Same open weights, served by 3 providers. Weights: google/gemma-4-26B-A4B-it.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | google/gemma-4-26B-A4B-it | flexFP80.8× standard | $0.056 | $0.272 | — | $0.11 | Verified 4h ago · Changed 7h ago | |
DeepInfra | google/gemma-4-26B-A4B-it | standardFP8 | $0.07 | $0.34 | — | $0.138 | Verified 4h ago · Changed 7h ago | |
AWS Bedrock | google.gemma-4-26b-a4b | standardQuantization not disclosed | $0.13 | $0.40 | — | $0.198 | Verified 6h ago · Changed 6h ago | |
DeepInfra | google/gemma-4-26B-A4B-it | priorityFP81.5× standard | $0.105 | $0.51 | — | $0.206 | Verified 4h ago · Changed 7h ago | |
Google Vertex AI | google/gemma-4-26b-a4b-it-maas | standardQuantization not disclosed | $0.15 | $0.60 | $0.015 | $0.262 | Verified 6h ago · Changed 6h 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 fp8 | $13.8/mo |
| AWS Bedrock | $21/mo |
| Google Vertex AI | $27/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.