Compare Gemini 3.8 Flash from Google and Kimi K3 from moonshotai on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
| Attribute | Gemini 3.8 Flash | Kimi K3 |
|---|---|---|
| Input price | $0.75/M tokens | $0.1824/M tokens |
| Output price | $3.75/M tokens | $9.339/M tokens |
| Context window | 1,048,576 tokens | 1,048,576 tokens |
| Intelligence Index | 30.8 | Not available |
| Coding Index | 76.3 | 76.2 |
| Agentic Index | 40.2 | 50.0 |
| Latency (p50) | 2.69 s | 1.34 s |
| Throughput (p50) | 74.0 tok/s | 74.0 tok/s |
| Provided by | moonshotai | |
| Model page | Gemini 3.8 Flash model details, providers and pricing | Kimi K3 model details, providers and pricing |
Benchmark data updated
Gemini 3.8 Flash and Kimi K3 trade off on price: Gemini 3.8 Flash costs $0.75/M tokens input and $3.75/M tokens output, while Kimi K3 costs $0.1824/M tokens input and $9.339/M tokens output, so Kimi K3 is cheaper for input tokens and Gemini 3.8 Flash is cheaper for output tokens.
Gemini 3.8 Flash and Kimi K3 have the same context window of 1,048,576 tokens.
Gemini 3.8 Flash and Kimi K3 generate at the same median throughput on OpenRouter: 74.0 tokens per second.
Gemini 3.8 Flash scores higher on coding, with an Artificial Analysis Coding Index of 76.3 compared with 76.2 for Kimi K3.