gemma 3 27b it
Instantly via the EU router or as a dedicated GPU deployment. 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-3-27b-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 3 27b it is a multimodal language model from Google with 27B parameters and a 110K-token context window, hosted on EU GPUs via an OpenAI-compatible API.
- Router
- Router · warm
- Dedicated
- Dedicated · available
- Input (per 1M tokens)
- €0.10
- Output (per 1M tokens)
- €0.32
Specifications
| Parameters | 27B |
|---|---|
| Context window | 110,000 tokens |
| Minimum VRAM | 80 GB |
| Architecture | Gemma3ForConditionalGeneration (vLLM) |
| License | gemma |
| Modality | text+image->text |
| Released | March 2025 |
| 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 23-07-2026, responded in 985 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 8 benchmarks, with a range.
Range 43.3 to 50.6 · Rank 163 of 255 at Epoch AI
Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 11-11-2026
LiveBench · 48.4
Every benchmark (8)
| MATH level 5 | 74.0 |
|---|---|
| GeoBench | 52.0 |
| Fiction.LiveBench | 33.3 |
| GPQA diamond | 31.6 |
| OTIS Mock AIME 2024-2025 | 22.4 |
| DTBench | 20.9 |
| LMCA | 14.4 |
| Aider polyglot | 4.9 |
LiveBench · All tasks
| web of lies v3 | 38.0 |
|---|---|
| zebra puzzle | 29.3 |
| spatial | 36.0 |
| code generation | 47.9 |
|---|---|
| code completion | 50.0 |
| AMPS Hard | 74.0 |
|---|---|
| math comp | 55.2 |
| olympiad | 27.6 |
| tablejoin | 18.8 |
|---|---|
| tablereformat | 58.8 |
| connections | 27.3 |
|---|---|
| plot unscrambling | 28.6 |
| typos | 68.0 |
| paraphrase | 71.5 |
|---|---|
| simplify | 77.5 |
| story generation | 70.6 |
| summarize | 80.0 |
Frequently asked questions
Can I run gemma 3 27b it in the EU?
Yes. HostYourAI runs gemma 3 27b 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 3 27b 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 3 27b it cost?
Via the shared EU router you pay €0.10 per million input tokens and €0.32 per million output tokens, with no fixed costs. For high volume or isolation you can also run gemma 3 27b it on a dedicated GPU instance, billed per minute.
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 3 27b it for free
Creating an account takes a minute. Test gemma 3 27b it straight away in the playground.
