Same model, served by 3 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | google/gemini-3.1-flash-lite | standardQuantization not disclosedReduced context (1M of 1M) | $0.25 | $1.5 | — | $0.563 | Verified 6h ago · Changed 8h ago | |
Google Gemini API Original creator | gemini-3.1-flash-lite | standardQuantization not disclosed | $0.25 | $1.5 | $0.025 | $0.563 | Verified 8h ago · Changed 8h ago | |
Google Vertex AI | gemini-3.1-flash-lite | standardQuantization not disclosed | $0.25 | $1.5 | $0.025 | $0.563 | Verified 8h ago · Changed 8h 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.
| DeepInfra | $55/mo |
| Google Gemini API | $55/mo |
| Google Vertex AI | $55/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.