EvaEsi Reasoning Deep

Overview

Reasoning Deep is Reasoning given more room: a wider sweep of sources, a longer chain of work, and the largest output allowance in the family. It is the most expensive way to ask a question on the platform and it should feel like it. Reach for it when the answer is going into a decision, a filing, or a document someone will rely on.

How it behaves

The widest sweep and the longest chain of work.

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

• Long-form research and written analysis
• Questions where a shallow answer is worse than no answer
• Work that will be reviewed, cited or acted on

Reach for something else when

• Use reasoning when standard depth already answers the question.
• Use reasoning.fast when you need an answer inside an interactive wait.

Others in the Reasoning family

• EvaEsi Reasoning: Deeper synthesis for questions that need working through.
• EvaEsi Reasoning Verify: Checks claims against evidence and reports what it could not support.
• EvaEsi Reasoning Fast: Reasoning held to an interactive latency budget.

Example

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