gemma 4 31B it
Runs as your own dedicated GPU deployment, ready to launch from the wizard. Data stays in Europe.
$ 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!"}]
}'
Call it now
Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.
text+image->text · google · sovereign EU
Runs on EU infrastructure operated by European companies, from your request to the GPU. See the full chain
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...
- Router
- Router · on request
- Dedicated
- Dedicated · available
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
Dedicated GPU · per hour
Shared EU router, you pay only per token. Dedicated GPU deployments are billed per minute, 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.
Measured by Epoch AI across 7 benchmarks, with a range.
Range 64.6 to 70.7 · Rank 101 of 257 at Epoch AI
Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 19-11-2026
LiveBench · 61.6
Every benchmark (7)
| OTIS Mock AIME 2024-2025 | 73.3 |
|---|---|
| DTBench | 71.1 |
| GPQA diamond | 70.5 |
| WeirdML | 52.3 |
| LMCA | 46.2 |
| Surface Evolver Bench | 30.6 |
| SimpleQA Verified | 10.4 |
LiveBench · All tasks
| theory of mind | 51.9 |
|---|---|
| zebra puzzle | 29.8 |
| spatial | 92.0 |
| logic with navigation | 64.0 |
| code generation | 62.0 |
|---|---|
| code completion | 58.7 |
| javascript | 20.0 |
|---|---|
| typescript | 35.0 |
| python | 65.0 |
| AMPS Hard | 100.0 |
|---|---|
| integrals with game | 26.3 |
| math comp | 87.3 |
| olympiad | 82.2 |
| consecutive events | 29.9 |
|---|---|
| tablejoin | 46.4 |
| tablereformat | 100.0 |
| connections | 92.5 |
|---|---|
| plot unscrambling | 47.5 |
| typos | 74.0 |
| paraphrase | 69.5 |
|---|---|
| simplify | 61.3 |
| story generation | 71.7 |
| summarize | 67.9 |
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 minute. 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
One platform, four layers
Start with one layer and add the others when the work asks for it. They share one key, one balance and one Activity view.
Try gemma 4 31B it for free
Creating an account takes a minute. Test gemma 4 31B it straight away in the playground.







