XiaomiMiMo/MiMo-V2-Flash
by NovitaAI · family mimo · listed Dec 2025RTW
MiMo flash model for fast multimodal assistance and agent workflows
Current rates USD per 1M tokens
Input$0.10
Output$0.30
Cache read$0.30
Cache write—
Against the market
On the record
- Model id
xiaomimimo/mimo-v2-flash- Context window
- 262K tokens
- Max output
- 32K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Dec 2024
- Released
- 2025-12-19
- Last updated
- 2025-12-19
- Provider docs
- novita.ai/docs/guides/introduction
Back of the envelope
≈
Also listed at
- Jiekou.AIfree in · free out
- Kilo Gateway$0.09 in · $0.29 out
- Qiniu$0.10 in · $0.30 out
- Vercel AI Gateway$0.10 in · $0.30 out
- Hugging Face$0.10 in · $0.30 out
- ZenMux$0.10 in · $0.30 out
- Meganova$0.10 in · $0.30 out
- NanoGPT$0.102 in · $0.306 out
- Xiaomi$0.14 in · $0.28 out