Zhipu AI model product
GLM 4.5V
5-Air (106B total, 12B active) that extends hybrid reasoning to images and video.
Updated Aug 17, 2026. Default version: GLM-4.5V
LLMBoard Text Score31.1GLM-4.5V
Coverage100%17 benchmark families
Context window64KTokens
Official input price$0.60Zhipu AI API
GLM 4.5V Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GLM 4.5V Benchmark Results
Benchmark scores for GLM-4.5V.
No benchmark results
No benchmark result is linked to the scored version.
GLM 4.5V Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categoryoverall | Rank96 | Rating / score1156.4 | Votes3,279 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank96 | Rating / score1155.6 | Votes3,279 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank190 | Rating / score1353.4 | Votes4,973 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank197 | Rating / score1333.7 | Votes4,973 | ObservationsN/A | Result date |
GLM 4.5V Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.60 input, $1.8 output per 1M
- Official provider
- Zhipu AI
- Lowest third-party
- From $0.29 input, $0.86 output per 1M via 302.AI
- Tracked offerings
- 12
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| Provider302.AI | Provider model IDglm-4.5v | Regionglobal | Input / 1M$0.29 | Output / 1M$0.86 | Context64K | Updated |
| ProviderNanoGPT | Provider model IDz-ai/glm-4.5v | Regionglobal | Input / 1M$0.60 | Output / 1M$1.8 | Context64K | Updated |
| ProviderHugging Face | Provider model IDzai-org/GLM-4.5V | Regionglobal | Input / 1M$0.60 | Output / 1M$1.8 | Context65.5K | Updated |
| ProviderJiekou.AI | Provider model IDzai-org/glm-4.5v | Regionglobal | Input / 1M$0.60 | Output / 1M$1.8 | Context65.5K | Updated |
| ProviderOpenRouter | Provider model IDz-ai/glm-4.5v | Regionglobal | Input / 1M$0.60 | Output / 1M$1.8 | Context65.5K | Updated |
| ProviderZ.AI | Provider model IDglm-4.5v | Regionglobal | Input / 1M$0.60 | Output / 1M$1.8 | Context64K | Updated |
| ProviderMerge Gateway | Provider model IDzai/glm-4.5v | Regionglobal | Input / 1M$0.60 | Output / 1M$1.8 | Context128K | Updated |
| ProviderZhipu AI | Provider model IDglm-4.5v | Regionglobal | Input / 1M$0.60 | Output / 1M$1.8 | Context64K | Updated |
| ProviderVercel AI Gateway | Provider model IDzai/glm-4.5v | Regionglobal | Input / 1M$0.60 | Output / 1M$1.8 | Context66K | Updated |
| ProviderNovitaAI | Provider model IDzai-org/glm-4.5v | Regionglobal | Input / 1M$0.60 | Output / 1M$1.8 | Context65.5K | Updated |
| ProviderLLM Gateway | Provider model IDglm-4.5v | Regionglobal | Input / 1M$0.60 | Output / 1M$1.8 | Context128K | Updated |
| ProviderKilo Gateway | Provider model IDz-ai/glm-4.5v | Regionglobal | Input / 1M$0.60 | Output / 1M$1.8 | Context65.5K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GLM 4.5V Runtime Performance
Provider-specific output speed and catalog latency for GLM-4.5V. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GLM 4.5V Specifications
Technical details for the model's default version.
- Version
- GLM-4.5V
- Released
- Aug 11, 2025
- Knowledge cutoff
- Apr 1, 2025
- Parameters
- 108B
- Context window
- 64K
- Max output
- 16.4K
- Inputs
- image, text, video
- Outputs
- text
- Open weights
- Yes
- License
- MIT
GLM 4.5V Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGLM-4.5V | Released | LLMBoard31.1 | Parameters108B | Context64K | Max output16.4K | Open weightsYes | LicenseMIT |
GLM 4.5V vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to GLM 4.5V
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ZA
GLM 4.7 Flash
Zhipu AI
ZA
GLM 4.5 Air
Zhipu AI
ZA
GLM 4.5
Zhipu AI
ZA
GLM 4.7
Zhipu AI
ZA
GLM 4.6
Zhipu AI
ZA
GLM 5V Turbo
Zhipu AI
What is GLM 4.5V?
Key information about GLM 4.5V and its available data.
5-Air (106B total, 12B active) that extends hybrid reasoning to images and video. It achieves state-of-the-art results across 40+ VLM benchmarks (image reasoning, video understanding, GUI tasks, chart/document parsing, grounding) while supporting a Thinking Mode switch for deep reasoning.
Released under MIT with FP8/BF16 variants and tooling in Transformers, vLLM, and SGLang.
Data as of 2026-08-17.
FAQ
Common questions about GLM 4.5V.
When was GLM 4.5V released?
GLM 4.5V's default version was released on Aug 11, 2025.
How much does GLM 4.5V cost?
GLM 4.5V's official API price is $0.60 per million input tokens and $1.8 per million output tokens via Zhipu AI. The lowest tracked third-party offer starts at $0.29 input and $0.86 output via 302.AI.
Who created GLM 4.5V?
GLM 4.5V was created by Zhipu AI.
What is the context window for GLM 4.5V?
The default version has a 64K token context window.
Is GLM 4.5V open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer GLM 4.5V?
12 provider offerings are linked to the default version.
What models should I compare GLM 4.5V with?
Nearby ranked alternatives include Magistral Small, Llama 3.3 Nemotron Super 49B, Qwen3 30B A3B.