Compare Gemini 4 Argon 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 4 Argon | Kimi K3 |
|---|---|---|
| Input price | $2/M tokens | $0.1495/M tokens |
| Output price | $10/M tokens | $7.15/M tokens |
| Context window | 1,048,576 tokens | 1,048,576 tokens |
| Intelligence Index | 50.4 | Not available |
| Coding Index | Not available | 76.2 |
| Agentic Index | Not available | 50.0 |
| Latency (p50) | 4.72 s | 1.08 s |
| Throughput (p50) | 36.0 tok/s | 66.0 tok/s |
| Provided by | moonshotai | |
| Model page | Gemini 4 Argon model details, providers and pricing | Kimi K3 model details, providers and pricing |
Benchmark data updated
Kimi K3 is cheaper than Gemini 4 Argon on OpenRouter: Kimi K3 costs $0.1495/M tokens input and $7.15/M tokens output, while Gemini 4 Argon costs $2/M tokens input and $10/M tokens output.
Gemini 4 Argon and Kimi K3 have the same context window of 1,048,576 tokens.
Kimi K3 is faster on OpenRouter, generating a median 66.0 tokens per second compared with 36.0 tokens per second for Gemini 4 Argon.