Groq

Models served by Groq

Model	Context	Input /M	Output /M	Cache read /M	Latency	Throughput
GPT OSS 120B openai/gpt-oss-120b:groq	128k	$0.16/M	$0.63/M	$0.08/M	0.2s	293 tps
GPT OSS 20B openai/gpt-oss-20b:groq	128k	$0.08/M	$0.31/M	$0.04/M	0.4s	337 tps
Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct:groq	131k	$0.62/M	$0.83/M	$0.31/M	0.2s	71 tps
MiniMax M2.7 minimax/minimax-m2.7:groq	205k	$0.63/M	$1.89/M	N/A	0.3s	252.5 tps
Qwen3 32B qwen/qwen3-32b:groq	41k	$0.30/M	$0.62/M	$0.15/M	0.3s	270 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 Groq via the API

Append :groq to the model ID, set "provider": "groq" in the request body, or send an X-Provider: groq 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": "openai/gpt-oss-120b:groq",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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