Lucidity

Lucidity directly confirmed zero data retention for Synth API requests made through NanoGPT: prompts and outputs are not retained or used for training.

Models served by Lucidity

Model name

Model	Context	Input /M	Output /M	TTFT	Throughput
Synth 2.5 Flash Preview ZDR synth-2.5-flash:lucidity	30k	$0.0315/M	$0.105/M	N/A	N/A
Synth 2.5 Pro Preview ZDR synth-2.5-pro:lucidity	30k	$0.105/M	$0.21/M	N/A	N/A

Synth 2.5 Flash Preview

ZDR

synth-2.5-flash:lucidity

Context

30k

Input /M

$0.0315/M

Output /M

$0.105/M

TTFT

N/A

Throughput

N/A

Synth 2.5 Pro Preview

ZDR

synth-2.5-pro:lucidity

Context

30k

Input /M

$0.105/M

Output /M

$0.21/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 Lucidity via the API

Call a model served by Lucidity 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": "synth-2.5-flash:lucidity",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, append :lucidity to the model ID, set "provider": "lucidity" in the request body, or send an X-Provider: lucidity 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.