Public AI

Public AI confirmed that it does not store API prompt logs or user data; it records the requested model and request status. Training use and inference-partner coverage remain unconfirmed, so these routes are not classified as Zero Data Retention.

Models served by Public AI

Model name

Model	Context	Input /M	Output /M	TTFT	Throughput
Bielik 11B v3.0 Unverified speakleash/Bielik-11B-v3.0-Instruct:publicai	33k	$0.42/M	$0.42/M	N/A	N/A
Gemma SEA-LION v4 27B Unverified aisingapore/Gemma-SEA-LION-v4-27B-IT:publicai	131k	$0.21/M	$0.42/M	N/A	N/A
Qwen SEA-LION v4 32B Unverified aisingapore/Qwen-SEA-LION-v4-32B-IT:publicai	131k	$0.263/M	$0.525/M	N/A	N/A

Bielik 11B v3.0

Unverified

speakleash/Bielik-11B-v3.0-Instruct:publicai

Context

33k

Input /M

$0.42/M

Output /M

$0.42/M

TTFT

N/A

Throughput

N/A

Gemma SEA-LION v4 27B

Unverified

aisingapore/Gemma-SEA-LION-v4-27B-IT:publicai

Context

131k

Input /M

$0.21/M

Output /M

$0.42/M

TTFT

N/A

Throughput

N/A

Qwen SEA-LION v4 32B

Unverified

aisingapore/Qwen-SEA-LION-v4-32B-IT:publicai

Context

131k

Input /M

$0.263/M

Output /M

$0.525/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 Public AI via the API

Call a model served by Public AI 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": "speakleash/Bielik-11B-v3.0-Instruct:publicai",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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