Context bandAll contexts
- Input
- $0.7500
- Output
- $3.75
- Cache read
- $0.0750
Google · active
Gemini 3.8 Flash
Google's production Flash model for agentic and complex enterprise workflows.
API model
gemini-3.8-flash- Context
- 1M
- Max output
- 64K
- Bands
- 01
Current standard pricingUSD · per 1M tokens
Pricing provenanceVerified Oct 5, 2026
Pricing historyAll pricing changes
- Input: $0.7500 → $1.50Output: $3.75 → $7.50Cache read: $0.0750 → $0.1500
Price a workloadPreselected: Gemini 3.8 Flash
01
1/4 modelsSet your workload
02
calibratedLive monthly estimate
Google
Lowest costGemini 3.8 Flash
$8.25/ month
- Input
- $0.7500
- Output
- $7.50
- Cached
- $0.00000000
- Context rate
- Flat
Rate alternativessource-backed only
Cache-readSet cached input tokens above zero to estimate cache-read savings.
UnavailableBatchPublished batch rate unavailable for one or more required dimensions.
UnavailableVerified Oct 5, 2026Official pricing ↗