[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"blog.post.more-tokens-for-everyone":3,"blog.related.more-tokens-for-everyone":116,"blog.adjacent.more-tokens-for-everyone":348},{"data":4,"meta":112},[5],{"id":6,"Title":7,"Content":8,"Description":9,"Category":10,"slug":11,"createdAt":12,"updatedAt":13,"publishedAt":14,"readTime":15,"documentId":16,"Image":17,"author":66,"Seo":109},9,"More tokens for everyone","Just a quick one from us to let you know about a few changes we released last week that you probably want to hear about.\n\nUnderlying model prices are changing all the time (usually getting cheaper) and we are still committed to passing these savings on to you so you get the best value out of Chat Thing possible.\n\nWe've made two changes that are going to positively effect your bots.\n\n## More message tokens for all plans\n\nFirst, we've significantly boosted the number of message tokens on available on each plan! This is due our default model (gpt-3.5-turbo-0125) pricing being massively reduced by OpenAI.\n\n**For most plans your message tokens will have almost doubled over night!**\n\n![Xnapper-2024-03-20-12.36.27.png](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1710942287\u002FXnapper_2024_03_20_12_36_27_ca1e47a145.png)\n\n## Message tokens that go further\n\nThe second change we have made relates to how we calculate the tokens used while chatting to your bots.\n\nWe now count input and output tokens separately so they can be charged at different rates.\n\nMany model providers charge different amounts for input tokens and output tokens.\n\nInput tokens are often cheaper and include the prompt, the message, and anything else that is sent to the model when you chat with a bot. Output tokens are often more expensive and consist of the responses generated by your bots.\n\nPreviously, we treated all the tokens used by your bot the same, but now we have introduced multipliers for input and output tokens so we can adjust the number of message tokens they use to better reflect the underlying models.\n\nIn general you will use way more input tokens than output tokens, because every time you send a message the input tokens are made up from your bot prompt and entire chat history, so this new change should mean that on the whole your message tokens go further.\n\nWe have added a section to our docs explaining this change, include a table with each of the model's input and output modifier values.\n\n[https:\u002F\u002Fchatthing.ai\u002Fdocs\u002Fwhat-are-message-tokens](https:\u002F\u002Fchatthing.ai\u002Fdocs\u002Fwhat-are-message-tokens)\n\n![Xnapper-2024-03-20-12.37.12.png](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1710942287\u002FXnapper_2024_03_20_12_37_12_42580edec6.png)\n\n## AI bots are becoming more affordable every day\n\nOur biggest cancelation reason is its \"too expensive\" and to be honest, until recently it was hard to disagree, especially if you need the more expensive models.\n\nLuckily over the past 6 months we have been able to reduce the cost of our models multiple times and will continue to do so whenever the underlying cost changes.\n\nAt the current rate of price reductions AI bots will soon be extremely affordable for everyone and even more use-cases!\n","Underlying model prices are changing all the time (usually getting cheaper) and we are still committed to passing these savings on to you so you get the best value out of Chat Thing possible.","changelog","more-tokens-for-everyone","2024-03-20T13:35:57.646Z","2024-03-20T14:26:57.975Z","2024-03-20T13:47:42.984Z",null,"sphnm3aym2aihdt4pmrfwgn9",{"id":18,"name":19,"alternativeText":15,"caption":15,"width":20,"height":21,"formats":22,"hash":58,"ext":24,"mime":27,"size":59,"url":60,"previewUrl":15,"provider":61,"provider_metadata":62,"createdAt":63,"updatedAt":63,"documentId":64,"publishedAt":65,"focalPoint":15},256,"blog cover.jpg",1920,1080,{"large":23,"small":34,"medium":42,"thumbnail":50},{"ext":24,"url":25,"hash":26,"mime":27,"name":28,"path":15,"size":29,"width":30,"height":31,"provider_metadata":32},".jpg","https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1710942232\u002Flarge_blog_cover_926ff87fd1.jpg","large_blog_cover_926ff87fd1","image\u002Fjpeg","large_blog cover.jpg",90.15,1000,563,{"public_id":26,"resource_type":33},"image",{"ext":24,"url":35,"hash":36,"mime":27,"name":37,"path":15,"size":38,"width":39,"height":40,"provider_metadata":41},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1710942232\u002Fsmall_blog_cover_926ff87fd1.jpg","small_blog_cover_926ff87fd1","small_blog cover.jpg",30.76,500,281,{"public_id":36,"resource_type":33},{"ext":24,"url":43,"hash":44,"mime":27,"name":45,"path":15,"size":46,"width":47,"height":48,"provider_metadata":49},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1710942232\u002Fmedium_blog_cover_926ff87fd1.jpg","medium_blog_cover_926ff87fd1","medium_blog cover.jpg",59.53,750,422,{"public_id":44,"resource_type":33},{"ext":24,"url":51,"hash":52,"mime":27,"name":53,"path":15,"size":54,"width":55,"height":56,"provider_metadata":57},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1710942232\u002Fthumbnail_blog_cover_926ff87fd1.jpg","thumbnail_blog_cover_926ff87fd1","thumbnail_blog