Skip to content

Free tool · LinkedIn

LinkedIn post generator

Say what happened and get a LinkedIn post ready to paste, with every name and number you gave and none you didn't: 1 free run a day on GPT-6 Luna, no account needed. New jobs, launches, hiring and lessons learned.

1 free run a day, no account needed

GPT-6 Luna

Up to 1,500 characters. No files, tools or web search in a free run. One free run a browser, and one a network each day, shared with the free message on our home page.

Try an example:

By running it, you agree to the Terms and Privacy Policy and confirm you’re 18 or older. We keep what you send and its answer for 7 days, or in your account if you sign up.

Test runs checked . Updated .

LinkedIn post generator: three examples

Three inputs and the post a free run gave each, made once on September 29, 2026 with GPT-6 Luna and shown as it came back. The example buttons in the box above show the same.

A promotion

I've been promoted to Engineering Manager at Loomwise after 3 years as a senior engineer. Thank my manager, Sofia Reyes, and my team.

I’ve been promoted to Engineering Manager at Loomwise after 3 years as a senior engineer.

Thank you to my manager, Sofia Reyes, and to my team for your support along the way. Looking forward to this next chapter.

#EngineeringManagement #Loomwise
A product launch

We launched our first product, Ledgerly, a bookkeeping tool for freelancers. 1,200 people joined the waitlist. It's free for the first month.

We launched Ledgerly, our first product—and it’s built for freelancers.

1,200 people joined the waitlist. Now, Ledgerly is here to make bookkeeping easier.

It’s free for the first month.

#Freelancers #Bookkeeping #Ledgerly
A lesson learned

A lesson from my first year freelancing: I raised my rates twice and lost only one client. Keep it under 150 words, no hashtags.

A lesson from my first year freelancing: I raised my rates twice and lost only one client.

For a long time, I worried that charging more would mean losing the clients I valued. But raising my rates helped me see that the right working relationships aren’t built on keeping my prices as low as possible.

It was a useful reminder to value my work—and to be willing to say what it costs.

Which AI model is best at this? We tested every one

In our test runs of 5 LinkedIn post generator inputs on 17 models, GPT-6 Luna, DeepSeek V4.1 Flash, Gemini 3.8 Flash and 8 more passed the most: 5 of 5. That includes GPT-6 Luna, the model a free run is on.

Run on September 29, 2026: 5 inputs on 17 models, each with this tool's own instructions.

Each model's results on the tool's test inputs
ModelPassedHard onesMessages used on ProCost per runTime per run
GPT-6 LunaOpenAIThe free run's model5 of 52 of 21 each, of 60 a day on Pro$0.00003.2 s
DeepSeek V4.1 FlashDeepSeek5 of 52 of 21 each, of 60 a day on Pro$0.00041.0 s
Gemini 3.8 FlashGoogle5 of 52 of 21 each, of 250 a month on Pro$0.00031.2 s
DeepSeek V4 ProDeepSeek5 of 52 of 21 each, of 250 a month on Pro$0.00328.6 s
Grok 4.7xAI5 of 52 of 21 each, of 250 a month on Pro$0.007313.4 s
GPT-6.1 SolOpenAI5 of 52 of 21 each, of 125 a month on Pro$0.00102.8 s
GPT-6 SolOpenAI5 of 52 of 21 each, of 125 a month on Pro$0.00133.3 s
Claude Sonnet 5.5Anthropic5 of 52 of 21 each, of 125 a month on Pro$0.00383.5 s
Gemini 3.1 Pro (preview)Google5 of 52 of 21 each, of 125 a month on Pro$0.00678.8 s
Claude Opus 5.5Anthropic5 of 52 of 21 each, of 62 a month on Pro$0.00925.1 s
GPT-6 AstraOpenAI5 of 52 of 21 each, of 31 a month on Pro$0.00473.0 s
GLM 5.3 FlashZ.ai4 of 51 of 21 each, of 60 a day on Pro$0.00012.8 s
Claude Haiku 4.5Anthropic4 of 51 of 21 each, of 250 a month on Pro$0.00091.9 s
Kimi K3Moonshot4 of 51 of 21 each, of 125 a month on Pro$0.00194.3 s
Claude Fable 5.1Anthropic4 of 51 of 21 each, of 31 a month on Pro$0.01514.2 s
GLM 5.3Z.ai3 of 50 of 21 each, of 250 a month on Pro$0.00081.0 s
Claude Sonnet 5Anthropic3 of 50 of 21 each, of 125 a month on Pro$0.00283.3 s
Passed: of the 5 test inputs, how many answers passed their check (an answer the provider failed to give isn't counted). Messages used: what each run counted as on Pro, and Pro's count on the model. Cost: what OpenRouter charged us per run, on average; in llmwise you pay per message, not per token. Time: from sending to the whole answer.

Side by side: under 120 words, no hashtags

The same input on GPT-6 Luna and DeepSeek V4.1 Flash, as each answered it, unedited.

Write this LinkedIn post, ready to paste. Keep every name and number I give, add none I didn't, and follow every rule I set. End with up to three relevant hashtags.

