Skip to main content
Models

GLM-5.3

Model Overview

Direct supply
ChatStreamingToolsThinkingCache

GLM-5.3: Zhipu's flagship text model with a 1M-token context window and 128K max output. Markedly stronger at complex software engineering, terminal operation and agent tasks, with deep thinking always on.

Input Modalities

Text

Output Modalities

Text

Recommended for

Ideal for intelligent dialogue scenarios requiring chat, streaming, tools, deep thinking, and cache optimization.

Capabilities

Chat

Multi-turn conversational completions

Streaming

Tokens are delivered incrementally as they are generated

Tool Use

Can call functions/tools defined in the request

Thinking

Produces an extended internal reasoning trace before the final answer

Prompt Caching

Reuses previously processed prompt prefixes at a lower rate

Supported Modes

Chat

Model Pricing

40% off
Pay-as-you-go

Full Pricing Breakdown

Every billed dimension for GLM-5.3

Token Pricing

Cache Read$0.298$0.179per 1M tokens
Input$1.191$0.715per 1M tokens
Output$4.167$2.50per 1M tokens
Thinking$2.50per 1M tokens

Indicative pricing — final cost is confirmed at request time.

Time-based Pricing

  • Defaultall other times$0.715 / $2.50per 1M tokensCache read $0.179
  • CN Night 00:00-08:00 (UTC+8)every day 16:00–24:00 UTC$0.358 / $1.25per 1M tokensCache read $0.09

Window times follow the timezone shown; requests crossing a window boundary are billed by the window the request started in.

Context & Limits

Context Window
1,000,000 tokens
Max Output
131,072 tokens

Response speed

Typical response time
26.7 s

Median of 128 successful requests over the last 7 days

API Code Example

Get API Key
OpenAI Compatible
import openai
 
client = openai.OpenAI(
base_url="https://api.modelsite.ai/v1",
api_key="sk-ms-...",
)
 
response = client.chat.completions.create(
model="glm-5.3",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)