GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...
Tested on 1 benchmarks. Top scores: Chatbot Arena Elo · Overall (1352.4%).
Chatbot Arena overall Elo rating. Crowdsourced human preference ranking from blind head-to-head comparisons across all topics.
- Typemultimodal
- Context66K tokens (~33 books)
- ReleasedAug 2025
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.003
Frequently Asked Questions
Related Models
ERNIE-5.5-Flash-Preview (free) · baiduQwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteJais 3 0.9B · MBZUAIBenchmarks
Chatbot Arena Elo · OverallIdentifiers and sizes
- Hugging Face repo · zai-org/GLM-4.5V
- License · mit
- Total parameters · 108B (107,710,933,120) · source Hugging Face safetensors · fetched 2026-11-14
- Weights as published · 215 GB in BF16, F32 (computed from the safetensors tensor counts per dtype)
- Weights size, computed · 215 GB at BF16/FP16 · 108 GB at INT8/Q8 · 53.9 GB at Q4 (computed from the parameter count, not measured; excludes KV cache and runtime overhead)
Key facts · as of 2026-11-22
- GLM 4.5V by z-ai. Not enough public benchmark scores to rank yet.
- List price $0.60 input · $1.80 output per 1M tokens (as of 2026-11-22).
- Sold by 2 providers (as of 2026-11-22): Novita (fp8) $0.60 in / $1.80 out · Z.AI (fp8) $0.60 in / $1.80 out. Every provider
How to cite · data as of 2026-11-22
GLM 4.5V · benchmarks, pricing and providers. BenchGecko, data as of 2026-11-22. https://benchgecko.ai/model/glm-4-5v
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP