Pre-release · Signup open now
ปัญญาประดิษฐ์ ภาษาไทย AI that works in Thai, priced in baht.
ThaiGPT+ runs on Thai models, hosted in Thailand, and improved by Thai contributors. Drafting, document Q&A with citations, translation, dialect and voice — on a phone, on a desktop, or through an API you can call from anything. The + is what comes next: vision, hearing, and a router that picks the right model for you.
Pick a prompt to see how ThaiGPT+ answers.
The product
Four surfaces, one brand.
A mobile app built for a phone-first market with the highest mobile penetration in Southeast Asia. A desktop workspace built for institutions. An API built for everyone else. And the training loop that keeps improving what sits behind all three. These are live, interactive previews — click through them.
Mobile — voice-first, offline-capable
Thailand has around 135 mobile connections for every 100 people. The phone is not a secondary surface here, it is the surface. The microphone is the primary control: Thai keyboard input is slow, and speech reaches users who read slowly or read a different dialect than they speak.
Change the network. Watch the app, not an error page.
Thailand is phone-first by a wider margin than almost anywhere: more mobile connections than people, and most of the country reaching the internet through one. The app is designed for the connection people actually have, and it keeps working when they have none.
- Full model, full context
- Document Q&A with citations
- Voice in and voice out
- Live translation TH ↔ EN ↔ ZH
Every answer is metered in baht and shows the region it was served from.
Replying in Thai.
ผมไม่มีราคาตลาดแบบเรียลไทม์
I don't have live market prices. I can show this week's ministry bulletin, or draft a message to your co-op.
Drafted — 46 words, plain register. Tap to edit before sending.
Tap the microphone — voice is the primary control
The models
One family, six jobs.
A single Thai model is the wrong shape for a country where the same platform has to answer a ministry's 400-page regulatory corpus and a farmer's question on a phone with no signal. ThaiGPT+ ships a family, and the router picks between them. Sizes and context windows are targets for the pre-release, not benchmark results.
Four ways to say the same thing
This is the part that has no Lao equivalent and no off-the-shelf answer. Thai is not one language in practice: around a third of the country speaks a regional variety at home and writes Central Thai at work, and a model that only knows the written standard cannot hear half its users.
The written standard. What every general-purpose model has seen, and roughly all it has seen.
The largest regional variety, spoken across the northeast and close enough to Lao that the work crosses the border in both directions.
Northern Thai, with its own historic script still in liturgical and heritage use.
Southern Thai — fast, heavily contracted, and the variety speech systems get wrong first.
And five ways to be polite about it
Register in Thai is not a tone setting, it is a different vocabulary. Getting it wrong in a letter to a ministry is not a style error, it is a social one — and it is the single thing a foreign model is most reliably bad at.
- 1ราชาศัพท์ · royal
- 2ภาษาราชการ · official
- 3ทางการ · formal
- 4สุภาพ · polite
- 5ภาษาพูด · plain
Register is a request parameter, not a prompt instruction — so it is auditable, and a workspace can pin it.
See how the router picksSmart routing
One endpoint. The right model, every request.
Most requests do not need the biggest model, and some must never leave the phone. ThaiGPT+ reads each request before a token is generated, and decides which model answers it, which pipeline it goes through, and which region it is allowed to run in. You call one endpoint and never pick a model again.
How the router worksComing soon Roadmap — not yet shipped
Next: it learns to see, read and hear Thai.
Text was the first sense. ThaiGPT+ Vision, Scribe and Voice add the others — a model that can be shown a photographed form, a stamped and scanned circular, a handwritten minute, a shelf, a leaf or a prescription label, and answer about it in Thai.
ThaiLLM-Vision
Photographs, screenshots, charts, shelves, scenes, forms. Answers about what is in the frame, in Thai, with the region it was served from.
ThaiLLM-Scribe
The document specialist: stamped, scanned, skewed, multi-column, part-handwritten Thai paperwork into structured fields you can put in a database.
ThaiLLM-Voice
Thai speech recognition and synthesis across the four regional varieties, including the common case of a question asked in Isan that has to be answered in Central Thai — or the reverse.
