Z.ai · Released Dec 8, 2025
GLM 4.6V
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...
- Released
- Dec 8 2025
- Context window
- 131K 33K out
- Input / 1M tokens
- $0.30 from $0.14
- Output / 1M tokens
- $0.90 from $0.41
Where to run it
15 providers compared
Included in Zhipu AI Coding Plan. Cheapest: AIHubMix at $0.14 / $0.41 per 1M input / output tokens — 67% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Zhipu AI Coding Plansubscription plan | Plan | Plan | Plan | 128K | 33K | — | Plan |
| AIHubMix | $0.14 | $0.41 | $0.027 | 128K | 33K | — | Cheapest |
| 302.AI | $0.14 | $0.43 | — | 128K | 33K | — | +5% |
| ZenMux | $0.15 | $0.44 | $0.029 | 200K | 128K | — | +6% |
| Zhipu AI | $0.15 | $0.45 | $0.03 | 128K | 33K | — | +9% |
| NovitaBF16 | $0.30 | $0.90 | $0.055 | 131K | 33K | 99.8%24h | +119% |
| Z.AIFP8 | $0.30 | $0.90 | $0.05 | 131K | 33K | 95.3%24h | +119% |
| NanoGPTno tool calling | $0.30 | $0.90 | $0.15 | 128K | 24K | — | +119% |
| Kilo Gateway | $0.30 | $0.90 | $0.055 | 131K | 33K | — | +119% |
| LLM Gateway | $0.30 | $0.90 | $0.055 | 131K | 16K | — | +119% |
| Novita AI | $0.30 | $0.90 | $0.055 | 131K | 33K | — | +119% |
| Tempr Gateway | $0.30 | $0.90 | $0.05 | 128K | 33K | — | +119% |
| DevPass (LLM Gateway) | $0.30 | $0.90 | $0.05 | 131K | 33K | — | +119% |
| Eden AI | $0.30 | $0.90 | $0.05 | 131K | 33K | — | +119% |
| AI/ML API | $0.41 | $1.24 | $0.076 | 131K | 33K | — | +201% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated GLM 4.6V. Scores appear here automatically once it does.
Specs
Details
- Model ID
z-ai/glm-4.6v- Developer
- Z.ai
- Release date
- Dec 8, 2025 ·
- Context window
- 131,072 tokens
- Max output
- 32,768 tokens
- API price
- $0.30 / $0.90 per 1M input / output tokens
- Providers
- 15
- Input types
- image, text, video
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.