cover.jpg",9.82,245,138,{"public_id":52,"resource_type":33},"blog_cover_926ff87fd1",230.21,"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1710942232\u002Fblog_cover_926ff87fd1.jpg","cloudinary",{"public_id":58,"resource_type":33},"2024-03-20T13:43:53.556Z","h9jnnxsezyt6pdnch43maipy","2026-05-15T15:25:35.762Z",{"id":67,"Name":68,"createdAt":69,"updatedAt":70,"publishedAt":71,"documentId":72,"Image":73},2,"Zef","2024-03-20T13:35:42.255Z","2024-03-20T13:35:43.988Z","2024-03-20T13:35:43.980Z","qpnfq2shgxc6b1too3b96idh",{"id":74,"name":75,"alternativeText":15,"caption":15,"width":76,"height":76,"formats":77,"hash":103,"ext":24,"mime":27,"size":104,"url":105,"previewUrl":15,"provider":61,"provider_metadata":106,"createdAt":107,"updatedAt":107,"documentId":108,"publishedAt":65,"focalPoint":15},255,"IMG_2278.jpg",1972,{"large":78,"small":84,"medium":90,"thumbnail":96},{"ext":24,"url":79,"hash":80,"mime":27,"name":81,"path":15,"size":82,"width":30,"height":30,"provider_metadata":83},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1710941716\u002Flarge_IMG_2278_d3b5e4fa69.jpg","large_IMG_2278_d3b5e4fa69","large_IMG_2278.jpg",194.09,{"public_id":80,"resource_type":33},{"ext":24,"url":85,"hash":86,"mime":27,"name":87,"path":15,"size":88,"width":39,"height":39,"provider_metadata":89},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1710941717\u002Fsmall_IMG_2278_d3b5e4fa69.jpg","small_IMG_2278_d3b5e4fa69","small_IMG_2278.jpg",54.08,{"public_id":86,"resource_type":33},{"ext":24,"url":91,"hash":92,"mime":27,"name":93,"path":15,"size":94,"width":47,"height":47,"provider_metadata":95},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1710941716\u002Fmedium_IMG_2278_d3b5e4fa69.jpg","medium_IMG_2278_d3b5e4fa69","medium_IMG_2278.jpg",114.8,{"public_id":92,"resource_type":33},{"ext":24,"url":97,"hash":98,"mime":27,"name":99,"path":15,"size":100,"width":101,"height":101,"provider_metadata":102},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1710941716\u002Fthumbnail_IMG_2278_d3b5e4fa69.jpg","thumbnail_IMG_2278_d3b5e4fa69","thumbnail_IMG_2278.jpg",6.59,156,{"public_id":98,"resource_type":33},"IMG_2278_d3b5e4fa69",641.66,"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1710941716\u002FIMG_2278_d3b5e4fa69.jpg",{"public_id":103,"resource_type":33},"2024-03-20T13:35:18.234Z","b2ylr2lzfx0rstj4qs9sh8b7",{"id":110,"metaTitle":7,"metaDescription":111,"keywords":15,"metaRobots":15,"structuredData":15,"metaViewport":15,"canonicalURL":15,"metaImage":15},20,"We have boosted message tokens across all plans to reflect the falling price of AI models",{"pagination":113},{"page":114,"pageSize":115,"pageCount":114,"total":114},1,25,{"data":117,"meta":343},[118,218,280],{"id":119,"Title":120,"Content":121,"Description":122,"Category":10,"slug":123,"createdAt":124,"updatedAt":125,"publishedAt":126,"readTime":15,"documentId":127,"Image":128,"author":168},32,"Custom Domains: Your Bot, Your Brand, Your Domain","Your bots just got a whole lot more professional. We're excited to announce **Custom Domains** — a feature that lets you serve your Chat Thing bots from your very own domain.\n\nInstead of embedding your bot from `embed.chatthing.ai`, you can now use something like `chat.yourcompany.com` or `support.yourbrand.io`. It's fully white-labelled, SSL-secured, and takes just a few minutes to set up.\n\n## Why Custom Domains?\n\nWhen you embed a Chat Thing bot on your website, your users see our domain in the embed URL. For most use cases that's fine, but if you're building a product, running an agency, or just want that extra polish — having your own domain makes all the difference.\n\n**Benefits include:**\n\n- **Brand consistency** — Your bot lives on your domain, matching the rest of your site\n- **Trust signals** — Users see your domain, not a third party\n- **Professional appearance** — Perfect for client-facing bots and enterprise deployments\n- **Full SSL coverage** — We handle certificates automatically via Cloudflare\n\n## How It Works\n\nSetting up a custom domain is straightforward:\n\n1. **Add your domain** — Head to your bot's Web channel settings and enter your desired domain (e.g., `chat.yourcompany.com`)\n2. **Configure DNS** — We'll generate three DNS records for you to add:\n   - A TXT record for SSL certificate validation\n   - A TXT record to verify domain ownership\n   - A CNAME record pointing to `embed.chatthing.ai`\n3. **Verify and go live** — Click verify, wait for DNS propagation, and you're done!\n\n![Custom domains section](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1770654691\u002Fdocs\u002Fmzhljvoxddzbh2rqbbqd.png)\n\nOnce active, your embed codes automatically update to use your custom domain. No code changes needed.\n\n![Custom domain active with embed code](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1770654295\u002Fdocs\u002Flribfkrjyalvghfyo4ed.png)\n\n## Domain Status Flow\n\nYour domain will progress through these statuses:\n\n- **Pending** — Domain added, awaiting setup\n- **DNS Pending** — Records detected, SSL certificate being issued\n- **Active** — Fully configured and ready to use ✅\n- **Failed** — Check your DNS records and try again\n\n## Availability\n\nCustom Domains is available as a paid addon. Each addon provides one custom domain slot across your team. You can purchase additional slots from your [billing page](https:\u002F\u002Fchatthing.ai\u002Fapp\u002Fbilling) if you need multiple domains.