Skip to main content
Modern AI models can do more than blurt the first answer that comes to mind. The best ones quietly work through the problem first — drafting, checking, revising — before producing a final reply. That hidden draft is called reasoning (or “extended thinking”, “chain of thought”). Pria gives you a single slider, the Reasoning Effort picker, to control how much of that thinking you want.

​
What “reasoning” means

When a thinking model receives your question, it can spend extra time generating an internal monologue before it starts writing the reply:
  • “Let me re-read the question.”
  • “There are two ways to interpret this — I’ll consider both.”
  • “That step looks wrong, let me redo it.”
You only see the polished final answer, but the reasoning step is what makes the difference between a snappy guess and a carefully argued response. Pria can also surface the live thinking stream so you can watch the model work — useful for transparency, debugging tricky problems, and learning how the model approaches a task.
Not every model supports reasoning. In the model catalog, the Features icon marks the models that do.

​
The 5 effort levels

None

No thinking. The model answers immediately from its first read. Fast and cheap. Good for casual chat, quick lookups, and voice conversations where latency matters.

Low

A brief inner pass — usually a few seconds extra. Catches obvious mistakes without slowing things down much.

Medium

A solid amount of thinking. The model checks its work, considers alternatives, and reorders its plan if needed. A sensible default for most knowledge work.

High

Deep thinking. Several seconds to a minute of internal reasoning. Use for nuanced analysis, complex multi-step problems, and long-form writing where quality matters more than speed.

Max

Maximum effort. The model uses the largest reasoning budget the provider allows. Slow and credit-heavy, but produces the highest-quality output for genuinely hard problems.
Reasoning Effort is set alongside the model, not per message: whoever manages the Twin picks it under Instance Settings → Conversation → Reasoning Effort (with the Conversation Model). Members of a Twin use the level it’s set to; in your personal Pria the level is set by Pria and can’t be changed. The dropdown’s first option is None (Disable thinking); the rest are Low, Medium, High, and Max. Voice conversations have their own setting, Voice Reasoning Effort, because thinking time is silence in a conversation. An assistant can override it for its voice turns with STS / Voice Reasoning Effort; typed answers always use the Twin’s level.
The Instance Settings lightbox on the Conversation tab, showing Conversation Model, Max Tokens, and a Reasoning Effort dropdown set to None (Disable thinking), above moderation and history toggles.

Instance Settings → Conversation: the Reasoning Effort dropdown sits with the Conversation Model and Max Tokens. The default is “None (Disable thinking)”.

​
Per-model differences

Every AI provider handles thinking a little differently. Pria translates the same five levels for each model, so you don’t need to know the details. What you may notice:
  • Models that don’t reason ignore the setting and answer in one pass.
  • Some models can’t switch thinking off completely. With None they think at their lowest level; a few start at Low (for example, GPT-6.1 Sol).
  • Some models decide for themselves how much to think. There, the level steers the depth rather than fixing it.
  • Thinking is paid for even when you don’t see it. The display toggle below only changes what is shown.
Pick the level that matches the depth you want and Pria handles the translation for each model.

​
The thinking display toggle

By default the reasoning trace can appear above each answer in a 💡 lightbulb block. Whether it does is a per-Twin choice, controlled by whoever manages the Digital Twin under Instance Settings → Conversation → Display Details.
The Display Details section of Instance Settings showing Display Tools Details, Display Tool Execution, Display Thinking Details, and Display Thinking Execution toggles, each enabled.

Instance Settings → Conversation → Display Details: the Tools and Thinking toggles, each split into a persisted (Details) and a live (Execution) view.

​
Reading the four toggles

The screenshot shows four switches, because the same two-way split applies to the model’s tool activity as well as its thinking. They form a simple grid: Two questions decide which toggle you want:
  • Tools or Thinking — what are you watching? 🔧 Tools is the model acting — calling retrieval, web search, or an MCP connector. 💡 Thinking is the model reasoning — its internal chain-of-thought.
  • Details or Execution — when do you see it? Details = kept: the block stays above the answer, and it’s still there when you reopen the conversation later. Execution = live only: you watch it happen while the reply is being written, and then it’s gone. What is kept always follows the matching Details toggle — so you can watch the live trace without keeping it, or keep the saved block without the live view.
When thinking display is on, the next reply renders a collapsible 💡 block above the final answer — expand it to read the model’s work, or leave it folded. Because these are per-Twin settings, an administrator can keep thinking visible on a research twin and hidden on a customer-facing one.

​
Reading thinking blocks during a stream

While a reasoning model is thinking, you’ll see:
  • A growing “thinking” panel above the reply area, streaming in real time.
  • A spinner / waveform indicating the model is still planning.
  • The final answer appears below once thinking finishes and the model begins composing the reply.
The thinking block is collapsible after the answer arrives — click the header to fold or unfold it. Long thinking sessions are scrollable inside the panel, so they don’t push the answer off-screen.
Thinking content is informative, not authoritative. The final answer is what the model wants to commit to. Treat the thinking block as “showing the work”, not as a second answer to react to.

​
Cost & speed tradeoffs

Numbers are rough — they vary by model, question complexity, and provider. Watch the credit indicator on each reply to see the real cost.

​
When to use Max

Reach for Max when the answer’s quality matters more than time or cost:
  • Deep research questions that require synthesizing many sources.
  • Long, multi-step plans you’ll act on (project plans, architecture proposals).
  • Nuanced analysis where small mistakes have big downstream cost.
  • Hard puzzles, derivations, proofs, or ambiguous specifications.
  • Final-draft writing on important material.
You’ll usually pair Max with a frontier model (Claude Opus, GPT-5, Gemini 3 Pro, Grok 4) and a Knowledge Mode that gives the model rich context.

​
When to use None or Low

Drop to None or Low when speed and economy matter:
  • Voice mode (long thinking pauses break the conversation’s natural rhythm).
  • Quick factual lookups (“what’s the capital of…”).
  • Casual chitchat, small talk, formatting tweaks to existing text.
  • Bulk drafting where you’ll edit afterwards anyway.
  • Repetitive workflows where the answer is well within the model’s first-pass capability.
Setting effort to None on a reasoning-required problem doesn’t break the model — it just produces a shallower, more error-prone answer. If a reply looks wrong, bump the slider and re-ask.