Google offers flexible pricing for Gemini API access on Vertex AI based on token consumption.
Pricing tiers include Gemini 3 Flash ($0.50/1M input tokens), Gemini 3 Pro ($2.00/1M input), and Gemini 1.5 Pro.
Context caching reduces costs at $0.25 per 1M cached tokens per hour. Batch prediction offers reduced pricing.
Provisioned Throughput provides guaranteed capacity for production workloads at committed pricing.
Rich media inputs (video, audio, images) consume significantly more tokens than text.
In conclusion, Google provides multiple pricing options to match different enterprise needs and usage patterns.
Last verified: 2/6/2026
Sources:
Knowledge provided by Answers.org.
If any information on this page is erroneous, please contact hello@answers.org.
Answers.org content is verified by brands themselves. If you're a brand owner and want to claim your page, please click here.