Compare MiniMax M2-her from MiniMax and Ministral 3 3B 2512 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.


MiniMax M2-her and Ministral 3 3B 2512 are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
MiniMax M2-her, from MiniMax, has a 65,536-token context window and is priced at $0.30/M tokens input, $1.20/M tokens output on OpenRouter.
Ministral 3 3B 2512, from Mistral AI, has a 131,072-token context window and is priced at $0.10/M tokens input, $0.10/M tokens output on OpenRouter.
| Attribute | MiniMax M2-her | Ministral 3 3B 2512 |
|---|---|---|
| Input price | $0.30/M tokens | $0.10/M tokens |
| Output price | $1.20/M tokens | $0.10/M tokens |
| Context window | 65,536 tokens | 131,072 tokens |
| Intelligence Index | Not available | 4.8 |
| Coding Index | Not available | 4.8 |
| Agentic Index | Not available | 0.8 |
| Latency (p50) | 0.74 s | 0.35 s |
| Throughput (p50) | 51.5 tok/s | 130.0 tok/s |
Benchmark data updated
Ministral 3 3B 2512 is cheaper than MiniMax M2-her on OpenRouter: Ministral 3 3B 2512 costs $0.10/M tokens input and $0.10/M tokens output, while MiniMax M2-her costs $0.30/M tokens input and $1.20/M tokens output.
Ministral 3 3B 2512 has the longer context window at 131,072 tokens, compared with 65,536 tokens for MiniMax M2-her.
Ministral 3 3B 2512 is faster on OpenRouter, generating a median 130.0 tokens per second compared with 51.5 tokens per second for MiniMax M2-her.