MiMo-V2.6-Pro is the flagship foundation model from Xiaomi, built at a scale of over 1T parameters for the most demanding workloads. It has a 1M-token context window and native multimodal support. It is optimized for agentic workflows and performs at a high level across coding, visual, general, and research scenarios, including complex, long-horizon tasks across many agent harnesses.
$0.163market price $0.326
$0.0015market price $0.003
$0.326market price $0.652
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-V2.6-Pro is the flagship foundation model from Xiaomi, built at a scale of over 1T parameters for the most demanding workloads. It has a 1M-token context window and native multimodal support.
On NagaAI, MiMo-V2.6-Pro costs $0.163 per 1M input tokens and $0.326 per 1M output tokens. You pay only for what you use, with no subscription.
MiMo-V2.6-Pro reads up to 1.0M tokens in one request, counting the prompt and the answer together.
Yes. MiMo-V2.6-Pro 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-V2.5-ProXiaomiMiMo-V2.5Xiaomi
LFM3-1.7BLiquid AI$0.04 / $0.10 per 1M
Ripple 65B PreviewRicursive AI$0.10 / $0.30 per 1M