About
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,...
Related Models
Pricing
Input
$0.60
per 1M tokens
Output
$1.80
per 1M tokens
Blended
$0.90
per 1M tokens
Cheaper than 38% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.90
Monthly
$27.00
vs. Similar Models
Qwen3 14B (Non-reasoning)Q:0.0
$0.38-58%
OpenAI: GPT-4Q:0.0
$37.50+4067%
Google: Gemini 2.5 Flash LiteQ:-0.1
$0.17-81%
Hermes 4 - Llama-3.1 70B (Non-reasoning)Q:-0.1
$0.20-78%
Performance
46
tokens/sec
Faster than 11% of models
11.55
seconds
Faster than 11% of models
11.55
seconds
Faster than 38% of models
Market Median
94 tok/s
51% slower
Median TTFT
1.11s
938% slower
Throughput/Dollar
51
tok/s per $/1M
Speed Comparison
Gemma 4 26B A4B (Non-reasoning)
46 tok/s-0%
Anthropic: Claude Opus 4.6
46 tok/s+0%
GLM-4.6V (Reasoning)
46 tok/s+0%
Context Window
66K
tokens
Larger than 13% of models
Max Output
16K
tokens
25% of context
Benchmarks
MMLU-Pro
75.1%
GPQA Diamond
57.3%
HLE
3.6%
LiveCodeBench
35.2%
SciCode
18.8%
TerminalBench Hard
6.8%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
15.3%
IFBench
28.6%
Long Context Recall
0.0%
Tau2
19.6%
Market AverageTop Score