EvaEsi Reasoning Fast

Overview

Reasoning Fast keeps the evidence-first pipeline but caps how long it may spend, so it returns inside a wait a person will tolerate. It is the most expensive model in the Reasoning family per rung, for the same reason Instant Fast costs more than Instant: reserving capacity to answer promptly costs more than using capacity whenever it is free.

How it behaves

Reasoning inside an interactive wait.

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

• Interactive analysis where the user is waiting
• Chat surfaces that need reasoning without a long pause
• Live triage and routing decisions

Reach for something else when

• Use reasoning when the request can run in the background.
• Use instant.fast when the question does not need reasoning at all.

Others in the Reasoning family

• EvaEsi Reasoning: Deeper synthesis for questions that need working through.
• EvaEsi Reasoning Deep: A longer deliberation budget and a wider evidence sweep.
• EvaEsi Reasoning Verify: Checks claims against evidence and reports what it could not support.

Example

curl https://evaesi.dev/api/v1/responses \
  -H "Authorization: Bearer esi_dev_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "reasoning.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.