EvaEsi Instant Fast

Overview

Instant Fast answers the same questions as Instant with a shorter evidence sweep and a tighter output ceiling. It costs more per rung, not less, and that is the correct way round: what you are buying is a shorter wait, and low latency at scale is the expensive thing to supply. Use it where a person is watching a cursor blink.

How it behaves

The lowest latency on the platform.

Speed and depth trade against each other across a family. The faster versions cost more per rung, not less: what is being bought is a shorter wait, and reserving capacity to answer promptly costs more than using it whenever it is free.

Choosing this model

Reach for it when

• Autocomplete, inline suggestions and typeahead
• High-volume classification where each call must return quickly
• Interactive surfaces with a visible latency budget

Reach for something else when

• Use instant when nobody is waiting on the response in real time.
• Use reasoning when the answer matters more than the wait.

Others in the Instant family

• EvaEsi Instant: Fast general chat with live evidence. The platform default.

Example

curl https://evaesi.dev/api/v1/responses \
  -H "Authorization: Bearer esi_dev_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "instant.fast",
    "prompt": "Explain what this service does."
  }'

Pricing

Published rates for this model, read live from the platform. API usage is billed at these rates; subscription plans draw from a monthly allowance instead, shown below.

Limits

Plan terms

Subscription plans include a monthly rung allowance on each model, and apply a multiplier when drawing that allowance down. API usage is billed at the rates above and is not drawn from a plan allowance.