This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.

Z AI has launched a newer model, GLM-4.7-Flash. We suggest considering it instead.

For more information, see comparison of GLM-4.7-Flash to other models and API provider benchmarks for GLM-4.7-Flash.

GLM-4.5-Air logo
Z AI
•

Open weights model

•

Released July 2025

Análise de inteligência, desempenho e preço do GLM-4.5-Air

Benchmarks de provedores de API

Resumo do modelo

Inteligência

17
Artificial Analysis Intelligence Index
4 de 4 unidades para Inteligência.

Velocidade

89.8
Tokens de saída por segundo
2 de 4 unidades para Velocidade.

Preço de entrada

US$ 0,17
USD por 1M de tokens
3 de 4 unidades para Preço de entrada.

Preço de saída

US$ 0,98
USD por 1M de tokens
4 de 4 unidades para Preço de saída.

Verbosidade

N/D
Tokens de saída do Intelligence Index
Valor desconhecido entre 4 unidades para Verbosidade.

GLM-4.5-Air está entre os modelos líderes em inteligência, mas tem preço um pouco alto em comparação com outros modelos de pesos abertos de tamanho semelhante. O modelo aceita entrada em texto, gera saída em texto e tem uma janela de contexto de 128k tokens.

GLM-4.5-Air alcança 17 pontos no Artificial Analysis Intelligence Index, ficando bem acima da média entre os modelos comparáveis (mediana: 9).

O preço do GLM-4.5-Air é de $0.17 por 1M de tokens de entrada (preço um pouco alto, mediana: $0.15) e $0.98 por 1M de tokens de saída (preço alto, mediana: $0.45).

Com 90 tokens por segundo, GLM-4.5-Air é mais lento que a média (94).

RaciocínioSim

Esta página mostra a versão com raciocínio deste modelo.

Também pode existir uma variante sem raciocínio.

Modalidade de entrada

Compatível com: texto

Modalidade de saída

Compatível com: texto

Janela de contexto128k
~192 páginas A4 em fonte Arial tamanho 12
Parâmetros totais106B
Parâmetros ativos12B
Número de parâmetros ativos por token durante a inferência
LicençaMIT
Pesos do modeloHugging Face

As métricas são comparadas com modelos da mesma classe:

  • Modelos sem raciocínio → comparados apenas com outros modelos sem raciocínio
  • Modelos de raciocínio → comparados com modelos com e sem raciocínio
  • Modelos de pesos abertos → comparados apenas com outros modelos de pesos abertos da mesma classe de tamanho:
    • Muito pequeno: ≤4B parâmetros
    • Pequeno: 4B–40B parâmetros
    • Médio: 40B–150B parâmetros
    • Grande: >150B parâmetros
  • Modelos proprietários → comparados com modelos proprietários e de pesos abertos da mesma faixa de preço, usando uma proporção combinada de 3:1 entre os preços de entrada e saída:
    • <$0.15 por 1M de tokens
    • $0.15–$1 por 1M de tokens
    • >$1 por 1M de tokens

Destaques

Inteligência

Artificial Analysis Intelligence Index · Higher is better

Velocidade

Output tokens per second · Higher is better

Custo por tarefa

Weighted average cost (USD) per Intelligence Index task · Lower is better

Inteligência

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Estimate (independent evaluation forthcoming)
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Estimate (independent evaluation forthcoming)
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if the weights are available but commercial use is limited (typically requires obtaining a paid license).

Avaliações

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
GDPval-AA v2

Agentic real-world work tasks, (Elo-500)/2000

𝜏³-Banking

Agentic tool use

Terminal-Bench v2.1

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR

Long context reasoning

AA-Briefcase

Agentic knowledge work, Elo

AutomationBench-AA

Agentic SaaS workflows

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AANew

Agentic business operations

IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

Reasoning models are indicated by a lightbulb icon

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

AA-Omniscience

AA-Omniscience Index

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.
Reasoning models are indicated by a lightbulb icon

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.

