theserverless.dev InferenceList

Models

Showing 1–7 of 7 · Sorted by input price, low to high.

More filters
Model Provider Modality Input ↑ Output Context
Google: Gemma 3 12B
Cheaper on DeepInfra (−20%)
Google text image $0.05/1M $0.15/1M 131K
Google: Gemma 3 4B
Cheaper on Amazon Bedrock (−60%)
Google text image $0.05/1M $0.1/1M 131K
Google: Gemma 4 26B A4B
Cheaper on PrimeIntellect (−82.9%)
Google image text video $0.0765/1M $0.255/1M 262K
Google: Gemma 3 27B
Cheaper on DeepInfra (−32.2%)
Google text image $0.08/1M $0.35/1M 131K
Google: Gemma 4 31B
Cheaper on CoreWeave (−36%)
Google image text video $0.2/1M $0.4/1M 262K
Google: Gemini 3.8 Flash TTS
Cheaper on fal (−98.3%)
Google text audio $0.5/1M $9/1M 33K
Google: Gemini 2.5 Pro
Cheaper on Oracle Cloud (−27.3%)
Google text image audio video $1.25/1M $10/1M 1.0M

Token rates are USD per 1M tokens. A dash means the source did not publish that amount. A zero is a real zero.