Gemini 3.8 Flash API pricing Promo until 2026-12-31
Gemini 3.8 Flash by Google Vertex AI costs $1.50 per 1M input tokens and $7.50 per 1M output tokens (1M in + 1M out = $9.00).
- API model id
Gemini 3.8 Flash- Input / 1M
- $1.50
- Output / 1M
- $7.50
- Cached input / 1M
- $0.15
- Context window
- —
- Promotional price
- $0.75 in / $3.75 out / $0.075 cached, valid through 2026-12-31. Standard price above applies after that.
- Notes
- Standard price.
- Source
- https://cloud.google.com/vertex-ai/generative-ai/pricing
- Provider type
- Cloud (HQ: US)
- Regions
- Global, Regional
- EU data residency
- unknown — Global and non-global (regional) endpoints are offered (~10% uplift for regional); which EU regions host which model is not listed on the pricing page.
- Last verified
- 2026-10-15
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| Google Vertex AI | Gemini 3.8 Flash | $3.38 |
Uses standard list prices (no caching, batch or off-peak discounts). € and CHF rows are priced in that currency by the provider and not converted, so compare them with care.
Other Google Vertex AI models
- Gemini 4 Argon: $4.00 / $20.00
- Gemini 3.5 Flash-Lite: $0.30 / $2.50
- Claude Sonnet 5.5: $2.00 / $10.00
- Claude Opus 5.5: $4.00 / $20.00
- Grok 4.7: $2.00 / $6.00
- gpt-oss-120b: $0.09 / $0.36
- Llama 4 Maverick: $0.35 / $1.15
- Mistral Medium 3: $0.40 / $2.00