---
What I learned from shutting down my startup, Pantry Pal, after 3 years. Keep it under 120 words and use no hashtags.
GPT-6 Luna
After 3 years, I’m shutting down Pantry Pal.

It’s hard to close something you’ve put so much into. But building it taught me that commitment isn’t the same as progress, and that changing direction—or stopping—can be the right decision.

I’m leaving with a clearer sense of what it takes to build a business, and a lot of gratitude for the people who supported Pantry Pal along the way.

The startup is ending. The lessons aren’t.
DeepSeek V4.1 Flash
Pantry Pal is shut down. Three years, and it's over.

I learned more in the last month than in the first year. Closing something takes nearly as much work as starting it.

Here's what I'd tell anyone building right now: a good product can still fail to be a business. That's the lesson I keep circling back to.

Three years on Pantry Pal. I don't regret any of them, including the ending.

No hashtags, as you asked.

How the inputs are scored

  • Key facts: the answer must state each fact the input turns on (a number, a name, a date or a condition), as the input gives it, keep any format rule the input sets (one sentence, a word limit, a number of items, a length for each), and say nothing the input rules out (an ingredient, a claim it doesn't back); how it's worded isn't judged.

The inputs: a new job, a feature launch, four engineers thanked, a hiring post with the salary, under 120 words, no hashtags, and three paragraphs, a closing question, no added figures. Every model gets the tool's own instructions and up to Pro's reply limit. The method is the same as our other test runs.

How to use the LinkedIn post generator

  1. Say what happened and what you want the post to do, with every name, date and number it needs. Up to 1,500 characters.

  2. Pick the tone, the hashtags and the language.

  3. Press “Write the post”. Without an account you see how it opens (1 free run a day, no account needed).

  4. Paste it into LinkedIn, tag the people you mention, and read it once on your phone before posting.

Tips for a better answer

  • One real number

    Give it the numbers you're happy to share (“1,200 on the waitlist”). A post with one real figure beats three adjectives.

  • Name who to thank

    Name the people to thank, and their roles. It keeps them exactly; you tag them after pasting.

  • Give it an ask

    Say what you want readers to do: apply, try it, share their own story. The post ends on that instead of a platitude.

  • Story for lessons

    Pick Story for a lesson learned. It opens on a moment rather than a conclusion, which is what gets read past the fold.

What a good post looks like

  • The news in the first line

    LinkedIn shows about the first 200 characters before “…see more”. The opening line has to make someone click: the news, not “I'm humbled to announce”.

  • Names and numbers exact

    Every person you thank, every figure and every company name should be exactly what you gave. Tag the people yourself after pasting: the tool can't.

  • No numbers you didn't give

    A post that turns “we grew” into “we grew 300%” is a post you'll have to correct in the comments. Check that no number appeared that you didn't provide.

  • Easy to read on a phone

    Short paragraphs of one to three lines read better on a phone than a block of text. Three hashtags at most, at the end, if any.

What's free, and what signing up adds

  • Without an account: 1 free run a day, on GPT-6 Luna, shared with the free message on our home page. It takes up to 1,500 characters, writes up to about 600 tokens (roughly 450 words), and shows you the start of the post.

  • Signing up is free, with an email link and no card. llmwise accounts are for people 18 and older. The post you ran comes with you as your first chat, and you get 5 free messages on almost every model (all but Claude Fable 5.1, Claude Opus 5.5, and GPT-6 Astra).

  • Signed in, the tool runs on the model you pick, on your plan, shows the whole answer, and you can carry on in the chat with any model, or ask another model the same thing.

More free tools are on the tools page, and what each plan gives is on pricing.

Questions

Is the LinkedIn post generator free?

Yes. Without an account you get 1 run a day on GPT-6 Luna, shared with the free message on our home page: you see how the post opens, and the rest when you sign up. Signing up is free and adds 5 free messages on almost every model in llmwise (all but Claude Fable 5.1, Claude Opus 5.5, and GPT-6 Astra), with no card.

Does it post to LinkedIn for me?

No. It writes the text; you paste it into LinkedIn yourself, and add the tags, the photo and the link there. It never signs in to your account.

What kinds of posts can it write?

New jobs and promotions, product launches, hiring posts, event recaps, thank-yous, milestones and lessons learned. Describe anything else and it writes it the same way.

Can I turn off the hashtags?

Pick “None” under hashtags, or say “no hashtags” in your description. By default it adds up to three at the end.

How long is the post?

Under 200 words by default, which is most of what gets read before people scroll on. Set your own limit in the description and it keeps to it.

Which AI is best for this, in your tests?

In our test runs of 5 LinkedIn post generator inputs on 17 models, GPT-6 Luna, DeepSeek V4.1 Flash, Gemini 3.8 Flash and 8 more passed the most: 5 of 5. That includes GPT-6 Luna, the model a free run is on. The table on this page has every model's result, what a run counts as on Pro, and the time it took.

Claude, GPT, Gemini, DeepSeek, Grok, Kimi, and GLM, 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.