z-ai
Z.ai: GLM 4.6
z-ai/glm-4.6
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
GLM-4.6 is a text-in, text-out model from Z.ai listed on OpenRouter with a 204,800-token context window and a knowledge cutoff of 2025-03-31. Z.ai's model card reports gains over GLM-4.5 in coding, reasoning, tool use, and agentic tasks, plus more refined writing and role-play; these are vendor claims. OpenRouter arena data shows mixed measured results, near or above break-even in most listed design and agent categories but weaker in fullstack and mobile-app agent tasks. Evidence is limited to the vendor card and the catalog, so workload validation is advised.[1][2]
Strengths
- Context window expanded to roughly 200K tokens, up from 128K in GLM-4.5, per the vendor card and catalog.[1][2]
- Vendor-reported improvements in coding, reasoning, and tool-using agent behavior; the catalog exposes tools, structured outputs, and reasoning parameters.[1][2]
- Measured arena results are near or above break-even in most listed design and agent categories.[1]
Limitations
- Evidence is a vendor model card plus a catalog listing; no independent evaluation was supplied, so results need validation on your workload.[1][2]
- Text-only input and output in the catalog; no multimodal capability is evidenced.[1]
- Knowledge cutoff is 2025-03-31, and measured arena performance is mixed, falling below break-even in fullstack and mobile-app agent tasks.[1]
Where to use it
- Worth evaluating for long-context document or agentic workflows that can use the roughly 200K-token window.[1][2]
- Candidate for coding assistance and front-end page generation, where the vendor reports gains; verify on your own stack.[1][2]
- May fit search- and tool-integrated agents, per the vendor card; the catalog confirms tool and reasoning parameters.[1][2]
Sources
- [1] OpenRouter catalog · Z.ai: GLM 4.6Sources checked: Nov 13, 2026
- [2] Model documentation · Z.ai: GLM 4.6Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...
Specifications
- Model ID
- z-ai/glm-4.6
- Creator
- z-ai
- Added to OpenRouter
- 30.09.2025
- Context length
- 204,800
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.500 / out $2
- Knowledge cutoff
- 31.03.2025
- 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 | BB — next 30% of the cohort | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| 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 | Coding index | 45.8 | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · androidnativewin rate 52.8% · rank 37 | 1,072Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · fullstackwin rate 42.3% · rank 40 | 1,007Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · godotgamedevwin rate 53.2% · rank 15 | 1,180Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · mobileappswin rate 47.2% · rank 41 | 1,090Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · 3dwin rate 54.2% · rank 86 | 1,111Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 54.3% · rank 85 | 1,156Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 52.6% · rank 78 | 1,159Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 54.8% · rank 79 | 1,141Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · svgwin rate 52.1% · rank 66 | 1,100Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 52.5% · rank 87 | 1,138Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 54.3% · rank 84 | 1,167Elo | CC — below the B band | 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 | 202,752 | $0.400 | $1.6 | — | — | — |
| Venicefp4 | 198,000 | $0.430 | $1.75 | — | — | 100% |
| DeepInfrafp4 | 202,752 | $0.500 | $2 | — | — | 100% |
| Novitabf16 | 204,800 | $0.550 | $2.2 | — | — | 100% |
| Z.AIfp4 | 202,752 | $0.600 | $2.2 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.