Gemini 3 Flash API Pricing
Compare prices from 3 providers, including 1 official. 2 price sources are collected automatically.
Data snapshot:
Gemini 3 Flash provider prices and multipliers
Input and output multipliers are each calculated as provider price ÷ official baseline; 1.00× equals the official price.
| Provider / operator | Input / 1M tokens | Output / 1M tokens | vs official | Price evidence | Public operating history | API docs | Refund policy | Payment / invoice |
|---|---|---|---|---|---|---|---|---|
| Google Vertex AIOperator type not confirmed | $0.50 | $3.00 | In 1.00×Out 1.00× | Official price sourcePlatform page ↗Observed: | —Unknown | View docs ↗ | Not provided | Visa · Mastercard · gcp_creditsInvoice support not confirmed |
| Qingfengge APIVerified platformTeam | $0.0276 | $0.0828 | In 0.0552×Out 0.0276× | Live API pricePlatform page ↗Observed: | 3 years 8 monthsDomain verified | View docs ↗ | Refund policy not public | Alipay · WeChat Pay · Business bank transferChinese tax invoice (fapiao) |
| PoloAPIOperator type not confirmed | $10.3448 | $41.3793 | In 20.7×Out 13.8× | Live API pricePlatform page ↗Observed: | —Unknown | View docs ↗ | Not provided | Alipay · WeChat PayInvoice support not confirmed |
Platform-submitted information or domain verification does not mean the price was independently checked and is not a ComputeUnion guarantee of pricing, availability, refunds, compliance, invoices, or service quality.
External capability references
Only source results safely mapped to the official model name are shown.
FAQ
How is Gemini 3 Flash API priced?
Input and output tokens are billed separately. The current recorded official baseline is $0.5000 input / $3.0000 output per 1M tokens.
Which provider is cheapest for Gemini 3 Flash?
The lowest recorded input price is $0.0276/1M tokens from Qingfengge API; verify provider terms and the observation date before production use.
How do official and relay prices differ?
Official and relay channels can differ in price, latency, limits, and service terms; evaluate them separately for production traffic.