Back to models

z-ai/glm-5.3

llm Tools · Released Oct 07, 2026

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

Context length 1,048,576
Avg latency —
Requests served 0
Success rate —
Cost per message 12 credits tokens per credit: 266 in / 88 out

Quick start

from openai import OpenAI

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

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

Saudi-hosted models and our tools cost 1 request per call, whatever the size. Global models use credits View full pricing details

Activate account?

Activate this account?