Compare Ministral 3 14B 2512 from Mistral AI and Nemotron 3 Nano 30B A3B 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.


Ministral 3 14B 2512 and Nemotron 3 Nano 30B A3B are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
Ministral 3 14B 2512, from Mistral AI, has a 262,144-token context window and is priced at $0.20/M tokens input, $0.20/M tokens output on OpenRouter.
Nemotron 3 Nano 30B A3B, from Nvidia, has a 262,144-token context window and is priced at $0.05/M tokens input, $0.20/M tokens output on OpenRouter.
| Ministral 3 14B 2512 | Nemotron 3 Nano 30B A3B | |
|---|---|---|
| Input price | $0.20/M tokens | $0.05/M tokens |
| Output price | $0.20/M tokens | $0.20/M tokens |
| Context window | 262,144 tokens | 262,144 tokens |
| Intelligence Index | 6.0 | 6.8 |
| Coding Index | 14.4 | Not available |
| Agentic Index | 1.1 | Not available |
| Latency (p50) | 0.25 s | 0.30 s |
| Throughput (p50) | 72.5 tok/s | 265.0 tok/s |
Nemotron 3 Nano 30B A3B is cheaper than Ministral 3 14B 2512 on OpenRouter: Nemotron 3 Nano 30B A3B costs $0.05/M tokens input and $0.20/M tokens output, while Ministral 3 14B 2512 costs $0.20/M tokens input and $0.20/M tokens output.
Ministral 3 14B 2512 and Nemotron 3 Nano 30B A3B have the same context window of 262,144 tokens.
Nemotron 3 Nano 30B A3B is faster on OpenRouter, generating a median 265.0 tokens per second compared with 72.5 tokens per second for Ministral 3 14B 2512.