MiniMax M2.7

minimax/minimax-m2.7

text in · text out · 204,800 context · 204,800 max output

toolsschemareasoningcacheno-train
Effective cost per 1k requests

cost = p_in·(input − cached) + p_cache_read·cached + p_out·output + p_req; cached tokens are the prefix a sticky endpoint already holds (part2b §9.3), which is why the cheapest list price is not always the cheapest request.

ProviderRegion · quantContext / max outInput / MOutput / MCache read / writeMarkupPer 1k reqUptime 30 dTTFT p50 / p95ThroughputLast 24 hFidelityDataCapabilitiesStatus
MiniMaxus · none204,800 / 204,800$0.300$1.200$0.060 / $0.375pass-through$0.960———no traffic— 365 dmodel defaultactive
OpenRouterglobal · unknown196,608 / 176,947$0.221$0.882$0.044 / —+5.0%$0.706———no traffic— no-train 30 d15 differactive

Quick start

curl https://api.ai.ml/v1/chat/completions \
  -H "Authorization: Bearer $AIML_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"minimax/minimax-m2.7","messages":[{"role":"user","content":"Say hello"}]}'
Get a key in the console

Changelog

  • new_model endpoint ep_openrouter_minimax-m2.7_global (minimax/minimax-m2.7) added as active; price input 0.221 output 0.882 USD/M 10/5/2026