Compare Phi 4 from Microsoft and Mistral Small 4 from Mistral AI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.


Phi 4 and Mistral Small 4 are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
Phi 4, from Microsoft, has a 16,384-token context window and is priced at $0.07/M tokens input, $0.14/M tokens output on OpenRouter.
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.
| Attribute | Phi 4 | Mistral Small 4 |
|---|---|---|
| Input price | $0.07/M tokens | $0.15/M tokens |
| Output price | $0.14/M tokens | $0.60/M tokens |
| Context window | 16,384 tokens | 262,144 tokens |
| Intelligence Index | 5.9 | 9.0 |
| Coding Index | Not available | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | Not available | 0.58 s |
| Throughput (p50) | Not available | 110.0 tok/s |
Benchmark data updated
Phi 4 is cheaper than Mistral Small 4 on OpenRouter: Phi 4 costs $0.07/M tokens input and $0.14/M tokens output, while Mistral Small 4 costs $0.15/M tokens input and $0.60/M tokens output.
Mistral Small 4 has the longer context window at 262,144 tokens, compared with 16,384 tokens for Phi 4.