GLBNXT Platform / Model Hub

Every model you need. You decide where it runs.

Compare open and frontier models from 14 creators in one catalogue. See where each one is hosted before you send it a single prompt, then call it through one OpenAI-compatible endpoint.

Model Hub60+ models · 14 creators
GLM-5.3Z.ai · ResearchGLBNXT Recommended
glm-5.3
Gemma 4 26BGoogle · ChatGLBNXT Recommended
glbnxt/gemma-4:26b
DeepSeek V4.1 FlashDeepSeek · Coding
deepseek-v4.1-flash
Qwen3 Embedding 0.6BAlibaba Cloud · Embedding
glbnxt/qwen3-embedding:0.6b
gpt-oss-120bOpenAI · ChatGLBNXT Recommended
glbnxt/gpt-oss-120b
Claude Opus 5.5Anthropic · Coding
claude-opus-5-5
Showing a preview of more than 60 models

Models from

Alibaba Cloud · Anthropic · BAAI · DeepSeek · Google · IBM · MiniMax · Mistral AI · Moonshot AI · Nous Research · NVIDIA · OpenAI · Perplexity · Z.ai

Alibaba Cloud · Anthropic · BAAI · DeepSeek · Google · IBM · MiniMax · Mistral AI · Moonshot AI · Nous Research · NVIDIA · OpenAI · Perplexity · Z.ai

Data residency, per model

Three flags. No guesswork about where your data goes.

Every model in the hub shows where its hardware sits and who operates it. Filter by region, and keep regulated workloads on Dutch or European infrastructure while teams still get access to frontier models for everything else.

13

The Netherlands

Hardware in the Netherlands. Every model with the glbnxt/ prefix runs here.

30

European Union

Hardware in the EU. The model card tells you who operates it.

55

United States

US hardware or a US provider. We show that up front, so nobody picks one of these by accident.

glbnxt/

glbnxt/ means we run it. Models with this prefix run only on infrastructure GLBNXT operates in the Netherlands.

Find the right model

Narrow 60+ models down to the one that fits.

Search by name or model ID, then stack filters until the shortlist matches your compliance and technical requirements.

Search

Type a model name or its technical ID. Copy the ID to your clipboard in one click.

Name · Model ID · One-click copy

Model creator

Filter by the organisation behind the model, from frontier labs to open-source research groups.

14 creators

Region

Keep only models hosted where your data is allowed to go.

NL · EU · US

Use case

Pick models built for the job, not just the biggest one.

Chat · Coding · Research · Embedding · OCR · Re-ranking · Safeguards

Weights

Separate open-weight models you could self-host from closed, API-only models.

Open · Closed

Licence

Check the licence before your legal team asks.

MIT · Apache 2.0

Beyond chat

A model for every step of the pipeline.

Production AI needs more than a chatbot. The hub covers the full chain, from reading a scanned document to retrieving the right passage and checking the answer.

Chat35 models

Assistants, Q&A and drafting for knowledge workers.

glbnxt/gpt-oss-120b · glm-5.3
Coding22 models

Code generation and agents that work across whole repositories.

glbnxt/Devstral Small 2 · GLM-5.3
(Deep) Research14 models

Reasoning models and web-grounded research with citations.

sonar-deep-research · GLM-5.3
Embedding3 models

Turn documents into vectors for search and RAG pipelines.

glbnxt/qwen3-embedding:0.6b
Re-ranking1 models

Sharpen retrieval by scoring query and passage together.

bge-reranker-v2-m3
OCR2 models

Read scans, tables and complex layouts into usable text.

deepseek-ocr · mistral-ocr-latest
Safeguards1 models

Classify and filter prompts and outputs against your own policy.

gpt-oss-safeguard-20b

Model cards

Know what a model can do before you write a line of code.

Each model card brings the facts your engineers and your compliance team both need into one view.

✓ Identity and provenance: full name, creator, copyable model ID and the creator's own model card.

✓ Where it runs: regional availability, with redundant regions shown side by side.

✓ Modalities: which inputs it accepts (text, image, audio, video, files) and what it returns.

✓ Supported API parameters, grouped by output control, sampling and tools.

✓ GLBNXT Recommended marks the models we have tested for production use.

