50 models7 providersprices scraped nightly — no estimates
google · gemma family

Gemma 2 2B IT

2B params · 8K context · gemma · released 2024-07

Gemma 2 2B IT is Google DeepMind's smallest Gemma 2 model, a 2-billion-parameter instruction-tuned transformer released July 2024 and designed primarily for on-device and edge inference. On structured tasks like classification and named-entity extraction, it runs comparably to Llama 3.2 3B and IBM Granite 2B, at a fraction of the compute cost. Hosted API versions exist across several providers, but the economics usually favor self-hosting on cheap GPU or running it on-device — inference at this parameter count barely stresses modern hardware. The 8K context limit is consistent with the rest of the Gemma 2 family. License is Gemma, permissive for commercial use but not OSI-approved.

Cheapest now
no hosted pricing yet
90-day price Δ
cheapest-host trend
Fastest TTFT
no data
Providers
0
indexed providers

No pricing data available for this model yet.

No hosted pricing scraped for this model yet. Methodology · Raw data