Xiaomi models on Felo
Compare the Xiaomi models currently available through Felo, including model IDs, pricing, context windows, and Quick Start examples.
2
models
1.05M
max context
1
protocols
Flagships first
ModelContextPricing
MiMo V2.6 Pro
Xiaomimimo-v2.6-proXiaomi's flagship foundation model, built at a scale of over 1T parameters to push the ceiling of capability on the most demanding tasks. It accepts text, image, audio, and video input with a 1M-token context window.
Multimodal reasoningAgentic tasksLong-context analysisVideo understanding
Context
1M
Max output
128K
Input tokens
$0.43 /M
Output tokens
$0.87 /M
MiMo V2.5 Pro
Xiaomimimo-v2.5-proXiaomi's flagship text route, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro.
Software engineeringLong-horizon agentsReasoningCost-sensitive workloads
Context
1.05M
Max output
128K
Input tokens
$0.43 /M
Output tokens
$0.87 /M