GLM-4.6V

Z.ai·Pending·Released 2025-12-08textvisionvideo
Context128k
Max output32k
Input / 1M$0.3 ↗
Output / 1M$0.9 ↗
Cached in$0.05
Benchmarks17

Benchmarks

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

LMArena Elo#119/1411378.7 ↗
AndroidWorld#2/557% ↗
ChartQAPro#1/465.5% ↗
CharXiv_Val-Reasoning#1/263.2% ↗
Design2Code#2/588.6% ↗
MathVista#2/685.2% ↗
MMBench V1.1#1/288.8% ↗
MMBrowseComp#1/27.6% ↗
MMLongBench-Doc#1/354.9% ↗
MMMU (Val)#1/276% ↗
MMMU_Pro#3/466% ↗
MMStar#1/575.9% ↗
OCRBench#1/686.5% ↗
OSWorld#5/837.2% ↗
VideoMMMU#2/574.7% ↗
WebVoyager#2/381% ↗

GLM-4.6V FAQ

What is GLM-4.6V?
GLM-4.6V is a large language model from Z.ai, released on December 8, 2025. It accepts text, image and video input.
When was GLM-4.6V released?
Z.ai released GLM-4.6V on December 8, 2025.
How much does GLM-4.6V cost?
GLM-4.6V costs $0.30 per 1M input tokens and $0.90 per 1M output tokens through the Z.ai API. Cached input costs $0.05 per 1M tokens. Prices are from Z.ai's official pricing as of October 5, 2026.
What is GLM-4.6V's context window?
GLM-4.6V has a 128K-token context window and can generate up to 32K output tokens.
How does GLM-4.6V score on benchmarks?
GLM-4.6V has 17 cited benchmark scores, including LMArena Elo 1378.7 Elo, LMArena Vision (LMArena) 1161.5 Elo and AndroidWorld 57%. Each score links to its source.

Access GLM-4.6V and every other model through one endpoint with automatic failover: Respan gateway.