Groq

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 Groq

Model name

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
GPT OSS 120B openai/gpt-oss-120b:groq	131k	$0.157/M	$0.63/M	$0.0787/M	0.2s	305 tps
GPT OSS 20B openai/gpt-oss-20b:groq	131k	$0.0787/M	$0.315/M	$0.0394/M	0.8s	316 tps
Llama 3.1 8B meta-llama/llama-3.1-8b-instruct:groq	131k	$0.0525/M	$0.084/M	$0.0262/M	0.2s	296 tps
Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct:groq	131k	$0.619/M	$0.829/M	$0.31/M	0.3s	204 tps
MiniMax M2.7 minimax/minimax-m2.7:groq	197k	$0.63/M	$1.89/M	N/A	0.5s	223.5 tps

GPT OSS 120B

openai/gpt-oss-120b:groq

Context

131k

Input /M

$0.157/M

Output /M

$0.63/M

Cache read /M

$0.0787/M

TTFT

0.2s

Throughput

305 tps

GPT OSS 20B

openai/gpt-oss-20b:groq

Context

131k

Input /M

$0.0787/M

Output /M

$0.315/M

Cache read /M

$0.0394/M

TTFT

0.8s

Throughput

316 tps

Llama 3.1 8B

meta-llama/llama-3.1-8b-instruct:groq

Context

131k

Input /M

$0.0525/M

Output /M

$0.084/M

Cache read /M

$0.0262/M

TTFT

0.2s

Throughput

296 tps

Llama 3.3 70B Instruct

meta-llama/llama-3.3-70b-instruct:groq

Context

131k

Input /M

$0.619/M

Output /M

$0.829/M

Cache read /M

$0.31/M

TTFT

0.3s

Throughput

204 tps

MiniMax M2.7

minimax/minimax-m2.7:groq

Context

197k

Input /M

$0.63/M

Output /M

$1.89/M

Cache read /M

N/A

TTFT

0.5s

Throughput

223.5 tps

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 Groq via the API

Call a model served by Groq 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": "openai/gpt-oss-120b:groq",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, 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 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.