Guide
Gemini pricing, explained with examples
Gemini 3.8 Flash's list price is $0.75 per million input tokens and $3.75 per million output tokens, with a 1,048,576-token context window. Indicative prices, checked 2026-11-04.
One call: 10,000 tokens in, 2,000 out
| Model | Input cost | Output cost | Total |
|---|---|---|---|
| Gemini 3.8 Flash | $0.0075 | $0.0075 | $0.0150 |
| Gemini 4 Argon | $0.0200 | $0.0200 | $0.0400 |
A month at volume: 10M tokens in, 2M out
| Model | Input cost | Output cost | Total |
|---|---|---|---|
| Gemini 3.8 Flash | $7.5000 | $7.5000 | $15.0000 |
| Gemini 4 Argon | $20.0000 | $20.0000 | $40.0000 |
Gemini's edge is the window: whole codebases and book-length documents fit without chunking. Flash is the cheapest way to process large volumes — roughly a third of Argon's price for the same tokens.
Dated rates: 3.8 Flash costs $0.75/$3.75 only through December 31, 2026 ($1.50/$7.50 from January 1, 2027). Argon costs $2/$10 only through November 30, 2026 ($4/$20 from December 1, 2026). The previous 2.5 Pro and 2.5 Flash are deprecated: from December 1, 2026 their API requests auto-route to 3.8 Flash and 3.5 Flash-Lite respectively.