\n\n## Get Started\n\nReady to give your bots a professional home? Check out our [Custom Domains documentation](https:\u002F\u002Fchatthing.ai\u002Fdocs\u002Fcustom-domains) for the full setup guide.","Give your AI bots a fully white-labelled experience. Custom domains let you serve your bot from your own domain like chat.yourcompany.com instead of embed.chatthing.ai.","custom-domains-your-bot-your-brand-your-domain","2026-02-10T11:49:25.830Z","2026-04-17T15:39:35.071Z","2026-02-10T12:00:48.918Z","xi6rdt5pnge2pst8iggy46ju",{"id":129,"name":130,"alternativeText":15,"caption":15,"width":131,"height":132,"formats":133,"hash":162,"ext":24,"mime":27,"size":163,"url":164,"previewUrl":15,"provider":61,"provider_metadata":165,"createdAt":166,"updatedAt":166,"documentId":167,"publishedAt":65,"focalPoint":15},694,"file_94---5d631697-29ed-4946-9cd4-efccfd7fe3f5.jpg",1280,720,{"large":134,"small":141,"medium":148,"thumbnail":155},{"ext":24,"url":135,"hash":136,"mime":27,"name":137,"path":15,"size":138,"width":30,"height":31,"sizeInBytes":139,"provider_metadata":140},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1770724454\u002Flarge_file_94_5d631697_29ed_4946_9cd4_efccfd7fe3f5_758939dc92.jpg","large_file_94_5d631697_29ed_4946_9cd4_efccfd7fe3f5_758939dc92","large_file_94---5d631697-29ed-4946-9cd4-efccfd7fe3f5.jpg",41.03,41029,{"public_id":136,"resource_type":33},{"ext":24,"url":142,"hash":143,"mime":27,"name":144,"path":15,"size":145,"width":39,"height":40,"sizeInBytes":146,"provider_metadata":147},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1770724454\u002Fsmall_file_94_5d631697_29ed_4946_9cd4_efccfd7fe3f5_758939dc92.jpg","small_file_94_5d631697_29ed_4946_9cd4_efccfd7fe3f5_758939dc92","small_file_94---5d631697-29ed-4946-9cd4-efccfd7fe3f5.jpg",15.21,15213,{"public_id":143,"resource_type":33},{"ext":24,"url":149,"hash":150,"mime":27,"name":151,"path":15,"size":152,"width":47,"height":48,"sizeInBytes":153,"provider_metadata":154},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1770724454\u002Fmedium_file_94_5d631697_29ed_4946_9cd4_efccfd7fe3f5_758939dc92.jpg","medium_file_94_5d631697_29ed_4946_9cd4_efccfd7fe3f5_758939dc92","medium_file_94---5d631697-29ed-4946-9cd4-efccfd7fe3f5.jpg",29.46,29457,{"public_id":150,"resource_type":33},{"ext":24,"url":156,"hash":157,"mime":27,"name":158,"path":15,"size":159,"width":55,"height":56,"sizeInBytes":160,"provider_metadata":161},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1770724454\u002Fthumbnail_file_94_5d631697_29ed_4946_9cd4_efccfd7fe3f5_758939dc92.jpg","thumbnail_file_94_5d631697_29ed_4946_9cd4_efccfd7fe3f5_758939dc92","thumbnail_file_94---5d631697-29ed-4946-9cd4-efccfd7fe3f5.jpg",4.78,4779,{"public_id":157,"resource_type":33},"file_94_5d631697_29ed_4946_9cd4_efccfd7fe3f5_758939dc92",53.77,"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1770724454\u002Ffile_94_5d631697_29ed_4946_9cd4_efccfd7fe3f5_758939dc92.jpg",{"public_id":162,"resource_type":33},"2026-02-10T11:54:14.857Z","fwim9aki1tntxtle4g2o0rc0",{"id":114,"Name":169,"createdAt":170,"updatedAt":171,"publishedAt":172,"documentId":173,"Image":174},"Gem","2023-08-25T14:44:02.325Z","2026-04-03T14:53:07.377Z","2023-08-25T14:44:05.581Z","rs8ltnu1mkqi6j2hvepdj8ym",{"id":175,"name":176,"alternativeText":15,"caption":15,"width":177,"height":178,"formats":179,"hash":212,"ext":24,"mime":27,"size":213,"url":214,"previewUrl":15,"provider":61,"provider_metadata":215,"createdAt":216,"updatedAt":216,"documentId":217,"publishedAt":65,"focalPoint":15},732,"me2026.jpg",2288,1978,{"large":180,"small":188,"medium":196,"thumbnail":204},{"ext":24,"url":181,"hash":182,"mime":27,"name":183,"path":15,"size":184,"width":30,"height":185,"sizeInBytes":186,"provider_metadata":187},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1775227982\u002Flarge_me2026_022d4321e3.jpg","large_me2026_022d4321e3","large_me2026.jpg",170.04,865,170040,{"public_id":182,"resource_type":33},{"ext":24,"url":189,"hash":190,"mime":27,"name":191,"path":15,"size":192,"width":39,"height":193,"sizeInBytes":194,"provider_metadata":195},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1775227982\u002Fsmall_me2026_022d4321e3.jpg","small_me2026_022d4321e3","small_me2026.jpg",43.94,432,43943,{"public_id":190,"resource_type":33},{"ext":24,"url":197,"hash":198,"mime":27,"name":199,"path":15,"size":200,"width":47,"height":201,"sizeInBytes":202,"provider_metadata":203},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1775227982\u002Fmedium_me2026_022d4321e3.jpg","medium_me2026_022d4321e3","medium_me2026.jpg",95.7,648,95701,{"public_id":198,"resource_type":33},{"ext":24,"url":205,"hash":206,"mime":27,"name":207,"path":15,"size":208,"width":209,"height":101,"sizeInBytes":210,"provider_metadata":211},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1775227982\u002Fthumbnail_me2026_022d4321e3.jpg","thumbnail_me2026_022d4321e3","thumbnail_me2026.jpg",6.75,181,6747,{"public_id":206,"resource_type":33},"me2026_022d4321e3",732.7,"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1775227982\u002Fme2026_022d4321e3.jpg",{"public_id":212,"resource_type":33},"2026-04-03T14:53:02.980Z","fzyymo1uivslt1rep9c83edj",{"id":219,"Title":220,"Content":221,"Description":222,"Category":10,"slug":223,"createdAt":224,"updatedAt":225,"publishedAt":226,"readTime":15,"documentId":227,"Image":228,"author":268},29,"New