Sovereign inference — MiniMax M2.5
Your sovereign, private MiniMax M2.5
A reasoning model in the large tier, served on ToothFairyAI's AU, EU and US endpoints — private by default, billed in Units of Intelligence at the published rates below. No training on your data, no vendor lock-in.
AU · EU · US resident0.84 UoI/1M input2.10 UoI/1M output1000K context
How MiniMax M2.5 compares
Independent intelligence index for MiniMax M2.5 against every peer in the Large tier (and the tier above where needed) — same source, same tests.
Latency — end-to-end seconds for a 500-token answer
Run MiniMax M2.5 privately
One key, one endpoint, three jurisdictions.
- Size tierLarge
- Input rate0.84 UoI/1M
- Output rate2.10 UoI/1M
- Cached input rate—
- Context window1000K tokens
- Max output33K tokens
- ReasoningYes — emits thinking traces
- Vision & video inputText only
- Tool callingSupported
- Data residencyAU, EU and US endpoints — processing stays inside the region you call