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 name

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
MiniMax M2-her minimax/minimax-m2-her	66k	$0.302/M	$1.21/M	N/A	N/A	N/A
MiniMax M2.1 minimax/minimax-m2.1:minimax	205k	$0.315/M	$1.26/M	$0.0315/M	1.6s	41 tps
MiniMax M2.7 minimax/minimax-m2.7:minimax	205k	$0.315/M	$1.26/M	Supported	0.7s	36 tps
MiniMax M2.7 Turbo minimax/minimax-m2.7-turbo:minimax	205k	$0.63/M	$2.52/M	$0.063/M	1s	46 tps
MiniMax M3 minimax/minimax-m3:minimax	512k	$0.315/M	$1.26/M	$0.063/M	1.5s	90 tps
MiniMax M3 Thinking minimax/minimax-m3:thinking:minimax	512k	$0.315/M	$1.26/M	$0.063/M	1.5s	90 tps
MiniMax M3.1 Flash minimax/minimax-m3.1-flash:minimax	1M	$0.157/M	$0.63/M	$0.0158/M	N/A	N/A

MiniMax M2-her

minimax/minimax-m2-her

Context

66k

Input /M

$0.302/M

Output /M

$1.21/M

Cache read /M

N/A

TTFT

N/A

Throughput

N/A

MiniMax M2.1

minimax/minimax-m2.1:minimax

Context

205k

Input /M

$0.315/M

Output /M

$1.26/M

Cache read /M

$0.0315/M

TTFT

1.6s

Throughput

41 tps

MiniMax M2.7

minimax/minimax-m2.7:minimax

Context

205k

Input /M

$0.315/M

Output /M

$1.26/M

Cache read /M

Supported

TTFT

0.7s

Throughput

36 tps

MiniMax M2.7 Turbo

minimax/minimax-m2.7-turbo:minimax

Context

205k

Input /M

$0.63/M

Output /M

$2.52/M

Cache read /M

$0.063/M

TTFT

1s

Throughput

46 tps

MiniMax M3

minimax/minimax-m3:minimax

Context

512k

Input /M

$0.315/M

Output /M

$1.26/M

Cache read /M

$0.063/M

TTFT

1.5s

Throughput

90 tps

MiniMax M3 Thinking

minimax/minimax-m3:thinking:minimax

Context

512k

Input /M

$0.315/M

Output /M

$1.26/M

Cache read /M

$0.063/M

TTFT

1.5s

Throughput

90 tps

MiniMax M3.1 Flash

minimax/minimax-m3.1-flash:minimax

Context

1M

Input /M

$0.157/M

Output /M

$0.63/M

Cache read /M

$0.0158/M

TTFT

N/A

Throughput

N/A

Prices are per million tokens. TTFT is the observed time to first token. 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

Call a model served by MiniMax using its displayed model ID, including the provider suffix when selection is supported.

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"}]
  }'

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.

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