in Chat Thing: Dictation, Spoken Responses, Spam Protection, Bot Duplication & More!","We've been hard at work shipping some highly-requested features to help you build even better AI agents. Here’s a look at what’s new:\n\n### 🗣️ Dictation & Spoken Responses\n\nFrankly, we're a little embarrassed this one took so long, but we're thrilled to finally release Dictation and Spoken Responses for the web channel! Your users can now interact with your bots using just their voice for a more natural and accessible experience.\n\nAnd this is just the beginning—soon, you’ll be able to customise the voice to perfectly match your brand.\n\nLearn how to enable it in the [Web Channel Documentation](https:\u002F\u002Fchatthing.ai\u002Fdocs\u002Fweb-channel#dictation-and-spoken-responses).\n\n![Xnapper-2025-07-30-20.00.42.png](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1753902103\u002FXnapper_2025_07_30_20_00_42_d3a9b00e2d.png)\n\n### 🛡️ Spam Protection\n\nProtect your public-facing bots from abuse with our new Spam Protection feature. Powered by Cloudflare Turnstile, it provides a seamless, privacy-preserving way to block automated spam without forcing your users to solve annoying CAPTCHAs. You can activate it from your web channel settings.\n\nCheck out the [Spam Protection Documentation](https:\u002F\u002Fchatthing.ai\u002Fdocs\u002Fweb-channel#spam-protection) to get started.\n\n![Cloudflare turnstile spam protection](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1753965261\u002FCloudflare_turnstile_spam_protection_f03ff305b8.png)\n\n### 💬 \"Talk to a human\" Power-up Update\n\nWe've made our \"Talk to a human\" power-up more flexible. You can now specify exactly which email address you want escalations to be forwarded to, directly within the power-up settings.\n\nFind out more in the[ Talk to a human Docs](https:\u002F\u002Fchatthing.ai\u002Fdocs\u002Ftalk-to-a-human).\n\n### ✨ Duplicate your Bots\n\nSpeed up your workflow with bot duplication! You can now create a copy of any existing bot, with full control to choose what you want to include—from data sources and prompts to channel settings and power-ups.\n\nLearn how in the [Duplicating Bots Documentation](https:\u002F\u002Fchatthing.ai\u002Fdocs\u002Fduplicating-bots).\n\n### Advanced: New Dynamic Prompt Tags\n\nFor our advanced users, you can now include two new replacement tags in your prompts that will be replaced dynamically at runtime: \u003Cbot-id> and \u003Cconversation-id>. This allows for more advanced logging, tracking, and multi-agent workflows.\n\n---\n\nWe can’t wait to see what you think of these updates, happy agent building","Announcing new Chat Thing features: Add voice dictation and spoken responses to your bot, enable Cloudflare spam protection, duplicate bots, and more.","new-in-chat-thing-dictation-spoken-responses-spam-protection-bot-duplication-and-more","2025-07-31T13:58:00.791Z","2025-07-31T14:00:47.897Z","2025-07-31T13:58:05.390Z","oqpzapmxkep0kh8kv70pb38f",{"id":229,"name":230,"alternativeText":15,"caption":15,"width":20,"height":21,"formats":231,"hash":262,"ext":233,"mime":236,"size":263,"url":264,"previewUrl":15,"provider":61,"provider_metadata":265,"createdAt":266,"updatedAt":266,"documentId":267,"publishedAt":65,"focalPoint":15},670,"Audio and spam protection.png",{"large":232,"small":241,"medium":248,"thumbnail":255},{"ext":233,"url":234,"hash":235,"mime":236,"name":237,"path":15,"size":238,"width":30,"height":31,"sizeInBytes":239,"provider_metadata":240},".png","https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1753970224\u002Flarge_Audio_and_spam_protection_3d99f3f000.png","large_Audio_and_spam_protection_3d99f3f000","image\u002Fpng","large_Audio and spam protection.png",277.43,277434,{"public_id":235,"resource_type":33},{"ext":233,"url":242,"hash":243,"mime":236,"name":244,"path":15,"size":245,"width":39,"height":40,"sizeInBytes":246,"provider_metadata":247},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1753970223\u002Fsmall_Audio_and_spam_protection_3d99f3f000.png","small_Audio_and_spam_protection_3d99f3f000","small_Audio and spam protection.png",79.14,79135,{"public_id":243,"resource_type":33},{"ext":233,"url":249,"hash":250,"mime":236,"name":251,"path":15,"size":252,"width":47,"height":48,"sizeInBytes":253,"provider_metadata":254},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1753970223\u002Fmedium_Audio_and_spam_protection_3d99f3f000.png","medium_Audio_and_spam_protection_3d99f3f000","medium_Audio and spam protection.png",157.7,157704,{"public_id":250,"resource_type":33},{"ext":233,"url":256,"hash":257,"mime":236,"name":258,"path":15,"size":259,"width":55,"height":56,"sizeInBytes":260,"provider_metadata":261},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1753970223\u002Fthumbnail_Audio_and_spam_protection_3d99f3f000.png","thumbnail_Audio_and_spam_protection_3d99f3f000","thumbnail_Audio