GLM 5.3 Flash API

GLM 5.3 Flash reads text and images and writes code for teams running coding agents at volume. From $0.081 per million input tokens.

Get API key Read the docs

1.3M token context
321.3B total parameters
18B active parameters
MIT licensed weights

from openai import OpenAI

client = OpenAI(
    base_url="https://api.modelsheep.com",
    api_key=API_KEY_MODELSHEEP,
)

response = client.chat.completions.create(
    model="zai-org/GLM-5.3-Flash",
    messages=[
        {
            "role": "user",
            "content": "Why do sheep count people?"
        }
    ],
)

print(response.choices[0].message.content)

How to use the GLM 5.3 Flash API

1
Create a ModelSheep account and copy an API key from the dashboard.
2
Point the OpenAI SDK at the base url https://api.modelsheep.com and pass zai-org/GLM-5.3-Flash as the model string.
3
Send your messages to /chat/completions with reasoning_effort set, then read the answer from choices[0].message.content.

What GLM 5.3 Flash is

GLM 5.3 Flash is an open weight model from Z.ai. It is the first GLM 5 series model to accept images and text together, trained on a new multimodal base rather than tuned from an older model. The architecture mixes sparse and linear attention, which lowers the cost of a long context. It activates a small share of its weights per token, and Z.ai reports it beats GLM 5.2 on benchmarks at one tenth the price.

What it does well

Fixes a bug across a repository via a terminal coding agent.
Drives a tool loop such as a browser session or automation chain.
Reads a screenshot or scanned page and answers in text.

What it is not for

Work needing a direct answer without reasoning. The model has no setting to turn thinking off. reasoning_effort lowers the budget, but every reply uses thinking tokens.
Languages beyond English and Chinese. The model card lists only those two. Test your language before shipping.

Calling it

Call /chat/completions with the OpenAI SDK and pass zai-org/GLM-5.3-Flash as the model string. Watch the reasoning_effort parameter. It accepts low, high, or max. It defaults to max if omitted or if you send an unknown value. A request meant to run cheaply may run at the full thinking budget.

zai-org/GLM-5.3-Flash /chat/completions

SDKs and languages

GLM 5.3 Flash answers on an HTTP endpoint, so any language that can post JSON reaches it. These are the ones the box above writes out.

OpenAI SDK: PythonTypeScriptGoJavaC#PHPRust
Anthropic SDK: PythonTypeScriptGoJavaC#PHPRust
HTTP: cURLPythonTypeScriptGoRustJavaC#PHP

Specifications

Author	Z.ai
Category	language
Accepts	text, image, video
Returns	text
Total parameters	321.3B
Active parameters	18B
Score	41.9 on Artificial Analysis intelligence index
Languages	English, ChineseRead off the model card metadata. Z.ai writes no sentence about language coverage.
Precision served	FP8
Context	1.3M tokens
Vector	n/a
License	MIT

Price

Input

$0.081

per million tokens

Output

$0.270

per million tokens

Against OpenRouter

10%

below the cheapest of 26 providers

The cheapest OpenRouter price for this model was $0.090 in and $0.300 out, with a median of $0.150 and $0.500 across the comparable providers. Read on 2026-09-17.

License

Z.ai releases the weights under the MIT license. It permits commercial use, changes, and redistribution. You do not need a separate vendor agreement to ship.

Similar models

Kimi K3moonshotai/Kimi-K3

Parameters: 2.8T
Context: 1M
Input per 1M: $2.250
Output per 1M: $11.475
License: Kimi K3

Qwen3.8 2.4T A95BQwen/Qwen3.8-2.4T-A95B

Parameters: 2.4T, 95B
Context: 1M
Input per 1M: $1.800
Output per 1M: $5.400
License: Qwen3.8 Max

DeepSeek V4.1 Flashdeepseek-ai/DeepSeek-V4.1-Flash

Parameters: 763.2B, 13B
Context: 1M
Input per 1M: $0.135
Output per 1M: $0.540
License: MIT

Start using GLM 5.3 Flash

Point the OpenAI SDK at api.modelsheep.com. Your prompts stay in Germany, and nothing is retained.

Get API key Read the quickstart