Xiaomi's flagship 1T-parameter model with 42B activations, 1M ultra-long context, and deep thinking capabilities. Performs comparably to Claude Opus 4.6 in agent scenarios.
OffRail routes requests to the best providers that are able to handle your prompt size and parameters.
Xiaomi's flagship 1T-parameter model with 42B activations, 1M ultra-long context, and deep thinking capabilities. Performs comparably to Claude Opus 4.6 in agent scenarios. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for MiMo V2.5 Pro on OffRail starts at $0.43 per million input tokens and $0.87 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
MiMo V2.5 Pro supports a context window of up to 1,000,000 tokens on its largest provider deployment.
MiMo V2.5 Pro is served by Xiaomi through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
MiMo V2.5 Pro supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).
MiMo V2.5 Pro was released on April 23, 2026.