and spam protection.png",28.05,28048,{"public_id":257,"resource_type":33},"Audio_and_spam_protection_3d99f3f000",235.92,"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1753970223\u002FAudio_and_spam_protection_3d99f3f000.png",{"public_id":262,"resource_type":33},"2025-07-31T13:57:04.793Z","uxsjqm1a2n6w8usjw345lxrc",{"id":67,"Name":68,"createdAt":69,"updatedAt":70,"publishedAt":71,"documentId":72,"Image":269},{"id":74,"name":75,"alternativeText":15,"caption":15,"width":76,"height":76,"formats":270,"hash":103,"ext":24,"mime":27,"size":104,"url":105,"previewUrl":15,"provider":61,"provider_metadata":279,"createdAt":107,"updatedAt":107,"documentId":108,"publishedAt":65,"focalPoint":15},{"large":271,"small":273,"medium":275,"thumbnail":277},{"ext":24,"url":79,"hash":80,"mime":27,"name":81,"path":15,"size":82,"width":30,"height":30,"provider_metadata":272},{"public_id":80,"resource_type":33},{"ext":24,"url":85,"hash":86,"mime":27,"name":87,"path":15,"size":88,"width":39,"height":39,"provider_metadata":274},{"public_id":86,"resource_type":33},{"ext":24,"url":91,"hash":92,"mime":27,"name":93,"path":15,"size":94,"width":47,"height":47,"provider_metadata":276},{"public_id":92,"resource_type":33},{"ext":24,"url":97,"hash":98,"mime":27,"name":99,"path":15,"size":100,"width":101,"height":101,"provider_metadata":278},{"public_id":98,"resource_type":33},{"public_id":103,"resource_type":33},{"id":281,"Title":282,"Content":283,"Description":284,"Category":10,"slug":285,"createdAt":286,"updatedAt":287,"publishedAt":288,"readTime":15,"documentId":289,"Image":290,"author":331},28,"Try GPT-4.1 now + more updates","Hi agent builders! It’s been a while but we’ve got some great updates for you today!\n\n## Introducing GPT-4.1 Models\nHot off the press, only released yesterday, we've integrated OpenAI's latest GPT-4.1 models into Chat Thing, offering significant performance enhancements across the board. You can't use these models via ChatGPT as they are API only so Chat Thing is a great place to test them out! Here's some of the improvements:\n\n- **Expanded Context Window**: Handle up to 1 million tokens, enabling deeper context understanding.​\n- **Improved Coding Capabilities**: Achieved a 54.6% score on SWE-bench Verified, surpassing GPT-4o's 33.2%. ​\n- **Enhanced Instruction Following**: Better at adhering to complex, multi-step instructions. ​\n- **Cost-Effective Options**: GPT-4.1 Nano is now our most affordable model.\n\nRead OpenAI’s announcement post [here](https:\u002F\u002Fopenai.com\u002Findex\u002Fgpt-4-1\u002F)\n\nYou can select the 4.1 models from the model selector in your bot settings now. \n\n## Enhanced Chat Responses\n\n- **Code Syntax Highlighting**: Code blocks in responses now feature syntax highlighting for improved readability.​\n![Code Block Syntax Highlighting PR 851.png](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1744732406\u002FCode_Block_Syntax_Highlighting_PR_851_f4893cc0d8.png)\n- **LaTeX Rendering**: Mathematical expressions are rendered using LaTeX for clearer presentation.​\n![LaTeX Math Expression Rendering PR 852.png](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1744732431\u002FLa_Te_X_Math_Expression_Rendering_PR_852_aa86045fe6.png)\n\n## Additional Updates\n\n- Multilingual Support: Added and refined translations for multi-modal chat interface elements.​\n- RSS Data Source Scraping: Enabled CSS exclude rules to refine content extraction.​\n- Email Enhancements: Included reply-to headers in \"talk-to-human\" emails for better communication.​\n- UI Improvements: Enhanced conversation view styling for better readability.​\n- Bug Fixes: Resolved issues including duplicate bot-to-bot responses and improved API power-up validation.​\n\nWe can’t wait to see what you think of these updates, happy agent building!","Create smarter AI agents with Chat Thing's latest update: now featuring OpenAI's GPT-4.1 models, code syntax highlighting, LaTeX rendering, and enhanced multilingual support.​","try-gpt-4-1-now-more-updates","2025-04-15T15:54:21.709Z","2025-04-15T15:54:26.380Z","2025-04-15T15:54:26.318Z","rwu362ud60msel9b830pga3v",{"id":291,"name":292,"alternativeText":15,"caption":15,"width":20,"height":21,"formats":293,"hash":325,"ext":295,"mime":298,"size":326,"url":327,"previewUrl":15,"provider":61,"provider_metadata":328,"createdAt":329,"updatedAt":329,"documentId":330,"publishedAt":65,"focalPoint":15},649,"GPT-4.1 Release from Figma.webp",{"large":294,"small":304,"medium":311,"thumbnail":318},{"ext":295,"url":296,"hash":297,"mime":298,"name":299,"path":15,"size":300,"width":30,"height":301,"sizeInBytes":302,"provider_metadata":303},".webp","https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1744732011\u002Flarge_GPT_4_1_Release_from_Figma_29961568c3.webp","large_GPT_4_1_Release_from_Figma_29961568c3","image\u002Fwebp","large_GPT-4.1 Release from Figma.webp",20.96,562,20956,{"public_id":297,"resource_type":33},{"ext":295,"url":305,"hash":306,"mime":298,"name":307,"path":15,"size":308,"width":39,"height":40,"sizeInBytes":309,"provider_metadata":310},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1744732011\u002Fsmall_GPT_4_1_Release_from_Figma_29961568c3.webp","small_GPT_4_1_Release_from_Figma_29961568c3","small_GPT-4.1 