HostYourAI
Product
EU RouterDecision models like JevHostYourAI CodeOpenAI-compatible APIAnthropic-compatible APIModel GardenDedicated InstancesPlaygroundFine-tuning (Loes)Earn with your GPU
Solutions
Use cases
HostYourAI CodeLLM InferenceRAG pipelinesChatbotsAI agentsFine-tuning
Industries
GovernmentHealthcareFinanceLegal
Models
Kimi K3DeepSeek V4 ProDeepSeek V4 FlashGLM 5.3Kimi K2.7 CodeQwen3.5 397BLlama 3.3 70BMistralMiniMax M3All models →
Compare
Azure OpenAIAWS BedrockClaude APIChatGPTOpenAICompare costs
Resources
DocumentationSavings checkGuide: migrate to the EU RouterGuide: deploy your own LLM (vLLM)Guide: build RAG on EU GPUsModel catalogNewsSecurityFAQ
Pricing News
NL EN DE
Login Book Demo Get Started
Model garden Router · on request Dedicated · available

GLM 5.3 Flash NVFP4

Runs as your own dedicated GPU deployment, ready to launch from the wizard. Data stays in Europe.

This model is ready for commercial or non-commercial use. <br

Start for free ← All models
nvidia/GLM-5.3-Flash-NVFP4 On request
text+image->text · nvidia · sovereign EU
Runs on EU infrastructure operated by European companies; US marketplace capacity is never part of this chain. Full chain
169B
Parameters
1,049K
Context window
223GB
Minimum VRAM
POST /api/v1/chat/completions On request

Specifications

Parameters 169B
Context window 1,048,576 tokens
Minimum VRAM 223 GB
Architecture Glm5NextForConditionalGeneration (vLLM)
License mit
Modality text+image->text
Released September 2026
Publisher nvidia ↗

Pricing

Shared router · per token
On request
Not available on the shared router. Pricing on request as a dedicated GPU deployment.
Prefer per token on the shared router? This model runs always-on as GLM 5.3 Flash.
Dedicated GPU · per hour
from €12,89 per hour
Your own vLLM instance on European cloud (223 GB VRAM), billed hourly.

Shared EU router, pay-per-token, scale-to-zero. Dedicated GPU deployments are billed hourly, see pricing.

Bench index

Bench is our quality index for every model, 0 to 100. It rests on the Epoch AI Capabilities Index (about 40 benchmarks), completed with LiveBench, and is refreshed every morning.

73.4 / 100 · Via LiveBench

Translated from its LiveBench result onto the same scale.

Range 67.1 to 79.7

Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 25-09-2026

LiveBench · 71.6 · Rank 49 of 63
Reasoning 77.6
Coding 79.0
Agentic coding 56.8
Mathematics 81.2
Data analysis 76.4
Language 77.3
Instruction following 52.8
LiveBench · All tasks
Reasoning
theory of mind 73.1
zebra puzzle 79.5
spatial 96.0
logic with navigation 62.0
Coding
code generation 77.5
code completion 80.4
Agentic coding
javascript 63.6
typescript 46.7
python 60.0
Mathematics
AMPS Hard 97.0
integrals with game 45.0
math comp 93.1
olympiad 89.8
Data analysis
consecutive events 84.3
tablejoin 48.8
tablereformat 96.1
Language
connections 93.7
plot unscrambling 60.3
typos 78.0
Instruction following
paraphrase 48.0
simplify 47.0
story generation 59.9
summarize 56.5

Call it now

Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.

curl https://hostyourai.com/api/v1/chat/completions \
  -H "Authorization: Bearer hyai-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/GLM-5.3-Flash-NVFP4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently asked questions

Can I run GLM 5.3 Flash NVFP4 in the EU?

Yes. HostYourAI runs GLM 5.3 Flash NVFP4 on GPUs in European datacenters via vLLM. Prompts and outputs never leave the EU and there is no US cloud provider in the chain.

Is hosting GLM 5.3 Flash NVFP4 GDPR-compliant?

Yes. All processing happens inside the EU, a Data Processing Agreement (DPA) is available and the subprocessor list is public. Open-source weights also mean: no training on your data.

How much does GLM 5.3 Flash NVFP4 cost?

GLM 5.3 Flash NVFP4 is available on request: through the shared EU router after a quick chat, or as your own dedicated GPU deployment billed per hour. Tell us your use case and we will set it up for you.

Is the API OpenAI-compatible?

Yes. You use the standard OpenAI SDKs with a custom base URL (https://hostyourai.com/api/v1). The Anthropic Messages API is supported as a drop-in as well.

More models from NVIDIA

Muse Glimmer 30B NVFP4

This model is ready for commercial or non-commercial use. <br

20B 131K context View model →
NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF16

Looking for the post-trained model? See NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 for the full-precision release, or NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 for optimized inference.

32B 262K context View model →
NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DSpark

The NVIDIA Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark model is the DSpark speculative decoding checkpoint for NVIDIA's Nemotron-3.5-Lightning-30B-A3B model family, which is a hybrid LatentMoE language model designed for reasoning, chat, and agentic workflows. For more information, please check BF16, NVFP4. The NVIDIA Nemotron-3.5-Lightning-30B-A3B-DSpark-NVFP4 model is intended for DSpark speculative decoding deployments tuned for DGX Spark and low-concurrency data centre workflows.

0.8B 1M context View model →
NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4

The pre-training data has a cutoff date of September 2025. The post-training data has a cutoff date of May 2026.

18B 1M context View model →
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16

The pre-training data has a cutoff date of September 2025. The post-training data has a cutoff date of May 2026.

32B 262K context View model →
Ising Calibration 1.5 31B NVFP4

GOVERNING TERMS: Use of this model is governed by the OpenMDW License Agreement, version 1.1. ADDITIONAL INFORMATION: Apache License, Version 2.0.

17B 262K context View model →

Try GLM 5.3 Flash NVFP4 for free

Creating an account takes a minute. Test GLM 5.3 Flash NVFP4 straight away in the playground.

Start for free