gemini-2.5-flash-preview-05-20 vs Gemini 3 Flash Thinking
Gemini 3 Flash Thinking is cheaper on output tokens. Choose gemini-2.5-flash-preview-05-20 or Gemini 3 Flash Thinking based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | gemini-2.5-flash-preview-05-20 | Gemini 3 Flash Thinking |
|---|---|---|
| Provider | Jiekou.AI | NanoGPT |
| Input / 1M tokens | $0.14 | $0.50 |
| Output / 1M tokens | $3.15 | $3.00 |
| Context window | 1M | 1M |
| Parameters | — | — |
| Open weights | No | No |
| Released | Jan 2026 | Dec 2025 |
| Aider Polyglot score | 55.1 | — |
| LiveBench score | — | 73.0 |
FAQ
Is gemini-2.5-flash-preview-05-20 or Gemini 3 Flash Thinking cheaper?
Gemini 3 Flash Thinking is cheaper on output tokens ($3.00 vs $3.15 per 1M).
Which has the larger context window, gemini-2.5-flash-preview-05-20 or Gemini 3 Flash Thinking?
Both models offer a similar context window.
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.