GLM-4.5V

Z.ai·Pending·Released 2025-08-11textvisionvideo
Context64k
Max output16k
Input / 1M$0.6 ↗
Output / 1M$1.8 ↗
Cached in$0.11
Benchmarks17

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

LMArena Elo#127/1411352.4 ↗
AndroidWorld#2/557% ↗
ChartQAPro#2/464% ↗
Design2Code#3/582.2% ↗
MathVision#3/465.6% ↗
MathVista#3/684.6% ↗
MMBench v1.1#1/288.2% ↗
MMLongBench-Doc#3/344.7% ↗
MMMU (val)#3/475.4% ↗
MMMU Pro#2/365.2% ↗
MMStar#2/575.3% ↗
OCRBench#1/686.5% ↗
OSWorld#6/835.8% ↗
VideoMME (w/o sub)#3/474.6% ↗
VideoMMMU#3/572.4% ↗
WebVoyagerSom84.4% ↗

GLM-4.5V FAQ

What is GLM-4.5V?
GLM-4.5V is a large language model from Z.ai, released on August 11, 2025. It accepts text, image and video input.
When was GLM-4.5V released?
Z.ai released GLM-4.5V on August 11, 2025.
How much does GLM-4.5V cost?
GLM-4.5V costs $0.60 per 1M input tokens and $1.80 per 1M output tokens through the Z.ai API. Cached input costs $0.11 per 1M tokens. Prices are from Z.ai's official pricing as of October 5, 2026.
What is GLM-4.5V's context window?
GLM-4.5V has a 64K-token context window and can generate up to 16K output tokens.
How does GLM-4.5V score on benchmarks?
GLM-4.5V has 17 cited benchmark scores, including LMArena Elo 1352.4 Elo, LMArena Vision (LMArena) 1152.7 Elo and AndroidWorld 57%. Each score links to its source.

Access GLM-4.5V and every other model through one endpoint with automatic failover: Respan gateway.