Inworld Inference adds Xiaomi MiMo V2.6 Flash model
What happened
Inworld AI has hosted Xiaomi's MiMo V2.6 Flash model on its Inworld Inference platform. According to Inworld's official X account, the model is an open-weight inference model that supports vision and function calling, with a context length of 524K tokens. On pricing, Inworld says the model costs $0.14 per million input tokens and $0.28 per million output tokens, with a cached input price of $0.003, and that long conversations remain inexpensive. These prices are Inworld's own claims, and the report includes no independent verification. Inworld also says the MiMo V2.6 series has been demonstrated for 3D game development.
AI-written from the coverage · updated 26 d ago
Coverage timeline
Follow the coverage to see the story from different sides.
- Inworld AIInworld launches Xiaomi's MiMo V2.6 Flash model
Xiaomi's MiMo V2.6 Flash is now hosted on Inworld Inference: - Open-weight inference model with vision and function calling support - The V2.6 series has been demonstrated for 3D game development - 524K-token context window - $0.14 per million input tokens and $0.28 per million output tokens - Cached input priced at $0.003, so long conversations remain inexpensive Learn more: http://inworld.ai/models