Skip to content

GPT · Writing

GPT-6 for writing

llmwise has 4 of OpenAI's GPT models, from GPT-6 Luna (up to 60 messages a day on Pro) to GPT-6 Astra (up to 31 messages a month). We ran the same writing prompts on every one and published every reply: which GPT model to use, from the results, what each costs per message, and how to get more out of it.

Based on 20 of our test runs on , through OpenRouter with the app's own prompt and settings. Updated .

Short answer

In our test runs on September 29, 2026, 2 models passed 5 of 5 writing prompts, so these prompts don't pick one for hard problems. For value, GPT-6.1 Sol (4 of 5), 125 a month on Pro; for everyday writing, GPT-6 Luna (5 of 5), from the daily count.

Our picks for writing

  • Hard problems

    Shared by 2 models

    2 models passed 5 of 5, both hard ones: GPT-6 Astra and GPT-6 Luna. These prompts don't tell them apart, so they share the pick.

  • Best value

    GPT-6.1 Sol

    Passed 4 of 5 writing prompts, with 125 a month on Pro.

  • Everyday

    GPT-6 Luna

    Passed 5 of 5 writing prompts; an everyday model, so its messages come from the daily count (60 a day on Pro), not the monthly allowance.

These picks aren't our opinion: they're what the results below give, by these rules, among the GPT models in llmwise. They change when the results do.

  • Hard problems: the model that passed the most prompts and, of those, the most hard ones. Models level on both share the pick: the prompts don't tell them apart, so we don't break the tie by price or by name.
  • Best value: among the models that draw on the monthly allowance, the one with the most messages on Pro that passed no more than one prompt fewer than the top model. Ties go to the one that passed more, then to the lower cost per reply.
  • Everyday: among the cheapest models on the page (the everyday models, which come from the daily count, when the page has any), the one that passed the most. Ties go to the one that passed more of the hard prompts, then to the lower cost per reply.

Our writing test runs, model by model

How each model did on our 5 writing prompts, what each reply counted as on Pro, and what it cost to run.

Our writing test runs
ModelPassedHard onesMessages used on ProCost per replyTime per reply
GPT-6 AstraOpenAI5 of 52 of 21 each, of 31 a month on Pro$0.01114.9 s
GPT-6.1 SolOpenAI4 of 52 of 21 each, of 125 a month on Pro$0.00113.2 s
GPT-6 SolOpenAI4 of 52 of 21 each, of 125 a month on Pro$0.00233.1 s
GPT-6 LunaOpenAI5 of 52 of 21 each, of 60 a day on Pro$0.00012.1 s
Passed: out of the job's 5 prompts, how many replies passed their check (a reply the provider failed to give isn't counted). Messages used: what each reply counted as on Pro, and Pro's count on the model. Cost: what OpenRouter charged us per reply, on average; in llmwise you pay per message, not per token. Time: from sending to the whole reply.

One prompt, side by side

Each model's reply to “A product announcement with five rules”, as it came, with whether it passed and what it cost.

The prompt: A product announcement with five rules (hard)
Write a product announcement for the Nordvik 2 desk lamp in under 120 words. Include all five facts: it dims in five steps; it charges from USB-C; its arm turns 270 degrees; it costs €79; it ships on 1 December. Use no exclamation marks, and end with a question.
  • GPT-6 Astra

    Passed: Graded 4.3 of 5 on average (lowest 4).

    Meet the Nordvik 2, a desk lamp that puts light where you need it. Choose from five dimming steps, turn the arm 270 degrees to find your angle, and charge it via USB-C.
    
    Priced at €79 and shipping on 1 December, the Nordvik 2 is ready for your next chapter, sketch or late-night idea.
    
    Ready to see your desk in a new light?

    406 tokens in, 87 out · 3.3 s · $0.0084 · 1 message on Pro · answered by openai/gpt-6-astra via OpenAI ·

  • GPT-6.1 Sol

    Passed: Graded 4.3 of 5 on average (lowest 4).

    Meet the Nordvik 2 desk lamp, designed to bring flexible lighting to your workspace. It dims in five steps, letting you choose the right brightness for focused work or a quieter evening. Its arm turns 270 degrees, so you can direct light where you need it, and it charges from USB-C for convenient powering.
    
    The Nordvik 2 costs €79 and ships on 1 December.
    
    Ready to see your desk in a new light?

    408 tokens in, 94 out · 1.9 s · $0.0009 · 1 message on Pro · answered by openai/gpt-6.1-sol via OpenAI ·

  • GPT-6 Luna

    Passed: Graded 4.0 of 5 on average (lowest 3).

