Back to Models
Long context
gemini-3.7-flash API pricing
Google's Gemini series — very long context windows and strong multimodal input.
Model ID
google/gemini-3.7-flashChatStreamingTool callingVision
Call summary
Input
$0.75$0.23/ 1M tokens
Cache write $0.23
Output
$3.75$1.13/ 1M tokens
Cache read $0.23
Context Window
1.05M
API Endpoints
1
Available Configurations
1
gemini-3.7-flash API endpoints
One API key — call this model through any of the endpoints below.
Production reliability
Privacy-safe aggregates from real Router One model calls, so you can assess stability and response latency before integrating.
Not enough production samples yet
This window needs at least 100 eligible requests across 5 independent principals. Metrics appear automatically after that threshold is met.
More Gemini models on Router One
Same gateway, same API key. Each page lists that model's endpoints, posted price, and context window.
gemini-3.1-pro-preview$6.00 in / $18.00 out per 1M1.05M contextgemini-3.5-flash$0.45 in / $2.70 out per 1M1.05M contextgemini-3.6-flash$0.45 in / $2.70 out per 1M1.05M contextgemini-3-flash-preview$1.20 in / $8.00 out per 1M1.05M contextgemini-3-pro-image-preview$0.50 per imagegemini-3-pro-preview-11-2025$0.882 in / $7.00 out per 1M1.05M context
Start using gemini-3.7-flash
Create an API key and call gemini-3.7-flash on Router One — pay as you go, with per-request cost and latency visibility.