MiniMax

Models served by MiniMax

Model	Context	Input /M	Output /M	Cache read /M	Latency	Throughput
MiniMax M2.1 FP8 minimax/minimax-m2.1:minimax	200k	$0.31/M	$2.52/M	$0.03/M	1.7s	10 tps
MiniMax M2.5 FP8 minimax/minimax-m2.5:minimax	205k	$0.63/M	$2.52/M	$0.06/M	1.2s	52 tps
MiniMax M2.7 FP8 minimax/minimax-m2.7:minimax	205k	$0.31/M	$1.26/M	Supported	1.2s	44 tps
MiniMax M2.7 Turbo FP8 minimax/minimax-m2.7-turbo:minimax	205k	$0.63/M	$2.52/M	$0.06/M	1.2s	44 tps
MiniMax M3 FP8 minimax/minimax-m3:minimax	512k	$0.31/M	$1.26/M	$0.06/M	1s	78 tps
MiniMax M3 Thinking FP8 minimax/minimax-m3:thinking:minimax	512k	$0.31/M	$1.26/M	$0.06/M	1s	78 tps

Prices are per million tokens and include the 5% provider-selection markup. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using MiniMax via the API

Append :minimax to the model ID, set "provider": "minimax" in the request body, or send an X-Provider: minimax header. Explicit provider selection adds a 5% markup over that provider's base price; the prices in the table above already include it.

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/minimax-m2.1:minimax",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

See the API documentation for provider preferences, price-aware routing, and error behavior.