Mara

Models served by Mara

Model	Context	Input /M	Output /M	Cache hit	Latency	Throughput
DeepSeek V3.1 deepseek-ai/DeepSeek-V3.1:mara	128k	$0.63/M	$1.79/M	N/A	1.6s	23 tps
DeepSeek V3.2 deepseek/deepseek-v3.2:mara	33k	$3.15/M	$4.73/M	N/A	1.1s	58 tps
GPT OSS 120B openai/gpt-oss-120b:mara	128k	$0.16/M	$0.79/M	N/A	1.2s	207 tps
MiniMax M2.7 minimax/minimax-m2.7:mara	205k	$0.25/M	$1.01/M	16.6%	6.6s	102 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 Mara via the API

Append :mara to the model ID, set "provider": "mara" in the request body, or send an X-Provider: mara 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": "deepseek-ai/DeepSeek-V3.1:mara",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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