z-ai
Z.ai: GLM 4.6V
z-ai/glm-4.6v
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
z-ai/glm-4.6v is listed by OpenRouter as a model accepting text, image, and video inputs and producing text, with a 128K-token context window. Z.ai's documentation describes GLM-4.6V as a 106B multimodal foundation model and reports document interpretation, vision-driven tool use, mixed image-text generation, and leading visual-understanding results among comparable-scale models. Those benchmark claims are vendor-reported; no independent evaluation is included in the source pack.[1][2]
Strengths
- The OpenRouter catalog reports text, image, and video inputs with text output and a 128K-token context window.[1]
- Vendor documentation says GLM-4.6V interprets richly formatted document pages directly as images, including text, layout, charts, tables, and figures.[2]
- The documentation reports native function calling that can use images, screenshots, document pages, and visual tool outputs inside a reasoning chain.[1][2]
Limitations
- The source pack contains no independent measurements; vendor claims of leading results should remain unverified until tested on the intended workload.[1][2]
- Z.ai acknowledges weaker pure-text QA, possible overthinking or repetition with complex prompts, occasional answer restatement, and limits in counting and identifying specific individuals.[2]
- OpenRouter lists only text output, while the model card describes interleaved image-text generation; confirm which output form the endpoint exposes.[1][2]
Where to use it
- Evaluate for long, image-heavy document review where layout, charts, tables, and figures must be interpreted together; test against representative files.[1][2]
- Consider prototypes for multimodal agents or tool workflows that take screenshots and document pages as direct visual inputs.[1][2]
- Pilot UI screenshot-to-HTML/CSS reconstruction and natural-language visual editing, which the vendor describes but the source pack does not independently measure.[2]
Sources
- [1] OpenRouter catalog · Z.ai: GLM 4.6VSources checked: Nov 13, 2026
- [2] Model documentation · Z.ai: GLM 4.6VSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...
Specifications
- Model ID
- z-ai/glm-4.6v
- Canonical ID
- z-ai/glm-4.6-20251208
- Creator
- z-ai
- Added to OpenRouter
- 08.12.2025
- Context length
- 131,072
- Modality
- text+image+video->text
- Input modalities
- image, text, video
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.300 / out $0.900
- 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: optional · parameters: include_reasoning, reasoning |
| Coding | No measurement | — |
| Agents | No measurement | parameters: tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| 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) |
|---|---|---|---|---|---|---|
| Novitabf16 | 131,072 | $0.300 | $0.900 | — | — | 100% |
| Z.AIfp8 | 131,072 | $0.300 | $0.900 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.