---
title: "GLM-5.3-Flash API hosted in the EU"
description: "Run Z.ai's GLM-5.3-Flash on inference.eu: a multimodal open model with 18B active parameters and 1M context, OpenAI-compatible, processed in the EU."
canonical: "https://inference.eu/models/glm-5-3-flash/"
language: "en"
---

Reasoning · Z.ai (Zhipu AI)

# Run GLM-5.3-Flash in the EU through an OpenAI-compatible API

GLM-5.3-Flash is the efficient, natively multimodal member of Z.ai's GLM-5 series: 320 billion parameters with 18 billion active, image input and a one-million-token context, under the MIT licence. On inference.eu you call it with the OpenAI or Anthropic request format, processed in EU data centres and never used for training.

[Contact sales](https://inference.eu/contact/)[Example request](#example)

1.  01320B · 18B
2.  02EU data centres
3.  03MIT

## What GLM-5.3-Flash is

GLM-5.3-Flash was released by Z.ai in late August 2026. Unlike GLM-5.3, it starts from a newly trained base model, pre-trained on a 30-trillion-token multimodal corpus. It is a mixture-of-experts model with 320 billion parameters in total and 18 billion active per token, with 45 layers, roughly half the depth of earlier large GLM models.

It is the first GLM-5 model to accept images natively. For the first time in the GLM series it combines sparse and linear attention, which lowers the cost of very long contexts, and it uses manifold-constrained hyper-connections to improve training efficiency. It reasons before answering, with effort levels low, high and max, and its weights are MIT-licensed.

## What it does well, and where it falls short

GLM-5.3-Flash is designed to give much of the flagship's coding and agent ability at a fraction of the compute. Z.ai reports that it outperforms GLM-5.2 across benchmarks and real workloads. It suits coding assistants, agents that read screenshots, and long-document work where the one-million-token window matters but a 750-billion-parameter model would be excessive.

On the hardest long-horizon tasks, the full GLM-5.3 or Kimi K3 still go further. Its reasoning defaults to the maximum level, which produces long outputs unless you lower it. The model card lists English and Chinese as its primary languages, so test European languages on your own content. It reads images but does not create them.

## Calling GLM-5.3-Flash through the API

inference.eu speaks both the OpenAI and the Anthropic request formats. Set the base URL to the inference.eu API, use your inference.eu key and set the model to `glm-5.3-flash`. Coding tools such as Claude Code, Cline or OpenHands work by changing those same three settings.

Send images as `image_url` content parts next to your text. Pass `reasoning_effort` as `low`, `high` or `max`; Z.ai defaults to `max`, so set `low` explicitly for quick replies. For chat, Z.ai recommends clearing earlier thinking from the history. Tool calls, JSON output and streaming work as usual.

## Data residency for GLM-5.3-Flash

On inference.eu, GLM-5.3-Flash runs on infrastructure in the European Union. Your prompts, images, source code and the model's responses are processed in EU data centres, are not sent to Z.ai in China, and are never used to train any model.

Every customer receives a data processing agreement under Article 28 of the GDPR together with our subprocessor list, so you can document every party involved. Billing is in euros. Unlike the GLM-5.3 flagship, GLM-5.3-Flash is released under the plain MIT licence, which allows commercial use with no revenue thresholds or review requirements.

## GLM-5.3-Flash

Maker

Z.ai (Zhipu AI)

Made in

China

Type

Reasoning

Parameters

320B

Active parameters

18B

Context window

1,048,576 tokens

Licence

[MIT](https://huggingface.co/zai-org/GLM-5.3-Flash/blob/main/LICENSE)

Released

August 2026

Model ID

glm-5.3-flash

Processing

EU data centres

Training on your data

Never

Source

[huggingface.co](https://huggingface.co/zai-org/GLM-5.3-Flash)

glm-5.3-flash · Python

```
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.inference.eu/v1", api_key=os.environ["INFERENCE_EU_API_KEY"])

response = client.chat.completions.create(
    model="glm-5.3-flash",
    messages=[{"role": "user", "content": "Summarise this contract in five bullet points."}],
)
print(response.choices[0].message.content)
```

## What teams use it for

-   1

    ### Everyday coding assistant

    Answer code questions, write functions and fix bugs in an IDE or terminal tool, with code processed in the EU.

