by Google·Text + Image·128K context·Released 2025-03-12·Gemma
Overview
Google's open Gemma 3, instruction-tuned at 27B parameters. Multilingual out of the box, vision-capable, and broadly available across providers, it's a dependable general-purpose workhorse for chat, summarization and light reasoning. Quality is well ahead of the smallest open models while pricing stays modest, which makes it a common step up when a 20B model isn't quite enough.
Benchmarks
Standardized scores (0–100), normalized across the catalog.
Intelligence45
Coding60
Instruction following85
Providers
LLMRouteHub routes to the cheapest healthy provider by default. Showing the top 5 of 9 providers by routed volume.
| Provider | Input | Output | Throughput | Uptime |
|---|---|---|---|---|
| Lambda | $0.11 | $0.22 | 96 tok/s | 99.8% |
| Hyperbolic | $0.12 | $0.24 | 89 tok/s | 99.6% |
| Parasail | $0.14 | $0.28 | 83 tok/s | 99.5% |
| DeepInfra | $0.16 | $0.33 | 76 tok/s | 99.4% |
| Together | $0.17 | $0.34 | 69 tok/s | 99.2% |
Use this model
curl https://llmroutehub.com/api/v1/chat/completions \
-H "Authorization: Bearer $LLMROUTEHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemma-3-27b-it",
"messages": [{ "role": "user", "content": "Hello" }]
}'