Ways to buy 6
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
 Google Vertex AIglobal-flex, cheapest · cached $0.037 | $0.375 | $1.88 | $0.375 / $1.88-50% vs list | $0.037 | -50% vs list |
 Google Gemini APIflex · cached $0.037 | $0.375 | $1.88 | $0.375 / $1.88-50% vs list | $0.037 | -50% vs list |
| Google Gemini API API The lab's own API · cached $0.075 | $0.75 | $3.75 | $0.75 / $3.75List price | $0.075 | List price |
| Google Vertex AI global · cached $0.075 | $0.75 | $3.75 | $0.75 / $3.75Same as list | $0.075 | Same as list |
| Google Vertex AI global-priority · cached $0.135 | $1.35 | $6.75 | $1.35 / $6.75+80% vs list | $0.135 | +80% vs list |
| Google Gemini API priority · cached $0.135 | $1.35 | $6.75 | $1.35 / $6.75+80% vs list | $0.135 | +80% vs list |
USD per 1M tokens; batch $0.375 in, $1.88 out on the lab's API. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $150.00 direct.
Helicone$150.00+0%
Kong AI Gateway$150.00+0%
LiteLLM$150.00+0%
Vercel AI Gateway$150.00+0%
Cloudflare AI Gateway$157.50+5%
Requesty$157.50+5%
Eden AI$158.25+5.5%
OpenRouter$158.25+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
| Gemini 3.7 Flash Google · 1MCheapest: $0.75 on Google Vertex AI (global-flex) | $0.75 | $3.75 | $0.75 / $3.75100% | $1.5 | 1M | $0.75 on Google Vertex AI (global-flex) | 100% |
| Gemini 3.5 Flash Lite Google · 1MCheapest: $0.425 on Google Vertex AI (global-flex) | $0.3 | $2.5 | $0.3 / $2.5 | $0.85 | 1M | $0.425 on Google Vertex AI (global-flex) | · |
| Gemini 3.6 Flash Google · 1MCheapest: $0.75 on Google Vertex AI (global-flex) | $0.75 | $3.75 | $0.75 / $3.75 | $1.5 | 1M | $0.75 on Google Vertex AI (global-flex) | · |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) Google · 66K | $0.25 | $1.5 | $0.25 / $1.5 | $0.563 | 66K | Lab list price | · |
 Muse Spark 1.3Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · |
| Muse Spark 1.1 Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · |
 Qwen3.8 Max (0902)Qwen (Alibaba) · 1M | $2 | $6 | $2 / $6 | $3 | 1M | Lab list price | · |
 Kimi K3Moonshot AI · 1M | $0.885 | $10.5 | $0.885 / $10.5 | $3.3 | 1M | on Sail Research (fp4) | · |
About Gemini 3.8 Flash
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
Takes text, image, video, files, audio in and returns text. First listed Sep 2, 2026. Up to 66K output tokens. Blended price $1.5 per 1M tokens at 3 input to 1 output. Overall score 15 on leadersboard.fru.dev (rank 13). Model id gemini-3-8-flash.
Price history
List price since Sep 2, 2026, from Internet Archive snapshots of the OpenRouter catalog, then daily reads.
Across fru.devCompany profile7 acquisitionsPay schedule7 conferences
Questions
How much does Gemini 3.8 Flash cost?
$0.75 per million input tokens and $3.75 per million output tokens, with cached input at $0.075, or $0.375 and $1.88 through the Batch API.
What is the context window of Gemini 3.8 Flash?
1M tokens, with up to 66K tokens of output.
Where is Gemini 3.8 Flash cheapest?
Of 6 routes tracked, Google Vertex AI is cheapest at $0.375 input and $1.88 output per million tokens.
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.