GLM-5.3 — Specifications
Compilado por Mustafa Ihsan da documentação publicada pelo fornecedor · Última atualização
| Desenvolvedor | Zhipu AI |
|---|---|
| Tipo | LLM (codificação/agentes, MoE) |
| Modalidade | Texto → Texto |
| Parâmetros | 744B total / 40B active (MoE) |
| Janela de contexto | 1 milhão |
| Saída máxima | 128K |
| Licença | GLM-5.3 License (open weights) |
| Pesos abertos | Sim |
| Lançado | 2026-08 |
| Preço da entrada | $1.40 /1M |
| Preço da saída | $4.40 /1M |
| Provedores de API | Zhipu (Z.ai), Alibaba Cloud Model Studio, OpenRouter |
Benchmarks
| Z.ai-reported | Terminal Bench 3.0 28.3 (GLM-5.2: 4.6); DeepSWE v1.1 66.9 (GLM-5.2: 46.2); CyberGym 84.5 (GLM-5.2: 77.2). Cached input $0.26 per 1M tokens. |
|---|
What is GLM-5.3?
GLM-5.3 is Zhipu AI’s (Z.ai) latest flagship model, released on 18 August 2026. According to Z.ai, it uses the same base model as GLM-5.2, with every improvement coming from post-training: Z.ai reports a 50% gain over GLM-5.2 on its in-house Z.ai Code Bench and much stronger results at finding and exploiting software vulnerabilities, including 84.5% on CyberGym. It is a 744B-parameter mixture-of-experts with 40B active parameters. It takes text only, with a 1M-token context window and up to 128K output tokens, and it always reasons: effort can be set to low, high or max, but reasoning cannot be switched off.
Z.ai’s API charges $1.40 per million input tokens, $0.26 per million cached input tokens and $4.40 per million output tokens, with cache storage free for a limited time, the same price as GLM-5.2. Alibaba Cloud Model Studio also lists it at $1.40 / $4.40, and it is available to subscribers of Z.ai’s GLM Coding Plan. For cheaper work, GLM-5.3-Flash (320B total, 18B active) costs $0.15 in / $0.50 out.
The weights are on Hugging Face in FP8, a download of about 756 GB, under Z.ai’s GLM-5.3 License rather than the MIT licence of GLM 5.2. The licence is permissive, but Model-as-a-Service companies with more than $10 billion in revenue over 12 months must pass a Z.ai security review before commercial use. At the same price, GLM-5.3 is the natural pick over GLM 5.2 for new projects; compare monthly costs with the Calculadora de custos de API de IA.
GLM-5.3 pricing: API cost per 1M tokens
| Entrada (por 1 milhão de tokens) | $1.40 |
|---|---|
| Saída (por 1 milhão de tokens) | $4.40 |
| Razão saída/entrada | 3.1× |
| Misturada (4:1 entrada:saída) | $2.00 por 1 milhão de tokens |
What GLM-5.3 costs per month
Gasto mensal real com uma proporção de entrada para saída de 4:1 — a razão efetivamente gerada por cargas de trabalho típicas de chat ou RAG.
| Carga de trabalho | Tokens/mês | Custo por mês |
|---|---|---|
| Projeto paralelo | 1 milhão de tokens de entrada / 0,25 milhão de tokens de saída | $2.50 |
| Equipe pequena | 20 milhões de tokens de entrada / 5 milhões de tokens de saída | $50 |
| Produção | 200 milhões de tokens de entrada / 50 milhões de tokens de saída | $500 |
Calcule seus próprios números na Calculadora de custos de API de IA.
Cheaper alternatives to GLM-5.3
| Modelo | Custo médio ponderado por US$ 1 milhão | Você economiza |
|---|---|---|
| Llama 3.1 8B aberta | $0.0240 | 99% mais barato |
| Mistral NeMo 12B aberta | $0.0292 | 99% mais barato |
| Gemma 3 4B aberta | $0.0600 | 97% mais barato |
Perguntas frequentes
How much does GLM-5.3 cost per 1M tokens?
GLM-5.3 costs $1.40 per 1M input tokens and $4.40 per 1M output tokens. At a typical 4:1 input-to-output mix that blends to about $2.00 per 1M tokens.
How much does GLM-5.3 cost per month?
A small-team workload of 20M input and 5M output tokens a month costs about $50 on GLM-5.3. A side project (1M in / 0.25M out) costs roughly $2.50.
What is a cheaper alternative to GLM-5.3?
Llama 3.1 8B is the strongest cheaper option in our database at $0.0240 per 1M blended — about 99% less than GLM-5.3. It is also open-weight, so self-hosting is an option.
Can I run GLM-5.3 locally?
Yes. GLM-5.3 is open-weight and needs about a large amount of VRAM at 4-bit quantisation.
Why does GLM-5.3 charge more for output than input?
Output tokens are generated one at a time and cannot be batched the way a prompt can, so they cost the provider more to serve. GLM-5.3 charges 3.1× more for output, which is why prompt-heavy workloads are far cheaper to run than generation-heavy ones.
Os preços correspondem às tarifas listadas oficialmente para a API principal do modelo e são revisados conforme os provedores os atualizam. Descontos por volume, processamento em lote ou entradas em cache não estão incluídos. Compare todos os modelos lado a lado na Banco de dados de modelos de IA ou o Ranking de LLMs.