kimi-k2-0905-preview vs Gemini 2.5 Flash
Gemini 2.5 Flash is cheaper on output tokens, while Gemini 2.5 Flash offers a larger context window. Choose kimi-k2-0905-preview or Gemini 2.5 Flash based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | kimi-k2-0905-preview | Gemini 2.5 Flash |
|---|---|---|
| Provider | 302.AI | |
| Input / 1M tokens | $0.63 | $0.30 |
| Output / 1M tokens | $2.53 | $2.50 |
| Context window | 262K | 1M |
| Parameters | — | — |
| Open weights | No | No |
| Released | Sep 2025 | Jun 2025 |
| SWE-bench Verified score | 71.2 | 28.7 |
| LMArena (Chatbot Arena) Elo score | 1380 | 1417 |
| FrontierMath score | — | 4.8 |
| Epoch Capabilities Index score | — | 143 |
| LMArena Vision Elo score | — | 1235 |
FAQ
Is kimi-k2-0905-preview or Gemini 2.5 Flash cheaper?
Gemini 2.5 Flash is cheaper on output tokens ($2.50 vs $2.53 per 1M).
Which has the larger context window, kimi-k2-0905-preview or Gemini 2.5 Flash?
Gemini 2.5 Flash has the larger context window (1M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.