google Open weights Vision

Gemma 3 27B pricing & benchmarks

Released Mar 12, 2025 · served by 5 providers

Input / 1M tokens$0.080
Output / 1M tokens$0.160
Context window262K
Cached input$0.040
Intelligence index7.4
Coding index10.1
Agentic index0.3
1M in + 300K out$0.13

What Gemma 3 27B is

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,...

Providers and prices for Gemma 3 27B

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
DeepInfracheapest $0.080 $0.160 131K fp8 99.6%
Novita $0.119 $0.200 98K bf16 86.7%
Nebius $0.100 $0.300 110K fp8 72.9%
Parasail $0.080 $0.450 131K fp8 99.5%
Phala $0.150 $0.460 262K 95.5%

Cheaper models in the same class

Models scoring within 4 points of Gemma 3 27B on the Intelligence Index, but with a lower output price.

FAQ

How much does the Gemma 3 27B API cost?

$0.080 per 1M input tokens and $0.160 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.13.

Is Gemma 3 27B free?

No. It is a paid model starting at $0.080 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Gemma 3 27B?

DeepInfra at $0.080 input / $0.160 output per 1M tokens (fp8 quantization).

Can I self-host Gemma 3 27B?

Yes — weights are published as google/gemma-3-27b-it on Hugging Face, so you can run it on your own hardware.