z-ai
Z.ai: GLM 5.3 FlashX Legal
z-ai/glm-5.3-flashx-legal
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
OpenRouter’s catalog describes z-ai/glm-5.3-flashx-legal as Z.ai’s legal-domain variant of GLM-5.3-FlashX. It is reported to accept text, image, and video input, produce text, support tools and structured outputs, and provide a context window of roughly one million tokens. Reasoning is mandatory and enabled by default, with max, high, and low effort settings. The catalog mentions legal-domain mid-training and reinforcement-based post-training, but this source pack contains no independent model card or measured performance evidence.[1]
Strengths
- Catalog-reported multimodal text generation: text, image, and video inputs map to text outputs.[1]
- Legal-domain adaptation is described as including mid-training and reinforcement-based post-training.[1]
- The catalog lists a roughly one-million-token context, tool calling, structured outputs, and multiple reasoning effort settings.[1]
Limitations
- Evidence is catalog-only: no independent model card was included in this source pack.[1]
- No measured benchmark results were supplied; the catalog benchmark fields are empty or null.[1]
- Legal accuracy, jurisdiction coverage, safety behavior, and multimodal effectiveness require workload-specific validation.[1]
Where to use it
- Evaluate for legal research, summarization, and drafting over long or mixed-modality case materials.[1]
- Prototype structured legal extraction or workflow calls where tool and structured-output support are relevant.[1]
- Pilot controlled legal-document intake and review workflows before relying on jurisdiction-specific outputs.[1]
Sources
- [1] OpenRouter catalog · Z.ai: GLM 5.3 FlashX LegalSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement...
Specifications
- Model ID
- z-ai/glm-5.3-flashx-legal
- Canonical ID
- z-ai/glm-5.3-flashx-legal-20261102
- Creator
- z-ai
- Added to OpenRouter
- 02.11.2026
- Context length
- 1,048,576
- Modality
- text+image+video->text
- Input modalities
- text, image, video
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.370 / out $1.25
- 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 | No measurement | reasoning: mandatory · default max · efforts: max, high, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | 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 | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | input: video |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
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) |
|---|---|---|---|---|---|---|
| Z.AIfp8 | 1,048,576 | $0.370 | $1.25 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.