Openness Index

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)
Reasoning models are indicated by a lightbulb icon

Comparações do Intelligence Index

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
Pareto line
Reasoning models are indicated by a lightbulb icon

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Custo

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better
Reasoning models are indicated by a lightbulb icon

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index
Reasoning models are indicated by a lightbulb icon

The cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens)
Reasoning models are indicated by a lightbulb icon

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Janela de contexto

Context Window

Context window: tokens limit · Higher is better
Reasoning models are indicated by a lightbulb icon

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Velocidade

Medida pela velocidade de saída (tokens por segundo)

Output Speed

Output tokens per second · Higher is better
Reasoning models are indicated by a lightbulb icon

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Time per Intelligence Index Task

Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better
Reasoning models are indicated by a lightbulb icon

The weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.

Latência

Medida pelo tempo (segundos) até o primeiro token

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time
Reasoning models are indicated by a lightbulb icon

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

Tempo de resposta de ponta a ponta

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better
Reasoning models are indicated by a lightbulb icon

Seconds to receive a 500 token response. Key components:

  • Input time: Time to receive the first response token
  • Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
  • Answer time: Time to generate 500 output tokens, based on output speed

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Tamanho do modelo (somente modelos de pesos abertos)

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference
Reasoning models are indicated by a lightbulb icon

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

Perguntas frequentes

Perguntas comuns sobre o GLM-4.5-Air

O GLM-4.5-Air foi lançado em 28 de julho de 2025.

Z AI criou o GLM-4.5-Air.

GLM-4.5-Air alcança 17 pontos (estimativa) no Artificial Analysis Intelligence Index, ficando bem acima da média entre outros modelos de pesos abertos de tamanho semelhante (mediana: 9).

GLM-4.5-Air gera a saída a 89.8 tokens por segundo (com base na mediana dos provedores que oferecem o modelo), um resultado abaixo da média em comparação com outros modelos de pesos abertos de tamanho semelhante (mediana: 94.4 t/s).

GLM-4.5-Air tem um tempo até o primeiro token (TTFT) de 2.60s (com base na mediana dos provedores que oferecem o modelo), um resultado na faixa superior em comparação com outros modelos de pesos abertos de tamanho semelhante (mediana: 1.77s).

GLM-4.5-Air custa $0.17 por 1M de tokens de entrada (melhor que a média, mediana: $0.40) e $0.98 por 1M de tokens de saída (um pouco acima da média, mediana: $0.71), com base na mediana dos provedores que oferecem o modelo.

GLM-4.5-Air custa $0.17 por 1M de tokens de entrada e $0.98 por 1M de tokens de saída (com base na mediana dos provedores que oferecem o modelo). Considerando uma tarifa combinada (proporção de 7:2:1 entre acerto do cache, entrada e saída), o preço é de $0.25 por 1M de tokens. O preço pode variar conforme o provedor. Comparar preços dos provedores

Sim, o GLM-4.5-Air é um modelo de raciocínio. Ele usa reflexão prolongada ou raciocínio em cadeia para resolver problemas complexos antes de fornecer uma resposta.

GLM-4.5-Air aceita entrada em texto.

GLM-4.5-Air permite saída em texto.

Não, o GLM-4.5-Air não aceita imagens como entrada. Ele só consegue processar texto.

Não, o GLM-4.5-Air não é multimodal. Ele aceita apenas entrada em texto.

GLM-4.5-Air tem uma janela de contexto de 130k tokens. Isso determina quanto texto e histórico da conversa o modelo consegue processar em uma única solicitação.

Sim, o GLM-4.5-Air é um modelo de pesos abertos. Os pesos estão disponíveis publicamente e podem ser baixados para auto-hospedagem.

GLM-4.5-Air tem 106 bilhões parâmetros (12 bilhões ativos).

GLM-4.5-Air é um modelo de mistura de especialistas (MoE) com 106 bilhões parâmetros no total, mas apenas 12 bilhões parâmetros ativos são usados durante a inferência.

GLM-4.5-Air foi lançado sob a licença MIT. Essa licença permite o uso comercial. Ver licença

GLM-4.5-Air alcança 17 pontos no Artificial Analysis Intelligence Index. Esse benchmark composto avalia os modelos em raciocínio, conhecimento, matemática e programação.

Sim, o GLM-4.5-Air está disponível por API em 2 provedores. Comparar provedores de API

GLM-4.5-Air está disponível em 2 provedores de API. Comparar provedores