GLM-4.5 Flash

glm-4.5-flash

The GLM-4.5 series is built for agent-style AI, combining reasoning, coding, and tool use. GLM-4.5 has 355B total parameters (32B active), while GLM-4.5-Air is a lighter 106B/12B version. Both support hybrid modes — a “thinking” mode for complex reasoning and tools, and a fast non-thinking mode for quick replies. The models are open-sourced (including FP8 versions) under the MIT license for commercial use, and they rank highly on benchmarks: GLM-4.5 scores 63.2 (3rd overall), while GLM-4.5-Air achieves 59.8 with better efficiency.

Context: 128K tokens
Endpoint

Get API Key Compare

Pricing

Input$0.014 / 1M

Output$0.056 / 1M

Cache Write (5m)$0.014 / 1M

Cache Write (1h)$0.014 / 1M

Cache Read$0.014 / 1M

Web Search$0 / 1M

Quick Start

Select an endpoint and copy a working example for this model.

Endpoint

python

from openai import OpenAI client = OpenAI(    api_key="YOUR_API_KEY",    base_url="https://api.apertis.ai/v1") response = client.chat.completions.create(    model="glm-4.5-flash",    messages=[        {"role": "user", "content": "Hello!"}    ],    max_tokens=1024,    temperature=0.7) print(response.choices[0].message.content) # Optional: Enable context compression to reduce token usage# response = client.chat.completions.create(#     model="glm-4.5-flash",#     messages=[{"role": "user", "content": "Hello!"}],#     extra_body={"compression": {"enabled": True, "model": "gpt-4.1-mini"}}# )

Supported Parameters

API docs

Common7 params

modelmessagesmax_tokenstemperaturetop_pstreamtools

Extended4 params

reasoning_effortstream_optionsthinkingextra_body

Cursor IDE Model IDs

Use these namespaced identifiers in Cursor IDE to avoid conflicts with built-in models.

glm-4.5-flash

Compare with Other Models

See how this model compares to others from the same provider.

GLM 5.3 Flash

GLM-5.3-Flash is Z.AI's efficient native multimodal model, designed for coding and long-horizon agentic workflows. It combines strong multimodal capabilities with an architecture optimized for responsive, cost-efficient task execution. Built on a hybrid sparse and linear attention architecture, GLM-5.3-Flash maintains accurate long-context behavior while reducing computational overhead, making it well suited for coding agents, extended multi-step tasks, and scalable production workloads.

Context: 1M
Input: $0.075/M
Output: $0.25/M

GLM 5.3

GLM-5.3 is Z.ai's large-scale reasoning model designed for complex software engineering and long-horizon agentic workflows. It supports text input and output with a 1M-token context window, enabling sustained reasoning across large codebases and extended multi-step tasks. Building on GLM-5.2, it delivers stronger coding performance while improving the balance between capability and token efficiency, making it well suited for autonomous coding agents, large-scale engineering workflows, and complex task execution.

Context: 1M
Input: $1.40/M
Output: $4.40/M

GLM-4.7 (Thinking)

GLM-4.7 is Z.AI's newest flagship model, upgraded for stronger programming performance and more reliable multi-step reasoning. It handles complex agent tasks better while offering smoother conversations and improved UI/experience quality.

Context: 202.8K
Input: $0.30/M
Output: $0.50/M

GLM 4.6 (Thinking)

GLM-4.6 improves on GLM-4.5 with a larger 200K context window, stronger coding performance (including better real-world agent tools like Claude Code and Cline), and clearer gains in reasoning with built-in tool use. It delivers more capable agent behavior, integrates better into agent frameworks, and produces more natural, readable writing — especially in role-playing scenarios.

Context: 202.8K
Input: $0.40/M
Output: $1.50/M