BETA
Back to models

z-ai/glm-5.3-flash

llm Tools · Released Oct 18, 2026

Open-weights GLM-5.3 Flash for fast general chat and tool use.

Context length 1,048,576
Avg latency ~936ms
Requests served 300
Success rate 100.0%
Price per 1M tokens 0.70 / 2.34 SAR Input / output, pay-as-you-go

Quick start

from openai import OpenAI

client = OpenAI(
    base_url="https://alapi.deep.sa/v1",
    api_key="sk-alapi-...",
)

resp = client.chat.completions.create(
    model="z-ai/glm-5.3-flash",
    messages=[{"role": "user", "content": "مرحبا"}],
)

Each model and tool has its own price per 1M tokens View full pricing details

Activate account?

Activate this account?