Model Terminal
MiMo-V2.5
Xiaomi MiMo-V2.5 is an omnimodal foundation model that understands and reasons over text, images, video, and audio in a single system with a 1M-token context window. It is designed for agentic applications including browsing, tool use, and multi-step reasoning tasks. Source: supabase.
Value score
Not scored
Context
—
tokens
Max output
—
tokens
Price
—
Capability radar
Peer value bars
Identity
- Developer
- xiaomi
- Openness
- —
- Modalities
- —
- Release
- —
- Knowledge cutoff
- —
- Deprecation
- —
- API docs
- —
Benchmarks
No benchmark scores yet.
Compare nearby
Pricing
- Input / 1M
- —
- Output / 1M
- —
- Speed
- —
