jishie

MiniMax-M2.5-highspeed

minimax-cn-coding-plan/MiniMax-M2.5-highspeed · family minimax · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

freeBlended $/1M (3:1)
freeInput $/1M
freeOutput $/1M
free1M in + 1M out
freeCache read $/1M
#486 of 5,000Cheapest rank
Provider
MiniMax Token Plan (minimaxi.com) (minimax-cn-coding-plan)
Context
204,800 tokens
Max output
131,072 tokens
Capabilities
toolsreasoningtext

Same model, other providers

“MiniMax-M2.5-highspeed” is offered by 6 providers — cheapest-effective first. This one (MiniMax Token Plan (minimaxi.com)) is the cheapest.

ProviderInputOutputBlendedContext
MiniMax Token Plan (minimaxi.com) (this)freefree$0.00205k
MiniMax Token Plan (minimax.io)freefree$0.00205k
LLM Gateway$0.6$2.4$1.05205k
OrcaRouter$0.6$2.4$1.05205k
MiniMax (minimax.io)$0.6$2.4$1.05205k
MiniMax (minimaxi.com)$0.6$2.4$1.05205k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at MiniMax Token Plan (minimaxi.com) and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"MiniMax-M2.5-highspeed","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):