ModelPickr

Models / Google / Gemma 3 4B IT

Google · gemma

Gemma 3 4B IT

Open multimodal Gemma instruction model for efficient text generation and image understanding

$0.05 in · $0.10 out

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

Provider input prices run from $0.04 to $0.069 per 1M tokens. Output prices run from $0.08 to $0.14.

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
8

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 4B IT

$0.45

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
Amazon Bedrock$0.04$0.08———
Merge Gateway$0.04$0.08———
Deep Infrareference$0.05$0.10———
Eden AI$0.05$0.10———
Hugging Face$0.05$0.10———
Kilo Gateway$0.05$0.10———
OpenRouter$0.05$0.10———
AI/ML API$0.069$0.14$0.055——

Jobs this model qualifies for