Saltar al contenido principal

GLM-4.5-Air

Z AIGLMOpen WeightMIT · Uso Comercial

Descripción

GLM-4.5-Air is a more compact variant of GLM-4.5 designed for efficient Agentic, Reasoning, and Coding (ARC) applications. It features 106 billion total parameters with 12 billion active parameters using MoE architecture. Like GLM-4.5, it is a hybrid reasoning model providing thinking mode for complex reasoning and tool usage, and non-thinking mode for immediate responses. Despite its compact design, GLM-4.5-Air delivers competitive performance with a score of 59.8 across 12 industry-standard benchmarks, ranking 6th overall while maintaining superior efficiency. It supports 128K context length and is released under MIT open-source license allowing commercial use.

Fecha de lanzamiento
2025-07-28
Parámetros
106.0B
Longitud del contexto
131K
Modalidades
text

Radar de capacidades

35
general
60
coding
79
reasoning
45
scienceest.
70
agents
0
multimodal

Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.

Rankings

Dominio#PosiciónPuntuaciónFuente
Capacidad agéntica84
51.0
LS
Ranking de codificación157
55.0
AA
Ranking general238
45.0
AA
Razonamiento matemático76
82.0
AA
Ciencia232
46.0
AA

Puntuaciones de benchmarks (LLM Stats)

Agents

BFCL-v376.4%Aut.
Terminal-Bench30.0%Aut.
BrowseComp21.3%Aut.

Biology

GPQA75.0%Aut.
SciCode37.3%Aut.

Code

LiveCodeBench70.7%Aut.
SWE-Bench Verified57.6%Aut.

Communication

TAU-bench Retail77.9%Aut.
TAU-bench Airline60.8%Aut.

Finance

MMLU-Pro81.4%Aut.

General

AA-Index64.8%Aut.

Math

MATH-50098.1%Aut.
AIME 202489.4%Aut.
Humanity's Last Exam10.6%Aut.

Índices de evaluación AA

Math Index
80.7
Intelligence Index
16.5
Math 500
1.0
Mmlu Pro
0.8
Aime 25
0.8
Gpqa
0.7
Livecodebench
0.7
Aime
0.7
Tau2
0.5
Lcr
0.4
Ifbench
0.4
Scicode
0.3
Terminalbench Hard
0.2
Hle
0.1

Puntuaciones por categoría LLM Stats

Language
80
Legal
80
Structured Output
80
Finance
80
Healthcare
80
General
70
Communication
70
Tool Calling
70
Math
60
Physics
60
Reasoning
60
Frontend Development
60
Biology
60
Chemistry
60
Code
50
Agents
40
Search
20
Vision
10

Precios

Precio de entrada$0.17 / 1M tokens
Precio de salida$0.98 / 1M tokens
Precio mixto (3:1)$0.372 / 1M tokens
Precio de lectura caché$0.03 / 1M tokens
Precio de escritura cachéGratis

Velocidad

Tokens/seg87.3
Retraso del primer token1.62s
Tiempo hasta la respuesta24.52s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

18 proveedores

Más barato: submodelMás caro: LLM Gateway
ProveedorEntradaSalida
1submodelMás barato
$0.1
$0.5
2ZenMux
$0.11
$0.56
3OpenRouter
$0.13
$0.85
4Hugging Face
$0.13
$0.85
5NovitaAI
$0.13
$0.85
6Kilo Gateway
$0.13
$0.85
7SiliconFlow (China)
$0.14
$0.86
8SiliconFlow
$0.14
$0.86
9Z AIPRINCIPAL
$0.17
$0.98
10Z.AI
$0.2
$1.1
11Vercel AI Gateway
$0.2
$1.1
12Zhipu AI
$0.2
$1.1
13OrcaRouter
$0.2
$1.1
14Merge Gateway
$0.2
$1.1
15NanoGPT
$0.2006
$0.2006
16Cortecs
$0.22
$1.34
17302.AI
$0.572
$1.714
18LLM Gateway
$1.1
$4.5

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas