MiniMax Models
haimaker.ai provides API access to all 9 MiniMax models, with context windows up to 1M tokens, priced from $0.15 to $0.60 per 1M input tokens. Access each model through its haimaker.ai API endpoint.
Models
9
Max context
1M
From
$0.15
/1M input
Modes
Chat
Minimax M3.1 Flash
MiniMax
minimax/minimax-m3.1-flash
Chat1M ctxIn: $0.15/1MOut: $0.60/1MCached in: $0.015/1M
function callingvisionreasoning
Minimax M3
MiniMax
minimax/minimax-m3
Chat1M ctxIn: $0.30/1MOut: $1.20/1MCached in: $0.060/1MPromo rate
function callingvisionreasoning
Minimax M2.7 Highspeed
MiniMax
minimax/minimax-m2.7-highspeed
Chat1M ctxIn: $0.60/1MOut: $2.40/1MCached in: $0.060/1MCache write: $0.38/1M
function callingreasoning
Minimax M2.7
MiniMax
minimax/minimax-m2.7
Chat1M ctxIn: $0.30/1MOut: $1.20/1MCached in: $0.060/1MCache write: $0.38/1M
function callingreasoning
Minimax M2.5 Lightning
MiniMax
minimax/minimax-m2.5-lightning
Chat1M ctxIn: $0.30/1MOut: $2.40/1MCached in: $0.030/1MCache write: $0.38/1M
function callingreasoning
Minimax M2.5
MiniMax
minimax/minimax-m2.5
Chat197K ctxIn: $0.30/1MOut: $1.20/1MCached in: $0.30/1MCache write: $0.30/1M
function callingreasoning
Minimax M2.1 Lightning
MiniMax
minimax/minimax-m2.1-lightning
Chat1M ctxIn: $0.30/1MOut: $2.40/1MCached in: $0.030/1MCache write: $0.38/1M
function callingreasoning
Minimax M2.1
MiniMax
minimax/minimax-m2.1
Chat1M ctxIn: $0.30/1MOut: $1.20/1MCached in: $0.030/1MCache write: $0.38/1M
function callingreasoning
Minimax M2
MiniMax
minimax/minimax-m2
Chat200K ctxIn: $0.30/1MOut: $1.20/1MCached in: $0.030/1MCache write: $0.38/1M
function callingreasoning