← Back to model catalog
MiniMax
MiniMax M2.5
minimax-m2.5
Guru+coding
MiniMax M2.5 is a coding model in the Majestix lineup built for coding, agentic, tool use workloads, with 128K context and $0.32 / $1.00 per 1M tokens.
Context Window
128K
Max Output
32K
Pricing
$0.32 input / $1.00 output per 1M tokens
What this model is good at
CodingAgenticTool UseReasoning
Benchmarks and operating signals
| Signal | Value | Note |
|---|---|---|
| Context Window | 128K | platform limit |
| Max Output | 32K | platform limit |
| Output Price | $1.00 / 1M | Majestix pricing |
Quick guidance
Use MiniMax M2.5 when your workload lines up with coding and agentic and you want a clear price-to-capability tradeoff inside Majestix.
This card intentionally focuses on platform context: pricing, limits, and where the model already appears in swarm templates. It is not a self-hosting guide or a vendor deployment manual.
If you want the narrative version, the paired blog intro is the fastest way to explain this model to customers, internal operators, or community readers.