nemotron-3.5-lightning pricing

Nvidia's nemotron-3.5-lightning is served through HowToFix's OpenAI-compatible gateway, billed per token against a prepaid balance.

Price

Input	$0.05 per 1M tokens
Output	$0.2 per 1M tokens
Cached input	$0.01 per 1M tokens

Rates are the ones the gateway bills against, read from the same table the live board renders. A request is charged on completion, using the tokens the upstream returned rather than an estimate.

What it is

NVIDIA Nemotron 3.5 Lightning, a fast model in the Nemotron 3.5 family.

Endpoints

Reachable through: openai.

Call it

curl https://api.howtofix.id/v1/chat/completions \
  -H "Authorization: Bearer sk-YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"nemotron-3.5-lightning","messages":[{"role":"user","content":"hello"}]}'

One key reaches every model on the board. Create an account, or read the API handbook first.