Skip to content
LLMs
Z.ai logo

Z.ai: GLM 4.5V

by Z.ai

Z.ai: GLM 4.5V is a large language model from Z.ai. It costs $0.600 per million input tokens and $1.80 per million output tokens. Its context window is 66K tokens.

ReasoningTool callingStructured outputPrompt cachingOpen weightsimage input
Input / 1M tokens
$0.600
Output / 1M tokens
$1.80
Cached input / 1M
$0.110

On repeated prefixes

Context window
66K

tokens

Who serves it cheapest

2 hosts serve GLM 4.5V. Same weights, same API - the price difference is pure margin and routing.

Providers serving Z.ai: GLM 4.5V, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
NovitaCheapestfp8$0.600$1.8066K-94.3%
Z.AIfp8$0.600$1.8066K-95.3%

The spread between Novita and Z.AI is about the same for identical weights. Quantization and context limits differ, so check both columns before switching.

About GLM 4.5V

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,...

Specifications

Z.ai: GLM 4.5V specifications
Model IDz-ai/glm-4.5v
ProviderZ.ai
Context window66K tokens
Max output16K tokens
Input modalitiestext, image
Output modalitiestext
Knowledge cutoff2024-12-31
Open weightsYes - zai-org/GLM-4.5V
ReleasedAugust 11, 2025

Cheaper alternatives

Models that cost less than GLM 4.5V while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Z.ai: GLM 4.5V cost?

$0.600 per million input tokens and $1.80 per million output tokens. Cached input reads cost $0.110 per million tokens.

What is the context window of Z.ai: GLM 4.5V?

66K tokens, with up to 16K tokens of output per request.

Which provider serves Z.ai: GLM 4.5V cheapest?

Novita at $0.600 per million input tokens - about the same cheaper than Z.AI, the most expensive of the 2 hosts serving it.

Confirm against the source: Z.ai official pricing.