MiniMax

Data handling can vary by model and deployment. The privacy badge above shows the more conservative of the provider-wide fallback and the policies for routes on this page; each model page shows the policy for that specific route.

Models served by MiniMax

Model	Context	Input /M	Output /M	Cache read /M	Latency	Throughput
MiniMax M2-her minimax/minimax-m2-her	66k	$0.30/M	$1.21/M	$0.15/M	N/A	N/A
MiniMax M2.1 FP8 minimax/minimax-m2.1:minimax	200k	$0.31/M	$2.52/M	$0.03/M	1.6s	55 tps
MiniMax M2.5 FP8 minimax/minimax-m2.5:minimax	205k	$0.63/M	$2.52/M	$0.06/M	1.2s	51.5 tps
MiniMax M2.7 FP8 minimax/minimax-m2.7:minimax	205k	$0.31/M	$1.26/M	Supported	1.2s	55 tps
MiniMax M2.7 Turbo FP8 minimax/minimax-m2.7-turbo:minimax	205k	$0.63/M	$2.52/M	$0.06/M	1.2s	55 tps
MiniMax M3 FP8 minimax/minimax-m3:minimax	512k	$0.31/M	$1.26/M	$0.06/M	0.7s	89 tps
MiniMax M3 Thinking FP8 minimax/minimax-m3:thinking:minimax	512k	$0.31/M	$1.26/M	$0.06/M	0.7s	89 tps

Prices are per million tokens. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using MiniMax via the API

For models with provider selection, 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 route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.

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-her",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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