Compare Kimi K3 from moonshotai and Nemotron 3.5 Super VL from Nvidia 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 Nemotron 3.5 Super VL 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 $0.239/M tokens input, $11.94/M tokens output on OpenRouter.
Nemotron 3.5 Super VL, from Nvidia, has a 1,048,576-token context window and is priced at $0.10/M tokens input, $0.40/M tokens output on OpenRouter.
| Attribute | Kimi K3 | Nemotron 3.5 Super VL |
|---|---|---|
| Input price | $0.239/M tokens | $0.10/M tokens |
| Output price | $11.94/M tokens | $0.40/M tokens |
| Context window | 1,048,576 tokens | 1,048,576 tokens |
| Intelligence Index | 43.6 | 26.5 |
| Coding Index | 76.2 | Not available |
| Agentic Index | 50.0 | Not available |
| Latency (p50) | 0.98 s | 0.18 s |
| Throughput (p50) | 74.0 tok/s | 171.0 tok/s |
Benchmark data updated
Nemotron 3.5 Super VL is cheaper than Kimi K3 on OpenRouter: Nemotron 3.5 Super VL costs $0.10/M tokens input and $0.40/M tokens output, while Kimi K3 costs $0.239/M tokens input and $11.94/M tokens output.
Kimi K3 and Nemotron 3.5 Super VL have the same context window of 1,048,576 tokens.
Nemotron 3.5 Super VL is faster on OpenRouter, generating a median 171.0 tokens per second compared with 74.0 tokens per second for Kimi K3.