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

gemma 4 31B it

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

Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned vari...

Start for free ← All models
google/gemma-4-31B-it vLLM ready
text+image->text · google · sovereign EU
Runs on EU infrastructure operated by European companies; US marketplace capacity is never part of this chain. Full chain
31B
Parameters
262K
Context window
80GB
Minimum VRAM
POST /api/v1/chat/completions On request

Specifications

Parameters 31B
Context window 262,144 tokens
Minimum VRAM 80 GB
Architecture Gemma4ForConditionalGeneration (vLLM)
License apache-2.0
Modality text+image->text
Released March 2026
Publisher google ↗

Pricing

Shared router · per token
On request
Not available on the shared router. Pricing on request as a dedicated GPU deployment.
Dedicated GPU · per hour
from €2,56 per hour
Your own vLLM instance on European cloud (80 GB VRAM), billed hourly.

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

✓ Verified working on 26-07-2026, responded in 3171 ms on our EU infrastructure.

Bench index

Bench is our quality index for every model, 0 to 100. It rests on public measurements (Epoch AI with about 40 benchmarks, LiveBench, LMArena and more) and is refreshed every morning. Where nobody measures, it shows an estimate with a range.

65.9 / 100 · Measured

Measured by Epoch AI across 8 benchmarks, with a range.

Range 62.8 to 68.9 · Rank 99 of 274 at Epoch AI

Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 08-10-2026

LiveBench · 61.6
Reasoning 59.4
Coding 60.3
Agentic coding 40.0
Mathematics 73.9
Data analysis 58.8
Language 71.3
Instruction following 67.6
Every benchmark (8)
OTIS Mock AIME 2024-2025 73.3
DTBench 71.1
GPQA diamond 67.7
WeirdML 52.3
LMCA 46.2
Surface Evolver Bench 30.6
SimpleQA Verified 10.4
Chess Puzzles 0.0
LiveBench · All tasks
Reasoning
theory of mind 51.9
zebra puzzle 29.8
spatial 92.0
logic with navigation 64.0
Coding
code generation 62.0
code completion 58.7
Agentic coding
javascript 20.0
typescript 35.0
python 65.0
Mathematics
AMPS Hard 100.0
integrals with game 26.3
math comp 87.3
olympiad 82.2
Data analysis
consecutive events 29.9
tablejoin 46.4
tablereformat 100.0
Language
connections 92.5
plot unscrambling 47.5
typos 74.0
Instruction following
paraphrase 69.5
simplify 61.3
story generation 71.7
summarize 67.9

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": "google/gemma-4-31B-it",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently asked questions

Can I run gemma 4 31B it in the EU?

Yes. HostYourAI runs gemma 4 31B it 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 gemma 4 31B it 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 gemma 4 31B it cost?

gemma 4 31B it 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 Google

diffusiongemma 26B A4B it

DiffusionGemma is a generative model built by Google DeepMind. Based on the 26B A4B Mixture-of-Experts (MoE) Gemma 4 architecture, DiffusionGemma generates tokens using discrete diffusion. This open-weights model is multimodal, handling text, image, and video inputs to generate text output.

26B 262K context View model →
gemma 4 31B it qat w4a16 ct

[!Note] This model card is for the new versions of the Gemma 4 family optimized with Quantization-Aware Training (QAT), which allows preserving similar quality to bfloat16 while dramatically reducing the memory requirements to load the model. Four versions of the QAT checkpoints are available: Unquantized QAT checkpoints (Q40): Half-precision weights extracted from the QAT pipeline, ideal for custom downstream compilation and research. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B, and their drafter models. GGUF (Q40): Ready-to-deploy formats for broad ecosystem compatibility. Availabl

34B 262K context View model →
gemma 4 26B A4B it qat q4 0 unquantized

[!Note] This model card is for the new versions of the Gemma 4 family optimized with Quantization-Aware Training (QAT), which allows preserving similar quality to bfloat16 while dramatically reducing the memory requirements to load the model. Four versions of the QAT checkpoints are available: Unquantized QAT checkpoints (Q40): Half-precision weights extracted from the QAT pipeline, ideal for custom downstream compilation and research. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B, and their drafter models. GGUF (Q40): Ready-to-deploy formats for broad ecosystem compatibility. Availabl

27B 262K context View model →
gemma 4 31B it qat q4 0 unquantized

[!Note] This model card is for the new versions of the Gemma 4 family optimized with Quantization-Aware Training (QAT), which allows preserving similar quality to bfloat16 while dramatically reducing the memory requirements to load the model. Four versions of the QAT checkpoints are available: Unquantized QAT checkpoints (Q40): Half-precision weights extracted from the QAT pipeline, ideal for custom downstream compilation and research. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B, and their drafter models. GGUF (Q40): Ready-to-deploy formats for broad ecosystem compatibility. Availabl

33B 262K context View model →
gemma 4 31B

Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.

33B 262K context View model →
gemma 4 26B A4B

Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.

27B 262K context View model →

Try gemma 4 31B it for free

Creating an account takes a minute. Test gemma 4 31B it straight away in the playground.

Start for free