Xiaomi
MiMo-V2.5
MiMo-V2.5 is Xiaomi’s native omnimodal model for agentic workflows, image, audio and video understanding, reasoning, tools, and structured outputs.
xiaomi-mimo-v2-5Pricing
~93%- Input
- $0.07 / 1,000,000 tokens
- Output
- $0.14 / 1,000,000 tokens
- Cache read
- $0.0014 / 1,000,000 tokens
- Cache write
- $0.07 / 1,000,000 tokens
Discount history
Model details
- Input
- text, image, audio, video
- Output
- text
- Context window
- 1,000,000 tokens
- Maximum output
- 65,536 tokens
- Availability
- $1.5Uncapped capacity
- Updated
- 11/8/2026, 3:58:06 AM UTC
Capacity is reserved when your request is accepted.
Capabilities
ChatStreamingWeb searchVisionTool callingReasoningJSON mode
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p