z-ai
Z.ai: GLM 5V Turbo
z-ai/glm-5v-turbo
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
GLM 5V Turbo (z-ai/glm-5v-turbo, canonical z-ai/glm-5v-turbo-20260401) is a Z.ai model listed in the OpenRouter catalog that accepts text, image, and video inputs and produces text output. The catalog describes it as a natively multimodal agent-oriented model aimed at vision-based coding and agent-driven tasks, and lists a large context window of about 200,000 tokens plus support for tool calling, structured responses, and optional reasoning. Because the only evidence is the OpenRouter catalog and no independent model card was available in this source pack, capability claims should be treated as vendor-reported rather than verified.[1]
Strengths
- Natively multimodal inputs per the catalog: accepts text, images, and video, returning text, which suits visual grounding tasks.[1]
- Agent-friendly API surface reported by OpenRouter: tool calling, tool choice, structured response formats, and configurable reasoning that is enabled by default but not mandatory.[1]
- Large reported context window of roughly 200,000 tokens, useful for long documents or extended agent sessions.[1]
Limitations
- Evidence is catalog-only: no independent model card, license terms, or hardware requirements were present in this source pack, and the 'first native multimodal agent' framing is the vendor's own description.[1]
- Measured Design Arena results listed by OpenRouter are uneven across categories: comparatively better in presentation/slide and Android-native agentic tasks, weaker in Godot game development, full-stack, mobile, and web app tasks; validate on your workload.[1]
- Knowledge cutoff, training details, and safety behavior are not documented in the supplied evidence and remain unknown.[1]
Where to use it
- Potentially a good fit for agentic coding pipelines where screenshots, UI recordings, or video inform code generation, given the multimodal inputs and tool support; pilot before committing.[1]
- Worth evaluating for automated slide and presentation generation agents, a category where its recorded arena results were comparatively favorable.[1]
- Reasonable candidate for long-context visual document analysis producing structured text, subject to workload testing.[1]
Sources
- [1] OpenRouter catalog · Z.ai: GLM 5V TurboSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...
Specifications
- Model ID
- z-ai/glm-5v-turbo
- Canonical ID
- z-ai/glm-5v-turbo-20260401
- Creator
- z-ai
- Added to OpenRouter
- 01.04.2026
- Context length
- 202,752
- Modality
- text+image+video->text
- Input modalities
- image, text, video
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $1.2 / out $4
- 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
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Design Arena | agents · agenticgamedevwin rate 42.6% · rank 24 | 1,049Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · agentichtmlslideswin rate 41.7% · rank 7 | 1,134Elo | —Not rated | 13.11.2026 |
| Design Arena | agents · agenticslideswin rate 51.6% · rank 5 | 1,171Elo | —Not rated | 13.11.2026 |
| Design Arena | agents · agenticslides(html)win rate 41.8% · rank 7 | 1,137Elo | —Not rated | 13.11.2026 |
| Design Arena | agents · agenticslides(python-pptx)win rate 53.9% · rank 5 | 1,183Elo | —Not rated | 13.11.2026 |
| Design Arena | agents · androidnativewin rate 54.8% · rank 5 | 1,267Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · fullstackwin rate 52.1% · rank 28 | 1,127Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · godotgamedevwin rate 26.9% · rank 35 | 940Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · htmlslideswin rate 44.6% · rank 23 | 1,017Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · mobileappswin rate 50.5% · rank 38 | 1,129Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · pptxslideswin rate 52.1% · rank 5 | 1,164Elo | —Not rated | 13.11.2026 |
| Design Arena | agents · python-pptxslideswin rate 51.9% · rank 17 | 1,165Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · webappswin rate 44.7% · rank 36 | 1,107Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · 3dwin rate 52.4% · rank 53 | 1,192Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · asciiartwin rate 42.6% · rank 59 | 1,113Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 49.6% · rank 59 | 1,219Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · datavizwin rate 47.6% · rank 61 | 1,200Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 49.5% · rank 50 | 1,208Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · svgwin rate 48.1% · rank 55 | 1,140Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 47.8% · rank 61 | 1,202Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 48.9% · rank 58 | 1,224Elo | BB — next 30% 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) |
|---|---|---|---|---|---|---|
| Z.AIfp8 | 202,752 | $1.2 | $4 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.