z-ai
Z.ai: GLM 5.3 (batch)
z-ai/glm-5.3:batch
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
z-ai/glm-5.3:batch is the batch variant of Z.ai's GLM-5.3 listed on OpenRouter. The catalog describes a text-only reasoning model with a 1M-token context window and mandatory reasoning with adjustable effort. Z.ai's model card says GLM-5.3 reuses the GLM-5.2 base and gains capability through post-training, aiming at complex software engineering and long-horizon agent tasks. Vendor-reported benchmarks show strong coding and security results, but these are self-reported, and the evidence does not describe batch-specific behavior. Validate performance on your own workloads.[1][2]
Strengths
- The OpenRouter catalog lists a 1M-token context window for this text-in, text-out model.[1]
- Reasoning effort is tunable across low, high, and max levels, and the endpoint advertises tool calling and structured output parameters.[1][2]
- Z.ai reports large gains over GLM-5.2 on its own coding and agent benchmarks, including results it presents as open-weights state of the art; these figures come from the vendor.[2]
Limitations
- The OpenRouter catalog marks reasoning as mandatory, so it cannot be disabled, only tuned via effort levels.[1]
- All benchmark evidence is vendor-reported or catalog-listed; no independent model card covering the batch variant was included, so results should be validated on real workloads.[1][2]
- The weights use a custom license whose terms are not detailed in the evidence, and the meaning of the batch suffix is not documented in the sources.[1][2]
Where to use it
- Potentially well suited to complex software engineering and long-horizon agentic workflows, which Z.ai names as design targets.[1][2]
- A candidate for long-document or large-codebase analysis given the listed 1M-token context, subject to workload testing.[1]
- May fit non-interactive, throughput-oriented batch jobs, though the sources do not define batch-specific behavior, so confirm semantics with the provider.[1]
Sources
- [1] OpenRouter catalog · Z.ai: GLM 5.3 (batch)Sources checked: Nov 13, 2026
- [2] Model documentation · Z.ai: GLM 5.3 (batch)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...
Specifications
- Model ID
- z-ai/glm-5.3:batch
- Canonical ID
- z-ai/glm-5.3-20260816
- Creator
- z-ai
- Added to OpenRouter
- 18.08.2026
- Context length
- 1,048,576
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.450 / out $2
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | BB — next 30% of the cohort | reasoning: mandatory · default max · efforts: max, high, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | AA — next 20% of the cohort | — |
| Agents | SS — top 10% of the cohort | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · default max · efforts: max, high, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 31.7 | BB — next 30% of the cohort | 13.11.2026 |
| Artificial Analysis | Coding index | 74.8 | AA — next 20% of the cohort | 13.11.2026 |
| Artificial Analysis | Agentic index | 53.1 | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · 3dwin rate 56% · rank 19 | 1,299Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · asciiartwin rate 47.2% · rank 23 | 1,210Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 52.3% · rank 21 | 1,285Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · datavizwin rate 50.6% · rank 34 | 1,253Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 50.6% · rank 21 | 1,290Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · svgwin rate 51.4% · rank 17 | 1,248Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 52.8% · rank 26 | 1,284Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 52.6% · rank 23 | 1,280Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | agents · htmlslideswin rate 39.1% · rank 2 | 1,189Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · mobileappswin rate 52.2% · rank 23 | 1,186Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · python-pptxslideswin rate 50.4% · rank 10 | 1,206Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | agents · webappswin rate 54.2% · rank 10 | 1,270Elo | AA — next 20% of the cohort | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| DeepInfrafp4 | 1,048,576 | $0.450 | $2 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.