Google · Pricing & cost calculator
Google's frontier model. 2M-token context is the killer feature.
Input tokens
$0.00125
per 1,000 tokens
Output tokens
$0.01000
per 1,000 tokens
Context window
2,000,000
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
$0.006875
at 1,500/500 tokens
Monthly spend
$68.75
10,000 requests × $0.006875
Could save ~92% with a similar-quality alternative
Same workload at 1,500/500 tokens × 10,000 req/month: $69 → $5. ~8× cheaper on input.
TrackCost's gateway auto-detects which requests are safe to route to the cheaper model and flags the ones that need Gemini 2.5 Pro's full capability. You stay in control — we surface the opportunity.
Gemini 2.5 Pro costs $0.00125 per 1,000 input tokens and $0.01000 per 1,000 output tokens as of the current Google API pricing.
Gemini 2.5 Flash is significantly cheaper than Gemini 2.5 Pro (~8× cheaper on input) and often works fine for tasks that don't need Gemini 2.5 Pro's full capability. TrackCost automatically suggests model downgrades where safe.
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 Pro supports up to 2,000,000 tokens of context. For comparison with other models, use the TrackCost savings calculator.