Same open weights, served by 1 provider. Weights: google/gemma-4-E4B-it.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2026-10-01 | google/gemma-4-E4B-it | flexFull precision0.8× standard | $0.016 | $0.08 | — | $0.032 | Verified 5h ago · Changed 7h ago | |
DeepInfra Deprecated, 2026-10-01 | google/gemma-4-E4B-it | standardFull precision | $0.02 | $0.10 | — | $0.04 | Verified 5h ago · Changed 7h ago | |
DeepInfra Deprecated, 2026-10-01 | google/gemma-4-E4B-it | priorityFull precision1.5× standard | $0.03 | $0.15 | — | $0.06 | Verified 5h 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.
| DeepInfra bfloat16 | $4/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.