Pokee

Pokee says developer API prompts and outputs are not used for training. Its infrastructure provider retains an approximately 120-character preview of each message for 1 day and encrypted raw request payloads for up to 7 days.

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 Pokee

Model name

Model	Context	Input /M	Output /M	TTFT	Throughput
Pokee-Isaac 28B pokee-isaac:pokee	10M	$0.16/M	$1.05/M	N/A	N/A

Pokee-Isaac 28B

pokee-isaac:pokee

Context

10M

Input /M

$0.16/M

Output /M

$1.05/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 Pokee via the API

Call a model served by Pokee 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": "pokee-isaac:pokee",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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