GLM-5.3by Z.ai
Recommended by GLBNXT
Model IDglm-5.3
Hosted inThe Netherlands
Context window1M tokens
Input / outputText / Text
Capabilities
Output controlresponse_formatmax_tokensstream
Samplingtemperature
Toolstoolstool_choice
View the creator's model card

One endpoint

Switch models by changing one string.

The hub sits behind an OpenAI-compatible API. Tools that already speak the OpenAI format connect with a new base URL and a scoped API key.

1 Pick a model in the hub and copy its ID.

2 Create an API key, scoped to only the models that key may use, with an expiry date.

3 Point your code at https://ai.glbnxt.com/v1.

4 Swap models later by changing the model string. Nothing else moves.

Works with n8n · Open WebUI · LibreChat · Langflow · OpenCode · Cline · Aider

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://ai.glbnxt.com/v1",
    api_key=os.environ["GLBNXT_API_KEY"],
)

reply = client.chat.completions.create(
    model="glbnxt/gpt-oss-120b",
    messages=[{"role": "user",
               "content": "Summarise this tender in 5 points."}],
)
print(reply.choices[0].message.content)

Managed by GLBNXT

We run the models. Your team ships the product.

Open-source serving

Open models run on Ollama, managed by GLBNXT inside your EU environment. Weights and requests never pass through an external system.

Production inference

NVIDIA NIM for latency-critical, high-throughput workloads on NVIDIA GPUs.

Routing and failover

Load balancing across instances, automatic failover and priority rules for critical workloads.

New models on request

Need a model that is not listed, or your own fine-tuned one? We validate, deploy and test it before it appears in your hub.

New model versions, same endpoint

Models keep improving and your endpoint URL doesn't change. Before a new version takes production traffic, you can run it against your own evaluation set.

  1. 01StageThe new version gets its own staging endpoint.
  2. 02EvaluateScore it on your data, with Langfuse, Opik or whatever you already use.
  3. 03ReviewIs it better for your use case? Decide against your own quality bar.
  4. 04PromoteSwitch production traffic over. Same URL as before.

Governed by default

Model choice your auditor can follow.

The Model Hub connects to the rest of the platform, so every model decision leaves a trail.

Attribution in every log

The audit trail records which model and version served each request. No silent rerouting to another model.

Usage by model

Token use, time to first token and top models per application and API key.

Scoped access

API keys only reach the models you assign to them, and expire on schedule.

Built for the AI Act

Model identity, provenance and version history support your technical documentation and record keeping.

Frequently Asked Questions

If you have any other questions, please email us.

Which models keep my data in the Netherlands or the EU?

Why are US-hosted models in the hub at all?

Can we add a model that isn't listed, or our own fine-tuned model?

Will a model update break our application?

Do we need to change our code to switch models?

Who decides which teams can use which model?

See the Model Hub with your own use case.

A 30-minute walkthrough. Bring a workload and we'll shortlist models for it together, Dutch and European options first.

This website and its contents are the exclusive property of GLBNXT. No part of this site, including text, images, or software, may be copied, reproduced, or distributed without prior written consent from GLBNXT B.V. located at Druivenstraat 5-7, 4816 KB Breda, The Netherlands, registered with the Dutch Chamber of Commerce (KvK) under number 95536779. VAT identification number (VAT ID) NL867171716B01. All rights reserved.

This website and its contents are the exclusive property of GLBNXT. No part of this site, including text, images, or software, may be copied, reproduced, or distributed without prior written consent from GLBNXT B.V. located at Druivenstraat 5-7, 4816 KB Breda, The Netherlands, registered with the Dutch Chamber of Commerce (KvK) under number 95536779. VAT identification number (VAT ID) NL867171716B01. All rights reserved.

This website and its contents are the exclusive property of GLBNXT. No part of this site, including text, images, or software, may be copied, reproduced, or distributed without prior written consent from GLBNXT B.V. located at Druivenstraat 5-7, 4816 KB Breda, The Netherlands, registered with the Dutch Chamber of Commerce (KvK) under number 95536779. VAT identification number (VAT ID) NL867171716B01. All rights reserved.

This website and its contents are the exclusive property of GLBNXT. No part of this site, including text, images, or software, may be copied, reproduced, or distributed without prior written consent from GLBNXT B.V. located at Druivenstraat 5-7, 4816 KB Breda, The Netherlands, registered with the Dutch Chamber of Commerce (KvK) under number 95536779. VAT identification number (VAT ID) NL867171716B01. All rights reserved.