Compare MiMo-V2.5 from Xiaomi and DeepSeek V4 Flash 0731 from DeepSeek on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
| Attribute | MiMo-V2.5 | DeepSeek V4 Flash 0731 |
|---|---|---|
| Input price | $0.40/M tokens | $0.0434/M tokens |
| Output price | $2/M tokens | $0.30/M tokens |
| Context window | 1,000,000 tokens | 1,048,576 tokens |
| Intelligence Index | Not available | Not available |
| Coding Index | 56.8 | 69.1 |
| Agentic Index | 15.8 | 41.0 |
| Latency (p50) | 32.25 s | 0.41 s |
| Throughput (p50) | 8.0 tok/s | 77.0 tok/s |
| Provided by | Xiaomi | DeepSeek |
| Model page | MiMo-V2.5 model details, providers and pricing | DeepSeek V4 Flash 0731 model details, providers and pricing |
Benchmark data updated
DeepSeek V4 Flash 0731 is cheaper than MiMo-V2.5 on OpenRouter: DeepSeek V4 Flash 0731 costs $0.0434/M tokens input and $0.30/M tokens output, while MiMo-V2.5 costs $0.40/M tokens input and $2/M tokens output.
DeepSeek V4 Flash 0731 has the longer context window at 1,048,576 tokens, compared with 1,000,000 tokens for MiMo-V2.5.
DeepSeek V4 Flash 0731 is faster on OpenRouter, generating a median 77.0 tokens per second compared with 8.0 tokens per second for MiMo-V2.5.
DeepSeek V4 Flash 0731 scores higher on coding, with an Artificial Analysis Coding Index of 69.1 compared with 56.8 for MiMo-V2.5.