400+ tok/s
3-4x faster than typical cloud inference. Less waiting, more coding.
€0.30 / €1.20
Per 1M tokens (input/output). Run thousands of agentic tasks for euros, not hundreds.
EU Sovereign
Data processed in Germany. Zero data retention — no training on your data.
Scale Without Surprises
Transparent pay-as-you-go pricing. Know exactly what you'll pay before you start.
Don't Take Our Word For It
MiniMax-M2.5 ranks among the top models on SWE-bench Verified — at a fraction of the cost
"MiniMax M2.5 is the first open-weight model to surpass Claude Sonnet on SWE-bench."
— OpenHands Blog
Works With Your Favorite Tools
Drop-in replacement via OpenAI-compatible API. Switch in minutes.
These tools are developed by their respective creators. Infercom is not affiliated with or endorsed by these projects.
See It In Action
Real agentic coding with MiniMax-M2.5 on EU infrastructure
OpenCode with MiniMax-M2.5 on Infercom — reasoning, tool calling, and file operations at 400+ tokens/secClick to enlarge
Developers Are Switching
"M2.5 gave me the best result I've gotten so far. Better than Claude Code with Opus 4.6.""A typical SWE-Bench task costs about $0.15 with M2.5 versus $3.00 with Opus."
"I went from Claude Max ($100/month) to MiniMax ($20/month) with the same usage patterns and haven't hit limits once.""The latency improvement is noticeable... those milliseconds add up over hundreds of interactions daily."
"There is a model that I can impartially say is basically up to the quality of Claude Sonnet.""At a price point approximately 13x cheaper than Opus, it could open up a new set of use cases."
"Full analysis of 5 benchmarks and cost comparison""MiniMax M2.5 vs Claude Opus: 60x Price Difference"
Your code, your prompts, your data — processed entirely on EU infrastructure. No US CLOUD Act exposure.