Choose a model to open its comparison page.
MiMo-V2.5 benchmark, API pricing, and provider data cover 144 API providers, with prices starting at $0.0001/M. MiMo-V2.5 free API options are available from 3 providers. The page also shows measured API speed and first-token latency.
Xiaomi MiMo-V2.5 is a native omnimodal sparse MoE model (310B total, 15B active) with unified text, image, video, and audio understanding, built on the MiMo-V2-Flash backbone with dedicated vision and...
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
2 metrics
2 metrics
6 metrics · Rated
4 metrics · Estimated
2 metrics · Provisional
0 metrics · No data
0 metrics · No data
0 metrics · No data
5 metrics · Estimated
0 metrics · No data
Third-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Xiaomi xiaomi/fp8 | $0.140/M | $0.280/M | 99.4% | — | — | 1.0M tokens / 131.1K tokens |
Novita novita/fp8 | $0.168/M | $0.336/M | 98.7% | — | — | 1.0M tokens / 131.1K tokens |
Parasail parasail/fp8 | $0.140/M | $0.280/M | 98.4% | — | — | 1.0M tokens / 1.0M tokens |
Venice venice/fp8 | $0.140/M | $0.280/M | 97.9% | — | — | 1M tokens / 65.5K tokens |
DeepInfra deepinfra/bf16 | $0.400/M | $2/M | 96.7% | — | — | 262.1K tokens / 16.4K tokens |
GMICloud gmicloud/fp8 | $0.140/M | $0.280/M | 91.7% | — | — | 1.1M tokens / — |
Compare MiMo-V2.5 API pricing across 141 providers. Prices range from $0.0001/M to $1398.60/M. 猫羽雫API offers the lowest rate at $0.0001/M. 3 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 0% | mimo-v2.5 | default | $1.00/M Cache read$0.020/M | $2.00/M | 89.9 t/s+16% | 2.13 s-59% | — | |
L1 100% | mimo-v2.5 | default | -40%$0.084/M Cache read$0.0017/M | -40%$0.168/M | 86.1 t/s+11% | 2.08 s-60% | — | |
L1 97% | mimo-v2.5 | 临时渠道 | -96%$0.0055/M Cache read$0.0011/M | -90%$0.027/M | 65.8 t/s | 6.20 s | — | |
L1 100% | mimo-v2.5 | default | -51%$0.068/M Cache read$0.0014/M | -51%$0.137/M | — | — | — | |
L1 100% | mimo-v2.5 | mimo-officially | -18%$0.114/M Cache read$0.0023/M | -18%$0.229/M | — | — | — | |
L1 100% | mimo-v2.5 | default | -2%$0.137/M Cache read$0.0027/M | -2%$0.274/M | — | — | — | |
L1 100% | [按次]mimo-v2.5 | default | $0.092/request | - | — | — | — | |
L1 100% | [按量]mimo-v2.5 | default | $0.920/M Cache read$0.092/M | $1.84/M | — | — | — | |
L1 100% | mimo-v2.5 | default | $0.920/M Cache read$0.092/M | $2.76/M | — | — | — | |
L1 100% | mimo-v2.5 | default | -51%$0.068/M Cache read$0.0014/M | -51%$0.137/M | — | — | — | |
L1 100% | mimo-v2.5 | default | $0.490/M Cache read$0.0098/M | $0.979/M | — | — | — | |
L1 100% | mimo-v2.5 | default | -9%$0.127/M Cache read$0.0025/M | -9%$0.255/M | — | — | — | |
L1 100% | mimo-v2.5 | default | $2.00/M | $2.00/M | — | — | — | |
L1 100% | mimo-v2.5 | default | -86%$0.019/M Cache read$0.0004/M | -86%$0.038/M | — | — | — | |
L1 100% | mimo-v2.5 | default | -32%$0.095/M | $0.284/M | — | — | — | |
L1 100% | mimo-v2.5 | default | -9%$0.127/M Cache read$0.0025/M | -9%$0.255/M | — | — | — | |
L1 100% | mimo-v2.5 | mimo | $0.153/M Cache read$0.031/M | $0.767/M | — | — | — | |
L1 100% | mimo-v2.5 | default | $10.00/request | - | — | — | — | |
L1 99% | mimo-v2.5 | default | -93%$0.0096/M Cache read$0.0002/M | -93%$0.019/M | — | — | — | |
L1 99% | mimo-v2.5 | 国产模型 | $0.010/request | - | — | — | — |
