ModelPickr

Models / Google / Gemma 4 12B IT

Google · gemma

Gemma 4 12B IT

Compact Gemma 4 instruction model for open, self-hosted chat and reasoning

$0.10 in · $0.30 out

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

Provider input prices run from $0.05 to $0.10 per 1M tokens. Output prices run from $0.25 to $0.30.

Context
262,144
Max output
32,768
Cache read
—
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
Yes
License
—
Released
Jun 9, 2026
Updated in source
Jun 9, 2026
Knowledge
—
Providers
2

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 4 12B IT

$1.05

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. One row per provider.
ProviderInputOutputCache readCache writeStatus
NanoGPT$0.05$0.25$0.025——
SiliconFlowreference$0.10$0.30———