Compare Kimi K3 from moonshotai and Hy4 preview from tencent on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.




Kimi K3 and Hy4 preview are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
Kimi K3, from moonshotai, has a 1,048,576-token context window and is priced at $0.19/M tokens input, $8.94/M tokens output on OpenRouter.
Hy4 preview, from tencent, has a 1,048,576-token context window and is priced at $0.834/M tokens input, $2.501/M tokens output on OpenRouter.
| Attribute | Kimi K3 | Hy4 preview |
|---|---|---|
| Input price | $0.19/M tokens | $0.834/M tokens |
| Output price | $8.94/M tokens | $2.501/M tokens |
| Context window | 1,048,576 tokens | 1,048,576 tokens |
| Intelligence Index | 43.6 | Not available |
| Coding Index | 76.2 | Not available |
| Agentic Index | 50.0 | Not available |
| Latency (p50) | 1.69 s | 1.22 s |
| Throughput (p50) | 75.0 tok/s | 53.0 tok/s |
Benchmark data updated
Kimi K3 and Hy4 preview trade off on price: Kimi K3 costs $0.19/M tokens input and $8.94/M tokens output, while Hy4 preview costs $0.834/M tokens input and $2.501/M tokens output, so Kimi K3 is cheaper for input tokens and Hy4 preview is cheaper for output tokens.
Kimi K3 and Hy4 preview have the same context window of 1,048,576 tokens.
Kimi K3 is faster on OpenRouter, generating a median 75.0 tokens per second compared with 53.0 tokens per second for Hy4 preview.