token prices omit retries, tools, caching and human review |
Z.ai models, explained
GLM-5.2
GLM-5.2 was released June 2026. It is listed as available; open weights with open weights. The documented context window is 1 million tokens, and the maximum output is 128,000 tokens.
- Best fit: long-horizon coding, automated research and open deployment.
- Modalities: Text input; text output.
- Access: Z.ai APIs, Coding Plan and downloadable weights.
- Pricing reference: Open-weight self-hosting plus Z.ai plans from the published subscription tier.
Read the complete GLM-5.2 guide for benchmarks, limitations, official sources and an evaluation framework.
GLM-5.3
GLM-5.3 was released August 14, 2026. It is listed as available through z.ai apis and coding plans with open weights. The documented context window is 1 million tokens, and the maximum output is 128,000 tokens.
- Best fit: agentic coding, long-horizon software engineering, vulnerability discovery and text-based tool use.
- Modalities: Text input; text output.
- Access: Z.ai API, GLM Coding Plan, compatible coding agents and downloadable weights.
- Pricing reference: Plan and API pricing varies; Z.ai does not publish one universal rate on the model overview.
Read the complete GLM-5.3 guide for benchmarks, limitations, official sources and an evaluation framework.
How to evaluate Z.ai models
Shortlist the Z.ai models that meet your access, licensing and modality requirements. Freeze 20 to 50 representative tasks, then give each candidate the same prompts, tools, context, reasoning budget and retry limits. Record the exact model identifier because provider aliases can change.
Measure | Record | Decision use |
|---|---|---|
Task completion | Pass rate and rubric score | Establish whether the model meets the acceptance threshold |
Reliability | Repeated-run variance and recovery behavior | Avoid choosing from one lucky result |
Quality | Factuality, instruction following and reviewer acceptance | Separate polished output from correct output |
Tool use | Wrong calls, retries, permission errors and unsafe actions | Evaluate the model and agent harness together |
Efficiency | Wall time, tokens, caching, tools and review labor | Calculate cost per accepted result |
Governance | Retention, training, regional processing and audit logs | Confirm the deployment fits policy requirements |
Availability, versions and lifecycle
Z.ai may expose different snapshots, effort settings, products and partner integrations under similar labels. Treat every model name as incomplete without an exact endpoint or checkpoint. Re-run regression tests after any model, system prompt, retrieval, tool or permission change.
- Available means a documented access route exists, not that every region or account has access.
- Preview models can change behavior, price or retirement dates before general availability.
- Open weights require an exact license and checkpoint review; “open” does not guarantee open training data or low operating cost.
- Restricted models require separate eligibility, safeguards and data-handling review.
- Legacy models remain useful for migration and reproduction but should not be the default for a new deployment.
Sources and update policy
Official Z.ai model documentation is the provider-level starting point. Each linked model guide cites its own first-party launch page, model card, pricing reference and safety documentation.
Compare this provider with the complete Best AI Models directory.
Last verified September 2, 2026. The hub should be updated when the provider launches, retires, renames or reprices a model, changes context or output limits, alters licensing, or modifies regional availability.
Frequently asked questions
How many Z.ai models are covered?
This hub covers 2: GLM-5.3, GLM-5.2. Every model has a dedicated guide linked from the directory table and profile sections.
What is the best Z.ai model?
Z.ai does not have a model with a current Overall rank on this page. Start with GLM-5.3 for its documented fit, then validate it against alternatives using the same task set.
Does Z.ai offer open weights?
Yes. The directory identifies GLM-5.3, GLM-5.2 as open-weight options. Review the exact license, downloadable artifact and serving requirements before deployment.
How current is the pricing?
Pricing references were verified September 2, 2026 from first-party documentation summarized in each model guide. Always recheck the provider before budgeting because cache, batch, long-context, tool and regional rates can change.
Should every Z.ai model be tested?
No. Remove models that fail access, license, modality, context, latency or governance requirements first. Test the smallest credible shortlist on representative work.