---
title: "GLM-5.3 API hosted in the EU"
description: "Run 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."
canonical: "https://inference.eu/models/glm-5-3/"
language: "en"
---

Reasoning · Z.ai (Zhipu AI)

# Run GLM-5.3 in the EU for coding and long agent tasks

GLM-5.3 is the flagship open-weight model from Z.ai, aimed at complex software engineering and long-horizon agent work, with a one-million-token context. On inference.eu you call it with the OpenAI or Anthropic request format, so coding tools work as they are, and your code is processed in EU data centres and never used for training.

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

1.  01753B
2.  02EU data centres
3.  03GLM-5.3 License

## What GLM-5.3 is

GLM-5.3 was announced by Z.ai, formerly Zhipu AI, in August 2026, with full weights published about two weeks later. It uses the same base model as GLM-5.2, a large mixture-of-experts network of roughly 753 billion parameters in the published checkpoint; every improvement in 5.3 comes from post-training.

Z.ai's documentation describes it as text-only, with a one-million-token context window and up to 128K output tokens. It always reasons before answering, with three effort levels: low, high and max. Z.ai reports a 50 per cent gain over GLM-5.2 on its internal coding benchmark and positions GLM-5.3 as its model for complex programming and long tasks.

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

GLM-5.3 is at its best in long coding sessions: working through a large repository, running commands, reading failures and iterating until tests pass. The one-million-token window keeps long tool histories in view. Z.ai also reports strong results in security research tasks such as vulnerability discovery, which is useful for defensive teams and calls for sensible access controls.

It is a very large model, so it is the wrong tool for short chat or simple extraction. Reasoning cannot be switched off, which adds output tokens even to easy requests; use the low effort level for those. It does not read images; GLM-5.3-Flash is the multimodal sibling. The model card lists English and Chinese as its main languages.

## Using GLM-5.3 through the API

inference.eu offers both the OpenAI and the Anthropic request formats. For OpenAI-style tools, set the base URL to the inference.eu API, use your inference.eu key and set the model to `glm-5.3`. For Claude Code and other Anthropic-format tools, use our Anthropic-compatible endpoint with the same model name.

Pass `reasoning_effort` as `low`, `high` or `max`; Z.ai's default is `max`. For chat-style use, Z.ai recommends clearing earlier thinking from the history so the context does not fill with old reasoning. Tool calls and streaming work as usual. Set a generous `max_tokens` for agent steps that plan or write large changes.

## Data residency for GLM-5.3

GLM-5.3 is developed in China, but on inference.eu its open weights run on infrastructure in the European Union. Your prompts, source code and the model's responses are processed in EU data centres, are not sent to Z.ai, and are never used to train any model.

Every customer receives a data processing agreement under Article 28 of the GDPR and our subprocessor list, which your security team can review before rollout. Billing is in euros. The GLM-5.3 licence is permissive for most users: it grants broad rights to use, modify and sell, and only asks model-as-a-service operators with more than 10 billion US dollars in annual revenue to pass a security review by Z.ai.

## GLM-5.3

Maker

Z.ai (Zhipu AI)

Made in

China

Type

Reasoning

Parameters

753B

Context window

1,048,576 tokens

Licence

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

Released

August 2026

Model ID

glm-5.3

Processing

EU data centres

Training on your data

Never

Source

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

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

## What teams use it for

-   1

    ### Long coding agent sessions

    Let an agent work through a feature or a migration over hundreds of steps, with code processed in the EU.

-   2

    ### Defensive security review

    Audit code for vulnerabilities and explain how they could be exploited and fixed, for internal security teams.

-   3

    ### Repository-scale refactoring

    Plan and carry out changes that touch many modules, keeping the whole codebase in context.

## GLM-5.3: 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 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. No data is sent to Z.ai or to China.

When you call it on inference.eu, the open weights run on EU infrastructure, so data does not leave the EU for inference. The model's behaviour still reflects its training, including on politically sensitive topics. For coding tasks this rarely matters, but test it on your own workload.

Z.ai documents a one-million-token context window and a maximum output of 128K tokens. That lets an agent keep a large repository and long tool histories in view, although very long sessions still benefit from trimming old reasoning.

Yes. The GLM-5.3 licence allows use, modification, distribution and sale. The only extra condition applies to model-as-a-service operators whose group revenue exceeds 10 billion US dollars over 12 months; they must pass a security review by Z.ai before commercial use.

No. GLM-5.3 always reasons before answering. You choose how much with \`reasoning\_effort\`: \`low\`, \`high\` or \`max\`, with \`max\` as the default. Use \`low\` for simple requests to keep answers short and inexpensive.

Yes. inference.eu has an Anthropic-compatible endpoint, so Claude Code and other tools that speak the Anthropic Messages format can use GLM-5.3 after you change the base URL, key and model name to \`glm-5.3\`.

No. Z.ai's documentation describes GLM-5.3 as text-only. GLM-5.3-Flash is the first natively multimodal model in the GLM-5 series and accepts images alongside text, at a much smaller active size. Use it when your agent needs to read screenshots.

GLM-5.3 is the large flagship for the hardest coding and long-horizon tasks and reads text only. GLM-5.3-Flash has 320 billion parameters with 18 billion active, reads images and is far lighter to run. Many teams use Flash by default and GLM-5.3 for hard cases.

Both are very large open-weight models from Chinese labs aimed at long-horizon coding and agents, with one-million-token context. Kimi K3 is larger and reads images and video; GLM-5.3 is text-only. Their licences differ too, so check both against your use.

No. Code and prompts sent to inference.eu are used only to produce your response. They are never used to train or fine-tune GLM-5.3 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-5.3-FlashRun 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.Reasoning](https://inference.eu/models/glm-5-3-flash/)
-   [Kimi K3Run Kimi K3, Moonshot AI's 2.8-trillion-parameter open-weight model with 1M context and image and video input, on inference.eu with processing in the EU.Reasoning](https://inference.eu/models/kimi-k3/)
-   [DeepSeek V4.1 Flash (1017)Run DeepSeek V4.1 Flash (1017) on inference.eu: a multimodal open reasoning model with 1M context, OpenAI-compatible, processed in the EU, not in China.Reasoning](https://inference.eu/models/deepseek-v4-1-flash-1017/)
-   [Devstral Small 2Run Devstral Small 2, Mistral AI's open 24B coding agent model, on inference.eu with OpenAI and Anthropic APIs and processing in EU data centres.Code](https://inference.eu/models/devstral-small-2/)

## 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