Updated

Two pale moonstone crescents interlocking at an angle on a dark background, abstract hero artwork for GPT-6 Luna Pro

OpenAI

GPT-6 Luna Pro

GPT-6 Luna in OpenAI's pro reasoning mode, giving the efficient GPT-6 model more work per request.

Chat with GPT-6 Luna Pro in Super AgentView pricing

What is GPT-6 Luna Pro?

GPT-6 Luna Pro runs OpenAI's most efficient GPT-6 model with pro reasoning mode switched on.

OpenAI describes pro as a reasoning mode on the same model ID, for difficult tasks that need more model work and can tolerate higher latency and token usage. On Luna, that means slower and more thorough answers from the lowest-cost GPT-6 tier. OpenAI hasn't published pro-mode benchmarks for Luna. You'll find it directly under GPT-6 Luna in Super Agent, with the same effort range from off to max.

Provider
OpenAI
Context window
1.05M tokens
Input
Text, Image
Reasoning
Off to max
Max output
128K tokens
Knowledge cutoff
May 18, 2026

How GPT-6 Luna Pro performs

On LMArena

People compare two anonymous answers and vote for the better one. Ranked here against the other chat models you can pick in Super Agent.

LMArena has no separate entry for GPT-6 Luna Pro. It runs the same model as GPT-6 Luna in a deeper reasoning mode, and that page shows the base model's arena results.

Source: LMArena, leaderboard published . Scores move as new votes come in.

What you can do with GPT-6 Luna Pro

  • GPT-6 Luna with OpenAI's pro reasoning mode

  • More model work per request than standard Luna

  • Same 1.05M-token context window and image input

  • Effort still runs from off to max

How to prompt GPT-6 Luna Pro

  • Send the full problem in one message; each answer takes a while.
  • Bring it in when standard Luna gives a shaky answer, and keep everyday chat on Luna.
  • Ask it to explain its reasoning when you need to trust the result.

Where GPT-6 Luna Pro fits best

  • Hard questions where you still want the Luna tier

  • Double-checking a plan Luna produced

  • Logic puzzles in scripts or story structure

  • Careful answers that can wait

How GPT-6 Luna Pro compares

GPT-6 Luna Pro compared with other chat models on Flashloop
ModelLMArena textLMArena codingContext windowReasoning
GPT-6 Luna ProNoNo1.05M tokensOff to max
GPT-6.1 Sol1480#271537#141.05M tokensLow to max
GPT-6.1 Sol ProNoNo1.05M tokensLow to max
Claude Sonnet 5.51478#291528#261M tokensLow to max
GPT-6 Luna1442#911507#651.05M tokensOff to max

Good to know before you start

  • Answers take longer than on GPT-6 Luna
  • Uses more tokens than standard Luna on the same request
  • For everyday chat, standard GPT-6 Luna is the better fit

Start chatting with GPT-6 Luna Pro

Chat with GPT-6 Luna Pro in Super Agent

  1. Select GPT-6 Luna Pro

    Open Super Agent on Flashloop and choose GPT-6 Luna Pro in the model picker.

  2. Enter your prompt

    Ask for what you need: an answer, a plan, or the images and videos you want the agent to make.

  3. Send and keep going

    Send the message. GPT-6 Luna Pro answers in Super Agent and runs any generations you asked for.

Questions about GPT-6 Luna Pro

Is GPT-6 Luna Pro a separate model?

No. It is GPT-6 Luna served with OpenAI's reasoning mode set to pro, which makes it do more work on each request.

When is GPT-6 Luna Pro worth using?

When a question is hard enough that standard Luna gets it wrong and you can wait longer for the answer. OpenAI keeps standard mode as the default and offers pro for difficult tasks.

Does GPT-6 Luna Pro support turning reasoning off?

Yes. In Super Agent it supports off, low, medium, high, extra high and max, and starts at low.

How is GPT-6 Luna Pro different from GPT-6 Sol Pro?

Both use pro reasoning mode, but on different base models. Luna is OpenAI's efficient, low-cost tier, and Sol is the higher-end tier above it.

More chat models on Flashloop

Browse all models