MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.
$0.20market price $0.40
$0.04market price $0.08
$1.00market price $2.00
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks.
On NagaAI, MiMo-V2.5 costs $0.20 per 1M input tokens and $1 per 1M output tokens. You pay only for what you use, with no subscription.
MiMo-V2.5 reads up to 1.1M tokens in one request, counting the prompt and the answer together.
Yes. MiMo-V2.5 can call your functions as tools and can answer in a JSON schema you give it.
It takes text and images as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
MiMo-V2.6-Pro-UltraSpeedXiaomiMiMo-V2.6-FlashXiaomiMiMo-V2.6-ProXiaomiMiMo-V2.5-ProXiaomi
LFM3-1.7BLiquid AI$0.04 / $0.10 per 1M
Ripple 65B PreviewRicursive AI$0.10 / $0.30 per 1M