    Meet the Nordvik 2, a desk lamp designed to bring flexible light to your workspace. Choose from five brightness levels, charge it via USB-C, and turn its arm up to 270 degrees to direct light where you need it. The Nordvik 2 costs €79 and ships on 1 December. Ready to brighten your desk?

    406 tokens in, 73 out · 1.5 s · $0.0001 · 1 message on Pro · answered by openai/gpt-6-luna via OpenAI ·

The writing prompts, and how they're scored

Rubric (graded). The grader model scores the reply from 1 to 5 on each published criterion. It passes with an average of 4 or more and no criterion under 3, and only if it also meets the prompt's automatic rules (length, words it must or mustn't use).

The grader is Claude Opus 5.5 at low reasoning effort; its own replies are graded by GPT-6 Astra, so no model grades itself. Its prompt and every rubric are on the methods page.

Each prompt was sent the way llmwise sends a message in a side-by-side comparison, which offers no tools: the app's own system prompt, the model's own settings, and Pro's reply size limit (8,000 tokens). Read all five writing prompts and how every reply was scored.

Prompts like these to try yourself

GPT in llmwise

GPT models in llmwise
ModelOn ProOn FreeContext windowImagesPDFsReasoningAPI price per 1M, in / out
GPT-6 AstraOpenAI31/mo on ProNo1.05M tokensYesWhole fileYes$10.00 / $50.00
GPT-6.1 SolOpenAI125/mo on ProYes1.05M tokensYesWhole fileYes$2.00 / $10.00
GPT-6 SolOpenAI125/mo on ProYes1.05M tokensYesWhole fileYes$2.00 / $10.00
GPT-6 LunaOpenAI60/day on ProYes1.05M tokensYesWhole fileYes$0.10 / $0.50
Each badge is how many messages Pro gets on the model: a month’s, or a day’s on an everyday model. Free is a one-time trial of 5 messages on the models marked. “Text only” models get the text of a PDF, not the file. API prices are the per-token prices in our model catalog as of October 2026 (OpenAI: OpenAI's list price). In llmwise you pay per message, not per token.

Every limit is published. Paid plans also have a monthly fair-use limit on AI cost: Pro $7.50, Max $20, Ultra $42, Studio $85. Using every message on your plan at typical sizes stays under it; very large messages and heavy research use it faster. Every limit, explained.

What matters for writing

  • Voice and tone

    The best draft is the one that sounds like you. Models differ in how well they pick up a voice from examples.

  • Following the brief

    Word counts, audiences, must-include points: a good writing model keeps to the brief.

  • Editing, not just drafting

    Most writing is editing. Ask for changes to a draft rather than a new one each time.

GPT for writing in llmwise

  • Drafts as documents

    Drafts open as documents beside the chat: edit them, step through versions and download them as PDF, Word or Markdown.

  • Personas

    Pick the Writer persona, or make your own with your voice and a default model.

  • Web search with sources

    The model can search the web and cite what it found as source cards, or read a link you paste. On Free, web search works inside your 5 trial messages; on a paid plan a search counts as one more message of the model in use.

  • Switch models mid-chat

    Start on a cheaper model; if the answer isn't good enough, switch models in the same chat. The next model sees the whole conversation, so you don't paste anything twice.

In llmwise, a message to GPT goes to its maker, OpenAI, or through OpenRouter when llmwise can't reach the maker directly. See the Privacy Policy.

Tips

  • Say who it's for, how long, and what it must include.

  • Paste a paragraph you like and ask for that voice.

  • Ask for three options for headlines and openings.

  • Get a second opinion: switch models and ask for a critique of the draft.

Questions

Is GPT good for writing?

In our test runs on September 29, 2026, GPT-6 Astra passed 5 of 5, GPT-6.1 Sol passed 4 of 5, GPT-6 Sol passed 4 of 5, GPT-6 Luna passed 5 of 5 of our writing prompts, against a best result of 5 of 5 among all 19 models. Every reply is published on this page and the methods page, so you can judge them yourself.

Which GPT model should I use for writing?

Start with GPT-6 Luna for short rewrites, subject lines, grammar fixes and quick replies, and move up to GPT-6 Astra for long pieces that need structure and judgment: reports, essays, careful edits.

Can I use GPT for writing for free?

Yes: GPT-6.1 Sol, GPT-6 Sol, and GPT-6 Luna are on the Free plan (a one-time trial of 5 messages). GPT-6 Astra needs a paid plan.

Can I export what it writes?

Yes. Ask for a document and it downloads as PDF, Word or Markdown, with every version kept.

Claude, GPT, Gemini, DeepSeek, Grok, Kimi, GLM, and Mistral, in one chat.

See what a message costs before you send it. Free is 5 messages to try; sign in with an email link, no password or card.