-   2

    ### Screenshot-driven agents

    Let an agent read screenshots of an application or dashboard and decide which action or tool comes next.

-   3

    ### Long-document analysis

    Read long reports, contracts or logs in one request with the one-million-token window and answer questions about them.

## GLM-5.3-Flash: common questions

The questions buyers, developers and legal teams ask us most. Something missing? Ask us directly.

Compliance depends on how you process data. On inference.eu, GLM-5.3-Flash requests are processed in EU data centres, not used for training and covered by a data processing agreement under Article 28 GDPR with a published subprocessor list. Nothing is sent to Z.ai or to China.

GLM-5.3-Flash supports a context of about one million tokens. Its hybrid of sparse and linear attention keeps long contexts affordable. Images count towards the context, and reasoning output needs room as well.

Yes. GLM-5.3-Flash is released under the MIT licence, which allows commercial use, modification and redistribution. Unlike the GLM-5.3 licence, there is no security-review clause for very large model-as-a-service operators, so the licence review is short.

Yes. It is the first natively multimodal model in the GLM-5 series and accepts images together with text. It can read screenshots, charts and documents and answers in text. Send images in the standard OpenAI \`image\_url\` format.

GLM-5.3-Flash has 320 billion parameters with 18 billion active, reads images and uses the MIT licence. GLM-5.3 is the larger, text-only flagship for the hardest coding tasks, under its own GLM-5.3 licence. Flash is the sensible default; use GLM-5.3 when Flash is not enough.

Pass \`reasoning\_effort\` as \`low\`, \`high\` or \`max\`. The model defaults to \`max\` if you pass nothing, which produces long outputs. For quick chat and simple tasks, set \`low\` explicitly to keep answers short.

On inference.eu the open weights run in EU data centres, so no prompts or code leave the EU for inference. The model's answers still reflect its training, including on politically sensitive topics. Test it on your own tasks before relying on it.

Both are efficient Chinese mixture-of-experts reasoning models with one-million-token context and permissive licences. GLM-5.3-Flash has slightly more active parameters and reads images; DeepSeek V4 Flash is text-only. Test both in your own coding or agent setup.

Change your OpenAI client's base URL to the inference.eu API, use your inference.eu key and set the model to \`glm-5.3-flash\`. Messages, images, tools and streaming work with the same code. Add \`reasoning\_effort\` to keep simple requests fast.

No. Requests to inference.eu are used only to produce your response. They are never used to train or fine-tune GLM-5.3-Flash or any other model, and they are not shared with Z.ai.

[Ask a question](https://inference.eu/contact/)

## Related

[All models](https://inference.eu/models/#directory)

-   [GLM-5.3Run Z.ai's GLM-5.3, an open-weight model built for complex coding and long agent tasks, on inference.eu with OpenAI and Anthropic APIs, processed in the EU.Reasoning](https://inference.eu/models/glm-5-3/)
-   [DeepSeek V4 FlashRun DeepSeek V4 Flash (0731) on inference.eu: a 1M-token open reasoning model behind an OpenAI-compatible API, processed in EU data centres, not in China.Reasoning](https://inference.eu/models/deepseek-v4-flash/)
-   [MiniMax M3Run MiniMax M3 on inference.eu: an open multimodal model with 1M context for coding and agent work, OpenAI-compatible and processed in EU data centres.Reasoning](https://inference.eu/models/minimax-m3/)
-   [Qwen3.8 27BRun Qwen3.8 27B on inference.eu: a dense open model with image and video input, adjustable reasoning and 256K context, OpenAI-compatible, processed in the EU.Reasoning](https://inference.eu/models/qwen3-8-27b/)

## Move your AI workloads to EU infrastructure

Tell us which models you use and roughly how much traffic you have. We reply within one working day with pricing and next steps.

-   Reply within one working day
-   Pricing for your volume
-   DPA ready to sign