Scheduled for retirement on Mar 30, 2027. Still available at the prices below until then.
Context
131K
Max output
131K
Serving providers
8
Cheapest input
$0.08 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisHeadline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Automation Bench | 0.0 | default | — | |||||||||||||||||
| CritPt | 0% | default | — | |||||||||||||||||
| EvalComputeProxyFrozen Aug 18, 2026 | 3956.2 | default | — | |||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | -121.8 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 43% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Humanity's Last Exam | 4% | default | — | |||||||||||||||||
| IFBench | 32% | default | — | |||||||||||||||||
| LiveCodeBench | 14% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Long-Context Reasoning | 7% | default | — | |||||||||||||||||
| MMLU-ProFrozen Aug 18, 2026 | 67% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| MMMU-Pro | 48% | default | — | |||||||||||||||||
| Omniscience | -67.2 | default | — | |||||||||||||||||
| Omniscience Accuracy | 0.1 | default | — | |||||||||||||||||
| Omniscience Non Hallucination | 0.1 | default | — | |||||||||||||||||
| SciCode | 23% | default | — | |||||||||||||||||
| Terminal Bench40 | 0 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench Hard | 4% | default | — | |||||||||||||||||
| TerminalBench v2.1 | 4% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 1% | default | — | |||||||||||||||||
| τ²-bench | 11% | default | — | |||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.08 to $0.90 per 1M tokens across 7 providers, so the dearest route costs 1025% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepInfraCheapest | $0.08 | $0.16 | 1 | |||||||||||||
Standarddeepinfra/google/gemma-3-27b-it
| ||||||||||||||||
| OpenRouter | $0.08 | $0.45 | 1 | |||||||||||||
Standardgoogle/gemma-3-27b-it
| ||||||||||||||||
| Nebius | $0.10 | $0.30 | 1 | |||||||||||||
Standardnebius/google/gemma-3-27b-it
| ||||||||||||||||
| Novita | $0.119 | $0.20 | 1 | |||||||||||||
Standardnovita/google/gemma-3-27b-it
| ||||||||||||||||
| Amazon Bedrock | $0.23 | $0.38 | 1 | |||||||||||||
Standardgoogle.gemma-3-27b-it
| ||||||||||||||||
| Scaleway | $0.25 | $0.50 | 1 | |||||||||||||
Standardscaleway/google/gemma-3-27b-it
| ||||||||||||||||
| Fireworks AI | $0.90 | $0.90 | 1 | |||||||||||||
Standardfireworks_ai/accounts/fireworks/models/gemma-3-27b-it
| ||||||||||||||||
| Free tier only | — | 1 | ||||||||||||||
Standardgemini/gemma-3-27b-it
| ||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 11% since first tracked
Cost calculator
estimate your monthly spend on this model$0
estimated / month
Model IDs
copy the exact identifier for your platformgemini/gemma-3-27b-itgoogle/gemma-3-27b-itdeepinfra/google/gemma-3-27b-itnebius/google/gemma-3-27b-itnovita/google/gemma-3-27b-itgoogle.gemma-3-27b-itscaleway/google/gemma-3-27b-itfireworks_ai/accounts/fireworks/models/gemma-3-27b-it
Frequently asked questions
Gemma 3 27B pricing, context and availabilityIs Gemma 3 27B still available?
Yes. Gemma 3 27B is scheduled for retirement on 2027-03-30.
How much does Gemma 3 27B cost?
Gemma 3 27B costs $0.08 per 1M input tokens from DeepInfra, and $0.16 per 1M output tokens from DeepInfra. Across 7 serving providers, input prices range from $0.08 to $0.90 per 1M tokens.
What is the context window of Gemma 3 27B?
Gemma 3 27B accepts up to 131K tokens of context and can return up to 131K output tokens.
Which providers serve Gemma 3 27B?
Gemma 3 27B is available from 8 serving providers, each with its own pricing and model ID. DeepInfra is currently the cheapest.
What can Gemma 3 27B do?
Gemma 3 27B supports image input (vision), tool use and structured output.
Other Google models
compare pricing across the Google lineupGemma 4 31B$0.09/1M · 13 providersGemma 4 26B A4B $0.07/1M · 10 providersGemini 2.5 Flash$0.15/1M · 8 providersGemini 3.7 Flash$0.75/1M · 7 providersGemini 2.5 Pro$1.25/1M · 7 providersGemini 3.5 Flash$1.50/1M · 7 providersGemini 3.1 Flash Lite$0.25/1M · 6 providersGemini 3.5 Flash Lite$0.30/1M · 6 providers
Popular comparisons
head-to-head pages featuring Gemma 3 27B
Gemma 3 27B vs GPT-4o Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI