Same model, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Google Gemini API Original creator | gemini-3.5-flash-lite | standardQuantization not disclosed | $0.30 | $2.5 | $0.03 | $0.85 | Verified 7h ago · Changed 7h ago | |
Google Vertex AI | gemini-3.5-flash-lite | standardQuantization not disclosed | $0.30 | $2.5 | $0.03 | $0.85 | Verified 7h ago · Changed 7h ago |
Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.
| Google Gemini API | $80/mo |
| Google Vertex AI | $80/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.