ModelPickr

Models / Google / Gemma 3 27B IT

Google · gemma

Gemma 3 27B IT

Largest open Gemma 3 instruction model for multilingual text generation and visual understanding

$0.099 in · $0.30 out

per 1M tokens · provider rate closest to the median. No first-party Google price was listed. The reference price is Cortecs's rate, the provider closest to the median.

Provider input prices run from $0.08 to $0.29 per 1M tokens. Output prices run from $0.16 to $0.63.

Context
131,072
Max output
131,072
Cache read
—
Cache write
—
Reasoning
No
Tool calls
Yes
Structured output
Unknown
Vision
Yes
Open weights
Yes
License
—
Released
Mar 12, 2025
Updated in source
Mar 12, 2025
Knowledge
2024-08
Providers
13

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

Estimated monthly cost

Gemma 3 27B IT

$1.04

Cache hit is ignored because this model has no cache-read price.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
Deep Infra$0.08$0.16———
Hugging Face$0.08$0.16———
Kilo Gateway$0.08$0.16———
Merge Gateway$0.08$0.45$0.04——
OpenRouter$0.08$0.45$0.04——
Cortecsreference$0.099$0.30———
Novita AI$0.12$0.20———
Prime Inference$0.12$0.30———
Venice AI$0.12$0.20———
AI/ML API$0.21$0.63$0.10——
Amazon Bedrock$0.23$0.38———
Eden AI$0.29$0.57———
EmpirioLabs AI$0$0———

Jobs this model qualifies for