ModelRun

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 ModelRun

Model	Context	Input /M	Output /M	Cache read /M	Latency	Throughput
Gemma 4 31B FP4 google/gemma-4-31b-it:modelrun	262k	$0.79/M	$1.05/M	$0.79/M	0.2s	90 tps
Gemma 4 31B (Thinking) FP4 google/gemma-4-31b-it:thinking:modelrun	262k	$0.79/M	$1.05/M	$0.79/M	0.2s	90 tps
Kimi K2.7 Code FP4 moonshotai/kimi-k2.7-code:modelrun	262k	$0.89/M	$3.94/M	$0.17/M	0.4s	140 tps
MiniMax M3 FP4 minimax/minimax-m3:modelrun	1.0M	$0.79/M	$3.15/M	$0.16/M	0.3s	75 tps
MiniMax M3 Thinking FP4 minimax/minimax-m3:thinking:modelrun	1.0M	$0.79/M	$3.15/M	$0.16/M	0.3s	75 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 ModelRun via the API

For models with provider selection, append :modelrun to the model ID, set "provider": "modelrun" in the request body, or send an X-Provider: modelrun 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": "google/gemma-4-31b-it:modelrun",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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