Prima Era

Prima Era S.R.L. (Italy) serves GLM-5.3 and Kimi K3 on Nebius data centres in the US, UK and France. Under its DPA with NanoGPT, prompts and outputs are processed only in volatile memory, never written to disk or used for training, and requests are not forwarded to other providers. An in-memory prefix cache is tied to NanoGPT's key. Request metadata is kept for 90 days and daily usage totals for accounting.

Models served by Prima Era

Model name

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
Kimi K3 FP4 ZDR moonshotai/kimi-k3:primaera	1.0M	$0.787/M	$8.40/M	$0.105/M	N/A	N/A

Kimi K3

FP4

ZDR

moonshotai/kimi-k3:primaera

Context

1.0M

Input /M

$0.787/M

Output /M

$8.40/M

Cache read /M

$0.105/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 Prima Era via the API

Call a model served by Prima Era 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": "moonshotai/kimi-k3:primaera",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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