MiMo-V2.5
AI model by Xiaomi. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. MiMo-V2.5 is a budget-tier option from Xiaomi at $0.28/M output tokens. Despite the low price, it scores competitively on GPQA Diamond (84.9%) and IFBench (67.1%) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, MiMo-V2.5 reports 74 tok/s output speed and 3348ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.
Cost model. For a workload of 1M input tokens + 100K output tokens, MiMo-V2.5 costs $0.17 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-03.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
MiMo-V2.5Current | $0.14 | $0.28 | 74 tok/s |
| DeepSeek V4 Flash (Non-reasoning) | $0.14 | $0.28 | 113 tok/s |
| DeepSeek V4 Flash 0731 (Reasoning, Max Effort) | $0.14 | $0.28 | 90 tok/s |
| DeepSeek V4 Flash (Reasoning, High Effort) | $0.14 | $0.28 | 0 tok/s |
| DeepSeek V4 Flash (Reasoning, Max Effort) | $0.14 | $0.28 | 0 tok/s |
| Gemma 4 12B (Non-reasoning) | $0.10 | $0.30 | 129 tok/s |