Compare Mistral Small 4 from Mistral AI and Nemotron 3.5 Content Safety 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.


Mistral Small 4 and Nemotron 3.5 Content Safety are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
Mistral Small 4, from Mistral AI, has a 262,144-token context window and is priced at $0.15/M tokens input, $0.60/M tokens output on OpenRouter.
Nemotron 3.5 Content Safety, from Nvidia, has a 131,072-token context window and is priced at $0.20/M tokens input, $0.20/M tokens output on OpenRouter.
| Attribute | Mistral Small 4 | Nemotron 3.5 Content Safety |
|---|---|---|
| Input price | $0.15/M tokens | $0.20/M tokens |
| Output price | $0.60/M tokens | $0.20/M tokens |
| Context window | 262,144 tokens | 131,072 tokens |
| Intelligence Index | 9.0 | Not available |
| Coding Index | Not available | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | 0.37 s | 0.18 s |
| Throughput (p50) | 204.0 tok/s | 190.0 tok/s |
Benchmark data updated
Mistral Small 4 and Nemotron 3.5 Content Safety trade off on price: Mistral Small 4 costs $0.15/M tokens input and $0.60/M tokens output, while Nemotron 3.5 Content Safety costs $0.20/M tokens input and $0.20/M tokens output, so Mistral Small 4 is cheaper for input tokens and Nemotron 3.5 Content Safety is cheaper for output tokens.
Mistral Small 4 has the longer context window at 262,144 tokens, compared with 131,072 tokens for Nemotron 3.5 Content Safety.
Mistral Small 4 is faster on OpenRouter, generating a median 204.0 tokens per second compared with 190.0 tokens per second for Nemotron 3.5 Content Safety.