GLM-5.3-Flash

Z.ai’s fast GLM model for coding and agentic tasks, built to do more with less compute. It reads images as well as text, with a context of a million tokens.

Get an API key API & docs

GLM-5.3-Flash Z.ai

Context: 1M; tokens
Inputs: Text and images

Best for

Coding and agents
Visual coding
Office work

What it does best.

Coding and agents: Write and fix code, and run multi-step work with tools.
Visual coding: Code from a screenshot, a mock-up or a diagram: images go in with the prompt.
Office work: Documents, slides and spreadsheets as output.

It mines while it answers.

On the Peryn API, every request mines as much $PEARL as it can while it is served: inside the AI work, and in the gaps between requests.

How Peryn works

The model.

Made by: Z.ai
Context: 1M tokens, up to 128K out
Size: 320B parameters, mixture of experts: 18B active per token
Inputs: Text and images
Licence: MIT
Official name: GLM-5.3-Flash

From Z.ai’s official model card.

One call, OpenAI-compatible.

Use the OpenAI SDK: set our base URL and your key, and keep your code.

import osfrom openai import OpenAI client = OpenAI(base_url="https://api.peryn.ai/v1",api_key=os.environ["PERYN_API_KEY"],) stream = client.chat.completions.create(model="glm-5.3-flash",messages=[{"role": "user", "content": "Hello"}],stream=True,)for chunk in stream:if chunk.choices:print(chunk.choices[0].delta.content or "", end="")

Other models on Peryn: DeepSeek V4.1 Flash · MiniMax M3.1 Flash · Hy4