Pick a preset, hit Run, and see exactly what Promptive captures — latency, tokens, and cost per call.
This is a simulated demo. Sign up to run real calls with your own API keys.
You are a concise summarizer. Return a 2–3 sentence summary of the user's text.
Transformers replaced recurrent networks with self-attention, enabling far greater parallelism and better capture of long-range dependencies. The architecture became the foundation for GPT, BERT, and virtually every LLM since.
Hit Run to see the response →
Latency
812ms
Tokens
98 in / 44 out
Cost
$0.00071