Compare MiniMax M3 from MiniMax and Phi 4 from Microsoft on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
MiniMax M3 and Phi 4 are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
MiniMax M3, from MiniMax, has a 1,048,576-token context window and is priced at $0.23/M tokens input, $0.96/M tokens output on OpenRouter.
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.
| MiniMax M3 | Phi 4 | |
|---|---|---|
| Input price | $0.23/M tokens | $0.07/M tokens |
| Output price | $0.96/M tokens | $0.14/M tokens |
| Context window | 1,048,576 tokens | 16,384 tokens |
| Intelligence Index | 29.2 | 5.9 |
| Coding Index | 58.6 | Not available |
| Agentic Index | 29.5 | Not available |
| Latency (p50) | 0.91 s | 1.78 s |
| Throughput (p50) | 42.0 tok/s | 65.0 tok/s |
Phi 4 is cheaper than MiniMax M3 on OpenRouter: Phi 4 costs $0.07/M tokens input and $0.14/M tokens output, while MiniMax M3 costs $0.23/M tokens input and $0.96/M tokens output.
MiniMax M3 has the longer context window at 1,048,576 tokens, compared with 16,384 tokens for Phi 4.
Phi 4 is faster on OpenRouter, generating a median 65.0 tokens per second compared with 42.0 tokens per second for MiniMax M3.