Release from Figma.webp",10.12,10118,{"public_id":306,"resource_type":33},{"ext":295,"url":312,"hash":313,"mime":298,"name":314,"path":15,"size":315,"width":47,"height":48,"sizeInBytes":316,"provider_metadata":317},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1744732011\u002Fmedium_GPT_4_1_Release_from_Figma_29961568c3.webp","medium_GPT_4_1_Release_from_Figma_29961568c3","medium_GPT-4.1 Release from Figma.webp",15.85,15848,{"public_id":313,"resource_type":33},{"ext":295,"url":319,"hash":320,"mime":298,"name":321,"path":15,"size":322,"width":55,"height":56,"sizeInBytes":323,"provider_metadata":324},"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1744732011\u002Fthumbnail_GPT_4_1_Release_from_Figma_29961568c3.webp","thumbnail_GPT_4_1_Release_from_Figma_29961568c3","thumbnail_GPT-4.1 Release from Figma.webp",4.46,4462,{"public_id":320,"resource_type":33},"GPT_4_1_Release_from_Figma_29961568c3",40.8,"https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1744732011\u002FGPT_4_1_Release_from_Figma_29961568c3.webp",{"public_id":325,"resource_type":33},"2025-04-15T15:46:52.064Z","izzhki5509t22umz9g0cq22p",{"id":67,"Name":68,"createdAt":69,"updatedAt":70,"publishedAt":71,"documentId":72,"Image":332},{"id":74,"name":75,"alternativeText":15,"caption":15,"width":76,"height":76,"formats":333,"hash":103,"ext":24,"mime":27,"size":104,"url":105,"previewUrl":15,"provider":61,"provider_metadata":342,"createdAt":107,"updatedAt":107,"documentId":108,"publishedAt":65,"focalPoint":15},{"large":334,"small":336,"medium":338,"thumbnail":340},{"ext":24,"url":79,"hash":80,"mime":27,"name":81,"path":15,"size":82,"width":30,"height":30,"provider_metadata":335},{"public_id":80,"resource_type":33},{"ext":24,"url":85,"hash":86,"mime":27,"name":87,"path":15,"size":88,"width":39,"height":39,"provider_metadata":337},{"public_id":86,"resource_type":33},{"ext":24,"url":91,"hash":92,"mime":27,"name":93,"path":15,"size":94,"width":47,"height":47,"provider_metadata":339},{"public_id":92,"resource_type":33},{"ext":24,"url":97,"hash":98,"mime":27,"name":99,"path":15,"size":100,"width":101,"height":101,"provider_metadata":341},{"public_id":98,"resource_type":33},{"public_id":103,"resource_type":33},{"pagination":344},{"page":114,"pageSize":345,"pageCount":346,"total":347},3,5,14,{"prev":349,"next":360},{"id":350,"Title":351,"Content":352,"Description":353,"Category":354,"slug":355,"createdAt":356,"updatedAt":357,"publishedAt":358,"readTime":15,"documentId":359},8,"OpenAI GPTs vs Chat Thing","OpenAI's rapid innovation in AI technology is a double-edged sword for startups using their APIs. Watching their developer events is a nerve racking experience! On one hand you are excited for amazing new features that can help us make our products even more powerful, but on the other hand OpenAI can release competing features that could make you redundant.\n\nAfter OpenAI released GPTs, we had a number of people reach out and ask...\n\n>\"Oh no, have OpenAI just killed Chat Thing?\". \n\nWell thankfully the dust has settled now, and after having some time to really dig into GPTs and their capabilities we were relieved to realise for most professional use cases there are still plenty of reason to use a service like Chat Thing over GPTs. \n\n## OpenAI GPTs compared to Chat Thing\n\nAt first glance it might seem like OpenAI GPTs and Chat Thing provide very similar functionality, and while GPTs do a great job of making custom AI chat bots more accessible to everyone, in a lot of areas they are severely lacking features hampering their overall usefulness. \n\nIn most cases, if you want to integrate AI chat bots into your business you are still probably better off using a service like Chat Thing. Of course we would say that, but we will let you make up your own mind after reading the points below.\n\n### Data Sources\n\nOpenAI GPTs allow you to add \"knowledge\" to your bot by uploading up to 10 files. There are also size limits on these files, and you get charged $0.20 per day per gigabyte per bot! This is a great way of adding data to basic bots, but the limitations make it very impractical for anything more complicated.\n\n![Chat Thing's data sources](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1701161616\u002Fdatasources_5a20d55635.png)\n\nChat Thing's data sources are leaps and bounds ahead of GPTs knowledge files in many ways:\n\n- Automatically connect to 8+ different types of data source, not just files\n- Automatically refresh data source content to keep it up to date\n- No limits on the number of documents in a data source\n- Advanced functionality such as web crawling\n\n### Bots you can use anywhere\n\nWhen you create a GPT its forever imprisoned within the ChatGPT interface. That might be a bit dramatic, but it does make GPTs a lot less useful. Not only that but you can only use GPTs if you are a $20 a month ChatGPT plus subscriber, so this hugely limits who can use your bot if you share it publicly. \n\nWith Chat Thing if you share your bot via a URL anyone can use it regardless of whether they are a ChatGPT or Chat Thing subscriber. In addition to that, you can integrate your bot over many different channels such as Slack, Telegram, Discord, WhatsApp all in a few clicks. That's not possible with GPTs at the moment.