Google · Pricing & cost calculator
Google's GPT-4o-mini equivalent. Cheap + huge context + fast.
Input tokens
$0.00015
per 1,000 tokens
Output tokens
$0.00060
per 1,000 tokens
Context window
1,000,000
tokens max
Prices sourced from Google's public API rate card. Last reviewed April 2026.
Drag the sliders. The math runs in your browser.
Per request
$0.000525
at 1,500/500 tokens
Monthly spend
$5.25
10,000 requests × $0.000525
Gemini 2.5 Flash costs $0.00015 per 1,000 input tokens and $0.00060 per 1,000 output tokens as of the current Google API pricing.
Gemini 2.5 Flash is already one of the cheapest options in its tier. For budget-critical workloads, consider caching common requests to save more.
The three highest-leverage ways: (1) route requests to a cheaper model where possible, (2) cache identical requests so you don't pay twice for the same response, (3) set hard monthly budgets that block requests when exceeded. TrackCost automates all three at the gateway layer.
Gemini 2.5 Flash supports up to 1,000,000 tokens of context. For comparison with other models, use the TrackCost savings calculator.