Google: Gemma 3 27B
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
Everything else
| Max output | 131K |
|---|---|
| Input / 1M | $0.08 |
| Output / 1M | $0.45 |
| Cache read / 1M | $0.04 |
| Cache write / 1M | — |
| 1M in + 1M out | $0.53 |
| Takes | text, image |
| Returns | text |
| Tools | yes |
| Reasoning | no |
| Open weights | yes |
| Released | 2025-03-12 |
| Knowledge cutoff | 2024-08-31 |
| Retires | — |
| Catalog id | google/gemma-3-27b-it |
Benchmarks
| source | epoch |
|---|---|
| eci | 131.06 |
| confidence | Confident |
| accessibility | Open weights (restricted use) |
| gpqa | 0.489 |
| gpqaStderr | 0.0303 |
| mathLevel5 | 0.74 |
| mathLevel5Stderr | 0.0112 |
| aime | 0.197 |
| aimeStderr | 0.0543 |
Benchmark scores by Epoch AI, CC BY 4.0.
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.