Reasoning

Reasoning refers to model behaviors that spend extra budget on problem solving and may expose that work through typed output. The exact request controls and visible output depend on the public API and model.

Support Matrix

API	Request controls	Visible output	Notes
`Responses`	`reasoning.effort`	`reasoning` items in `output[]` and reasoning stream events	Best starting point for new work
`Chat Completions`	`reasoning_effort` on supported models	assistant message fields such as `reasoning_details` or `reasoning_content`	Use for OpenAI chat compatibility
`Messages`	`thinking` and `output_config.effort`	Anthropic thinking blocks and thinking events	Use for Anthropic compatibility

Reasoning Effort

When reasoning effort is supported, the normalized values used in the docs are:

none
minimal
low
medium
high
xhigh

Higher effort usually increases latency and cost. Start low, then raise it only when the extra quality is worth it.

In Messages, output_config is a reasoning control, not a generic structured-output feature.

When To Use It

hard planning or decomposition tasks
agent workflows that need stronger tool selection and longer deliberation
tasks where quality matters more than minimal latency

Recommended Example

from openai import OpenAI

client = OpenAI(
    base_url="https://api.naga.ac/v1",
    api_key="YOUR_API_KEY",
)

response = client.responses.create(
    model="gpt-5",
    input="Explain the likely root cause of a slow PostgreSQL query and suggest the first two checks.",
    reasoning={"effort": "medium"},
)

print(response.output)

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.naga.ac/v1',
  apiKey: 'YOUR_API_KEY',
});

const response = await client.responses.create({
  model: 'gpt-5',
  input: 'Explain the likely root cause of a slow PostgreSQL query and suggest the first two checks.',
  reasoning: { effort: 'medium' },
});

console.log(response.output);

curl https://api.naga.ac/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5",
    "input": "Explain the likely root cause of a slow PostgreSQL query and suggest the first two checks.",
    "reasoning": {
      "effort": "medium"
    }
  }'

On Responses, visible reasoning can arrive as reasoning items before or alongside message items. On Chat Completions and Messages, it appears in protocol-specific fields and blocks instead.

Preserving Reasoning Across Turns

If a model pauses for tool use and you continue the conversation in another request, preserve any reasoning payload from that assistant turn unchanged.

Responses: replay the prior reasoning item unchanged in the next input[] turn if you want to preserve reasoning continuity
Chat Completions: if an assistant turn includes reasoning_details, send those details back unchanged with that assistant message when you append the later role: tool result
Messages: if an assistant turn includes thinking blocks, replay those blocks unchanged, including any signature, before the later tool_result block

Changing or dropping encrypted reasoning/signature data can break reasoning continuity across turns.

Get Started

Build

API Guides

Account

Product

Support Matrix

Reasoning Effort

When To Use It

Recommended Example

Preserving Reasoning Across Turns

​Support Matrix

​Reasoning Effort

​When To Use It

​Recommended Example

​Preserving Reasoning Across Turns

​Related Docs

Support Matrix

Reasoning Effort

When To Use It

Recommended Example

Preserving Reasoning Across Turns

Related Docs