HostYourAI
Product
EU RouterHostYourAI CodeOpenAI-compatible APIAnthropic-compatible APIModel GardenDedicated InstancesPlaygroundFine-tuning (Loes)Connect your GPU pool
Solutions
Use cases
HostYourAI CodeLLM InferenceRAG pipelinesChatbotsAI agentsFine-tuning
Industries
GovernmentHealthcareFinanceLegal
Models
Kimi K3DeepSeek V4 ProDeepSeek V4 FlashGLM 5.2Llama 3.1 405BQwen3.5 397BLlama 3.3 70BMistralDeepSeek R1All models →
Compare
Azure OpenAIAWS BedrockClaude APIChatGPTOpenAI
Resources
DocumentationGuide: migrate to the EU RouterGuide: deploy your own LLM (vLLM)Guide: build RAG on EU GPUsModel catalog
Pricing
NL EN DE
Login Book Demo Get Started
Model garden Router · on request Dedicated · available

MiniMax M2.5 NVFP4

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

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

Start for free ← All models
nvidia/MiniMax-M2.5-NVFP4 On request
text->text · nvidia · sovereign EU
Runs on EU infrastructure operated by European companies; US marketplace capacity is never part of this chain. Full chain
116B
Parameters
197K
Context window
168GB
Minimum VRAM
POST /api/v1/chat/completions On request

Specifications

Parameters 116B
Context window 196,608 tokens
Minimum VRAM 168 GB
Architecture MiniMaxM2ForCausalLM (vLLM)
License other
Modality text->text
Released March 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 MiniMax M2.5.
Dedicated GPU · per hour
from €12,89 per hour
Your own vLLM instance on European cloud (168 GB VRAM), billed hourly.

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

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/MiniMax-M2.5-NVFP4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently asked questions

Can I run MiniMax M2.5 NVFP4 in the EU?

Yes. HostYourAI runs MiniMax M2.5 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 MiniMax M2.5 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 MiniMax M2.5 NVFP4 cost?

MiniMax M2.5 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

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 →
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.

31B 262K context View model →
Ising Calibration 1.5 31B BF16

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

31B 262K context View model →
Cosmos3 Super Text2Image 4Step

Cosmos3-Super-Text2Image-4Step is a 4-step distilled version of the base Cosmos3-Super-Text2Image model. Given a text prompt, it generates a high-fidelity image.

64B 262K context View model →
Qwen Image Flash

The NVIDIA Qwen-Image-Flash model generates images from text prompts using a four-step, DMD2-distilled version of Qwen/Qwen-Image. The distillation used DMD2 from NVIDIA FastGen, NVIDIA Model Optimizer, and NVIDIA AutoModel while retaining the base model architecture. The packaged scheduler is configured for the four-step, shift-3 trajectory.

20B View model →
NVIDIA Nemotron Labs 3 Puzzle 75B A9B NVFP4

The model employs a hybrid MoE architecture with interleaved Mamba, MoE, and Attention layers. Like Nemotron-3-Super, it supports Multi-Token Prediction (MTP) for faster text generation. Compared to its parent, Puzzle-75B-A9B reduces the model from 120.7B total / 12.8B active parameters to 75.3B total / 9.3B active parameters.

45B 262K context View model →

Try MiniMax M2.5 NVFP4 for free

Creating an account takes a minute. Test MiniMax M2.5 NVFP4 straight away in the playground.

Start for free