Choose a model to open its comparison page.
MiMo-V2-Flash benchmark, API pricing, and provider data cover 14 API providers, with prices starting at $0.0014/M. MiMo-V2-Flash free API options are available from 1 provider. The page also shows measured API speed and first-token latency.
Xiaomi MiMo-V2-Flash is an open-source MoE language model with 309B total and 15B active parameters, optimized for fast reasoning and agentic workflows with up to 256K context.
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
Input and output token limits for this model, plus how it ranks on long-context understanding.
1 metric
4 metrics · Estimated
6 metrics · Estimated
4 metrics · Rated
5 metrics · Provisional
1 metric · Provisional
0 metrics · No data
0 metrics · No data
1 metric · Provisional
Compare MiMo-V2-Flash API pricing across 13 providers. Prices range from $0.0014/M to $0.095/M. 6345ywz API offers the lowest rate at $0.0014/M. 1 provider offers free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | mimo-v2-flash | mimo-officially | $0.080/M Cache read$0.0080/M | $0.240/M | — | — | — | |
L1 100% | MiMo-V2-Flash | default | $0.010/request | - | — | — | — | |
L1 100% | mimo-v2-flash | default | $0.019/M Cache read$0.0004/M | $0.038/M | — | — | — | |
L1 100% | mimo-v2-flash | other | $0.042/M Cache read$0.021/M | $0.125/M | — | — | — | |
Dext API Free | L1 100% | mimo-v2-flash | 公益 | Free | Free | — | — | — |
L1 100% | xiaomi/mimo-v2-flash | default | $0.095/M | $0.284/M | — | — | — | |
L1 99% | xiaomi/mimo-v2-flash | 0倍倍率分组 | $0.0014/M Cache read$0.0007/M | $0.0040/M | — | — | — | |
L1 100% | mimo-v2-flash | default | $0.077/M | $0.230/M | — | — | — | |
L1 99% | mimo-v2-flash | SSVIP | $0.025/request | - | — | — | — | |
L1 1% | mimo-v2-flash | XiaoMi | $0.011/M Cache read$0.0011/M | $0.033/M | — | — | — |
