Zhipu AI (Z.ai)

GLM-4.5V

Generally availableOpen weights64K contextReasoning

Summary

GLM-4.5V is an open-weight language model from Zhipu AI (Z.ai), released on 11 Aug 2025. It accepts text, images and video and generates text, with a 64K-token context window and up to 16K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.60 per million input tokens and $1.80 per million output tokens (Z.ai API), across 5 providers we track. It is scheduled for retirement on 31 Dec 2026.

GLM vision model for visual reasoning, documents, and multimodal agents

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperZhipu AI (Z.ai)
Release date11 Aug 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licensemit [Hugging Face]
Parameters108B [Hugging Face]
Context window64K (64,000 tokens) [models.dev]
Max output16K tokens [models.dev]
Knowledge cutoffApr 2025 [models.dev]
InputText, images and video [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Retirement date31 Dec 2026 [OpenRouter]
Hugging Facezai-org/GLM-4.5V [Hugging Face]

GLM-4.5V API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Z.ai API
glm-4.5v
$0.60$1.80$0.1164Kmodels.dev, 18 Nov 2026
Hugging Face Inference Providers
zai-org/GLM-4.5V
$0.60$1.80–66Kmodels.dev, 18 Nov 2026
Novita AI
zai-org/glm-4.5v
$0.60$1.80$0.1166Kmodels.dev, 18 Nov 2026
OpenRouter
z-ai/glm-4.5v
$0.60$1.80$0.1166KOpenRouter, 18 Nov 2026
Vercel AI Gateway
zai/glm-4.5v
$0.60$1.80$0.1166Kmodels.dev, 18 Nov 2026

Running GLM-4.5V locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)65 GB68 GB72 GB
Q8_0 (8-bit)114 GB117 GB121 GB
FP16 / BF16 (16-bit)215 GB218 GB222 GB

At 4-bit with an 8K conversation, GLM-4.5V needs about 68 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of GLM-4.5V?

GLM-4.5V has a context window of 64,000 tokens (64K) and can generate up to 16,384 tokens in a single response, according to models.dev.

How much does the GLM-4.5V API cost?

Through Z.ai API, GLM-4.5V costs $0.60 per million input tokens and $1.80 per million output tokens. Prices last verified 18 Nov 2026.

Is GLM-4.5V open source?

GLM-4.5V is an open-weight model: its weights are published on Hugging Face as zai-org/GLM-4.5V under the mit license. Check the license terms before commercial use.

When was GLM-4.5V released?

Zhipu AI (Z.ai) released GLM-4.5V on 11 Aug 2025, according to models.dev.

Which providers offer GLM-4.5V?

We track GLM-4.5V on 5 providers: Z.ai API, Hugging Face Inference Providers, Novita AI, OpenRouter, Vercel AI Gateway.

How much VRAM does GLM-4.5V need?

About 68 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 117 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Qwen3 Omni 30B A3B ThinkingAlibaba (Qwen)22 Sept 202566K$0.25$0.97Open
Kimi K2 InstructMoonshot AI11 Jul 2025131K$0.57$2.30Open
Kimi-K2-InstructMoonshot AI11 Jul 2025131K$0.57$2.30Open
Magistral Small 1.2Mistral AI18 Sept 2025128K$0.50$1.50Open
Hermes-4-405BNousresearch26 Aug 2025131K$1$3Open
DeepSeek-R1DeepSeek20 Jan 202564K$0.70$2.50Open

Change history

  • Retirement date changed from none to 31 Dec 2026
  • Z.ai API price changed: input $0.60 → $0.60, output $1.80 → $1.80 per 1M tokens

Sources