AI EngineerGuide

reasoning effort none returns a 400 on GPT-6 Astra

Returns 400 Applies to gpt-6-astra on the OpenAI Chat Completions and OpenAI Responses API.

OpenAI's docs describe this error but don't quote the exact message, so we don't either.

How to fix it

Use low, the lowest effort GPT-6 Astra supports.

Before
{
  "messages": [
    {
      "content": "Summarize this ticket.",
      "role": "user"
    }
  ],
  "model": "gpt-5.6-sol",
  "reasoning_effort": "none"
}
After (GPT-6 Astra)
{
  "messages": [
    {
      "content": "Summarize this ticket.",
      "role": "user"
    }
  ],
  "model": "gpt-6-astra",
  "reasoning_effort": "low"
}

Official source

Setting reasoning.effort (Responses) or reasoning_effort (Chat Completions) to none returns HTTP 400.

https://developers.openai.com/api/docs/guides/reasoning (last checked 2026-11-02)

Other changes for the same models

All migration errors

FAQ

How do I fix this when moving to gpt-6-astra?

Use low, the lowest effort GPT-6 Astra supports.

Where is this documented?

In OpenAI’s official docs: https://developers.openai.com/api/docs/guides/reasoning, last checked 2026-11-02.