jishie

MiniMax-M2.5

nebius/MiniMaxAI/MiniMax-M2.5 · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.52Blended $/1M (3:1)
$0.3Input $/1M
$1.2Output $/1M
$1.501M in + 1M out
$0.03 −90%Cache read $/1M
#2257 of 5,000Cheapest rank
Provider
Nebius Token Factory (nebius)
Context
196,608 tokens
Max output
8,192 tokens
Capabilities
toolsreasoningtext

Same model, other providers

“MiniMax-M2.5” is offered by 9 providers — cheapest-effective first. Alibaba Coding Plan (China) is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Alibaba Coding Plan (China)freefree$0.00197k
Alibaba Coding Planfreefree$0.00197k
Alibaba Token Planfreefree$0.00197k
Tencent Coding Plan (China)freefree$0.00205k
MiniMax Token Plan (minimax.io)freefree$0.00205k
Alibaba Token Plan (China)freefree$0.00197k
MiniMax Token Plan (minimaxi.com)freefree$0.00205k
CrofAI$0.11$0.95$0.32205k
Nebius Token Factory (this)$0.3$1.2$0.52197k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Nebius Token Factory and pass this model id:

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

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