\n\nWith Chat Thing you can even add an customisable embeddable widget to your site meaning you can use Chat Thing as a support agent helping to answer customer queries.\n\n![Chat Thing embeddable widget](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1701164565\u002Fwidget_fc9f4e0af7.png)\n\nIn summary here's the way Chat Thing makes your bots more shareable:\n\n- 6+ channels, interact with your bot via the web, Slack, Discord, Telegram, WhatsApp and API.\n- Shareable bot URLs that are useable by everyone, not just ChatGPT subscribers\n- Embeddable and customisable chat widgets\n- Password protect bots\n\n### Stopping hallucinations\n\nOne of the biggest issues with large language models such as GPT is their tendency to hallucinate and make up responses and data. This can be very detrimental to the usefulness of AI bots as depending on your use case the accuracy of responses might be very important. You don't want your support bot making things up when a customer has a problem, that will only anger them more!\n\nWith OpenAI GPTs, the only way to fight against hallucinations is via prompt engineering. You can write something along the lines of \"Only answer questions using the content in the provided documents. If the answer isn't there say 'I do not know'\". This technique works some of the time, but especially as the chat history gets longer the bots tend to stop paying as much attention to the prompt and can still hallucinate.\n\nIn Chat Thing you can use prompt engineering to prevent against hallucinations just like you can with GPTs, but we have also gone further and developed something we call response guards. Response guards basically get the bot to double check its responses before errors before sending them back to the user. This massively improves the reliability of the bot in giving back accurate information.\n\n![A screen shot of the response guard interface](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1701343041\u002Fresponse_guard_79b34ad6cd.png)\n\n### Conversation Logs\n\nWith OpenAI GPTs you have no way of seeing the conversations users have with your bot. Whilst this is good for privacy, it does limit GPTs for certain use cases. If you want to use them for customer support, lead generation, or many other uses having visibility of conversations will be essential. \n\nChat Thing provides you with full searchable conversation history so you can see how users are interacting with your bot. In addition to that user's can mark responses as positive or negative so you can see where your bot is lacking and make improvements in your data sources, or prompts etc. \n\nNot only that, but you can export all your bot's conversations as a CSV if you need to work with the data in other tools, and we are working more advanced features, such as bot usage statistics and graphs. None of which is available in GPTs.\n\n![A screen shot of the Chat Thing conversations interface](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1701344217\u002Fconversations_efd64fa3ff.png)\n\n![A screenshot of the new bot statistics screen](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1701344561\u002Fbot_statistics_7896dc59d4.png)\n\n### Personal Support\n\nAlthough getting started with creating an AI bot using GPTs or Chat Thing is quick and easy, tuning them to work exaclty how you want can be quite an art. There are many settings to tweak. Should I set a custom prompt? How do I change the tone? How do I stop hallucinations? Whats the best way to stop hallucinations. The list goes on!\n\nWith OpenAI GPTs you are completely on your own trying to figure out these issues, but with Chat Thing we have dedicated support with knowledge of helping people make thousands of bots ready to help whenever you need it. \n\nDon't just take our word for it, we get messages like the one below in our Discord community all the time. \n\n[![A message praising Chat Thing and our amazing support in Discord](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1701345105\u002Fdiscord_feedback_bcea77274b.png)](https:\u002F\u002Fdiscord.com\u002Fchannels\u002F1083665149627469834\u002F1083665149627469837\u002F1173961315551821845)\n\nWe have 850 members in [our Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002FDGCCR34Fsj) where you can get supports, or if email is more your style you can always email us there too and we will be happy to help. You won't get this kind of service setting up your GPTs from OpenAI.\n\n### Adaptability and new features\n\nAt Chat Thing we have the advantage of being a small nimble team that can adapt to customer requests and ideas at the click of your fingers. We have sooooo much in the pipeline we are really exited about, and we believe we can innovate at a faster pace than larger companies. \n\nWe are on the cusp of releasing a new and improved bot dashboard, and then shortly after that we will be releasing the first version of functions giving your bots powers they have never had before. \n\nOur long term vision for Chat Thing is to build a product that provides users with the easiest and most powerful way to integrate AI assistants into your websites and products. Chat Thing, should not only be a support tool, but a pro-active co-pilot that can not only guide users but take actions on their behalf! \n\n### Summary\n\nIn summary we are really pleased about the additional exposure OpenAI GPTs will provide to the bots industry. They are awesome for quickly dipping your toes in the world of AI bots, but for more professional use cases you will still need to reach for a service with more advanced features such as Chat Thing.