Compare Ministral 3 3B 2512 from Mistral and Voxtral Small 24B 2507 from Mistral on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.




| Attribute | Ministral 3 3B 2512 | Voxtral Small 24B 2507 |
|---|---|---|
| Input price | $0.10/M tokens | $0.10/M tokens |
| Output price | $0.10/M tokens | $0.30/M tokens |
| Context window | 131,072 tokens | 32,768 tokens |
| Intelligence Index | Not available | Not available |
| Coding Index | 4.8 | Not available |
| Agentic Index | 0.8 | Not available |
| Latency (p50) | 0.34 s | 0.73 s |
| Throughput (p50) | 141.0 tok/s | 61.0 tok/s |
| Provided by | Mistral | Mistral |
| Model page | Ministral 3 3B 2512 model details, providers and pricing | Voxtral Small 24B 2507 model details, providers and pricing |
Benchmark data updated
Ministral 3 3B 2512 is cheaper than Voxtral Small 24B 2507 on OpenRouter: Ministral 3 3B 2512 costs $0.10/M tokens input and $0.10/M tokens output, while Voxtral Small 24B 2507 costs $0.10/M tokens input and $0.30/M tokens output.
Ministral 3 3B 2512 has the longer context window at 131,072 tokens, compared with 32,768 tokens for Voxtral Small 24B 2507.
Ministral 3 3B 2512 is faster on OpenRouter, generating a median 141.0 tokens per second compared with 61.0 tokens per second for Voxtral Small 24B 2507.