Gemma 3 27B pricing & benchmarks
Gemma 3 27B is available from Google at $0.080 per million input tokens and $0.350 per million output tokens ($0.147 blended at 3:1). It accepts up to 131,072 tokens of context. 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,...
Pricing
Per million tokens · OpenRouter
Input$0.080
Output$0.350
Blended (3:1)$0.147
Specification
google/gemma-3-27b-it
Context window131K
Max output118K
ReleasedMar 2025
LicenceOpen weights
Modalitiesin:text, in:image, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 47.7% ±2.7 | — | 2026-08-27 | Independently run · Epoch AI |
| OTIS Mock AIME | 22.5% ±5.3 | — | 2026-08-27 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Cheaper models that score at least as well on GPQA Diamond
Strictly lower blended price AND an equal-or-higher GPQA Diamond score. One benchmark is one dimension — a model that wins here may still be weaker at your specific task.
| Model | Provider | Blended $/1M | GPQA Diamond | |
|---|---|---|---|---|
| gpt-oss-20b | OpenAI | $0.036 (−76%) | 60.8% | Compare → |
| Qwen3.7 Flash | Alibaba | $0.055 (−63%) | 82.3% | Compare → |
| Phi 4 | Microsoft | $0.088 (−41%) | 56.1% | Compare → |
| Qwen3.5-Flash | Alibaba | $0.114 (−23%) | 82.3% | Compare → |
| GPT-5 Nano | OpenAI | $0.138 (−7%) | 69.4% | Compare → |
Where to run Gemma 3 27B
5 hosts · 1.7× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| DeepInfra | $0.100 | $0.080 / $0.160 | 131K | fp8 | 99.3% |
| Novita ⚠ 98K context, not 131K |
$0.139 | $0.119 / $0.200 | 98K | bf16 | 95.0% |
| NextBit | $0.147 | $0.080 / $0.350 | 131K | fp8 | 99.0% |
| Nebius ⚠ 110K context, not 131K |
$0.150 | $0.100 / $0.300 | 110K | fp8 | 90.5% |
| Parasail | $0.172 | $0.080 / $0.450 | 131K | fp8 | 99.7% |
Host prices and uptime from OpenRouter, synced 2026-10-22. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Gemma 3 27B
FAQ
How much does Gemma 3 27B cost?
Gemma 3 27B costs $0.080 per million input tokens and $0.350 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.147 per million tokens.
What is Gemma 3 27B's context window?
Gemma 3 27B accepts up to 131,072 tokens of context, and can generate up to 117,964 output tokens.
How good is Gemma 3 27B on benchmarks?
Gemma 3 27B scores 47.7% on GPQA Diamond, independently run and published by Epoch AI. 2 benchmark results are listed on this page, each with its run date and source.
Is there a cheaper model as good as Gemma 3 27B?
Yes — 5 models in our catalogue cost less per token than Gemma 3 27B and score at least as high on the same benchmark. The cheapest is gpt-oss-20b at $0.036 per million tokens blended.