\n","OpenAI have been shipping new features like maniacs which is both a good and bad if you are running a startup built on top of their APIs. Watching their developer events is a nerve racking experience! On one hand you are excited for amazing new features that can help us make our products even more powerful, but on the other hand OpenAI can release competing features that could make you redundant. ","blog","open-ai-gpts-vs-chat-thing","2023-11-27T13:11:14.905Z","2023-11-30T12:53:36.702Z","2023-11-30T12:53:36.693Z","nvhudjazyc0mbk8y20opd8a3",{"id":361,"Title":362,"Content":363,"Description":364,"Category":354,"slug":365,"createdAt":366,"updatedAt":367,"publishedAt":367,"readTime":67,"documentId":368},12," Launch Week: Day 3 - Talk to a human & send email","**Welcome back to Power-Ups Launch Week at Chat Thing! We're already halfway through our exciting week of new releases, and today, we're thrilled to unveil not one, but two new power-ups: \"Talk to a Human\" and \"Send Email\". Let's dive into what each of these power-ups brings to your Chat Thing experience.**\n\nIn case you missed the first two days, here's the links\n* Day 1: [Zapier Power-up](\u002Fblog\u002Flaunch-week-01-zapier-ai-actions?previews=true)\n* Day 2: [Notion Power-ups](\u002Fblog\u002Fnotion-power-ups-launch-week-01-day-2?previews=true)\n\n## Day 3 Power-ups: Talk to a human & send email\n\nThe easiest way to see what these two power-ups can do, is to watch our launch video below:\n\n{% youtube  id=\"QmGWMwI8fv4\" \u002F%}\n\n### \"Talk to a Human\" Power-up\nAI bots are getting really good, even still there are often times where they trip up or can't fulfil a user's request.\n\nThe is **NOTHING** more frustrating than getting stuck in a dead-end loop with a customer support bot we no escape hatch! \n\nThat's why we've built the \"Talk to a Human\" power-up that allows your chatbot to escalate conversations to a real person whenever needed. User's can simply ask \"Can I talk with a human\", \"Or can someone help me with this\" and the bot will ask for their email a notify the bot owner via email so they can pick things up from there.\n\nHere's and example of the power-up in action:\n\n![Xnapper-2024-04-06-13.18.56.webp](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1712406210\u002FXnapper_2024_04_06_13_18_56_ec1464ce8c.webp)\n\nand the resulting email received:\n\n![Xnapper-2024-04-06-13.22.17.webp](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1712406210\u002FXnapper_2024_04_06_13_22_17_b29742d55b.webp)\n\nWhile initially focused on email alerts, we're already working on expanding this feature. Future enhancements will include flagging conversations in the Chat Thing UI that require human intervention, among other user-centric improvements like human takeover of conversations and more.\n\n### \"Send Email\" Power-up\nThe \"Send Email\" power-up allows your chatbot to compose and send emails directly from the conversation.\n\nThis power-up can be used in a similar way to the talk to human power-up, but it is more flexible making it useful in other scenarios too.\n\nUnlike the talk to a human power-up, the send email power-up allows you to define a list of recipients for the email the bot will send out as well as options to set the subject. \n\nYou can use these settings to implement your own version of talk to a human, creating contact forms, submitting feature requests or anything else that can be achieved by sending emails!\n\n![Xnapper-2024-04-06-13.38.13.webp](https:\u002F\u002Fres.cloudinary.com\u002Fdjyjvrw5u\u002Fimage\u002Fupload\u002Fv1712407139\u002FXnapper_2024_04_06_13_38_13_0a8a9f3ff3.webp)\n\nAgain, this feature is very MVP at the moment and we will expand upon it to make it more powerful. In the future, we plan to allow you to add your own SMTP details or use your own templates etc. \n\n## Getting started\nBefore you get started with either of these power-ups, we recommend you take a look at our general Power-ups documentation here: [Power-up basics](\u002Fdocs\u002Fpower-up-basics&previews=true).\n\nOnce you are happy with the basics of Power-ups, take a look at our dedicated docs here: [Talk to a human](\u002Fdocs\u002Ftalk-to-a-human?previews=true) and [Send email](\u002Fdocs\u002Femail-power-up?previews=true)\n\n## Up next!\nWow half way through all ready! What a wild ride. We think people will be very excited with tomorrow's announcement when we will release another two power-ups. See you then! ","Today we're thrilled to unveil not one, but two new power-ups: \"Talk to a Human\" and \"Send Email\". ","launch-week-day-3-talk-to-a-human-and-send-email","2024-04-06T08:02:04.126Z","2024-04-06T08:02:04.000Z","cor6bujv2xmmtybx7yrl1p02"]