Cross-modal
The one that matters: a photograph and a spoken question in the same request, answered against your own documents. This is the capability the separate models exist to make cheap.
The platform
The full force of PrivateGPT-Asia.
ThaiGPT+ inherits a complete private-AI application layer rather than rebuilding one. Everything below is platform capability, available on day one, running in-country.
PrivateGPTASIAThaiGPT+ is a branded deployment of PrivateGPT-Asia, not a rebuild. That is the whole reason a national AI platform can be fielded on this timescale: the hard application engineering is inherited, and the effort goes into the Thai layer that nobody else will build.
privategptasia.comRetrieval with citations
Answers traceable to the page and paragraph they came from. A claim you cannot open is a claim you cannot use.
Document ingestion
PDFs, scans, spreadsheets and office documents — including Thai documents that were typed, printed, stamped, then scanned again.
Tools and MCP
The model calls your systems through the Model Context Protocol instead of guessing at their contents.
Skills
Packaged procedures for work your organisation repeats — a circular, a report format, a review checklist.
Text-to-SQL
Questions answered against your own tables, with the query shown so somebody can check it.
Drop-in API compatibility
A Claude-API-shaped interface. An existing client points at a Thai endpoint with a base-URL change.
Runs where you put it
In-country servers, your own premises, or fully air-gapped. The platform does not require an internet round-trip to a foreign vendor.
Nothing leaves
Private by construction rather than by policy: data stays inside the environment the platform is deployed into.
And the part that only exists here
The platform gives ThaiGPT+ everything above on day one. Eight endpoints exist because Thai needs them and no general-purpose vendor is going to build them: word segmentation for text written without spaces, normalisation of Buddhist Era dates and Thai numerals, translation with register control, transliteration to and from RTGS, speech, dialect conversion, honorific grading, and Thai document OCR.
Why it costs less
Thai costs more to say in a foreign model.
Thai is written without spaces between words, is tonal, stacks up to four levels of vowel and tone mark around a single consonant, and carries heavy Pali-Sanskrit vocabulary. General-purpose tokenizers fragment it badly — often to the character — so a Thai user pays a multiple of the English price per sentence and gets a worse answer back. A Thai-optimised tokenizer attacks both sides of that ratio.
สรุปเอกสารนี้เป็นภาษาไทย
“summarise this document in Thai”
Thai is written without spaces between words, so a tokenizer trained on spaced languages falls back to characters — and a stacked vowel or tone mark often becomes a token of its own. You pay per fragment.
Trained on Thai, it segments close to real word boundaries and keeps a stacked cluster whole — fewer tokens in, more context per request, and a better answer out.
What that looks like at volume
Drag to set how much Thai your office or app actually puts through in a day. Token counts scale from the sentence above.
Late-2025 measurements, DataReportal Digital 2026: Thailand. Used for product sizing.
Residency and consent
Demonstrable, not asserted.
Anyone can put the word “sovereign” on a slide. These are the four places ThaiGPT+ makes it checkable from outside — in the product, not in a policy document.
The residency badge is one of the three places the kranok signature is used at all. It stays in permanent view in the institutional workspace.
"region": "th-bkk-1"Each API response carries the region that served it. Residency stops being a claim in a brochure and becomes a field your own systems can assert on.
off unless you turn it onProduct updates and evaluation-data use are two separate decisions. Neither is pre-ticked, both are reversible, and withdrawal propagates into the pipeline.
logged · exportableWorkspace activity is logged and exportable, so an institution can answer its own oversight questions — including under the PDPA — without asking us for a report.
egress: blockedAn institutional workspace can pin itself to a region, and the router declines rather than reaches for a model outside it. On-premise and air-gapped deployments are supported by the platform.
The collaboration
Three organisations, one platform.
ThaiGPT+ is not a re-skin and not a reseller agreement. Each partner owns a distinct layer, and the product only exists where the three meet.
XTNDTHAILANDXTND Thailand brings ThaiGPT+ to market. It owns the relationship with the people and institutions who use it — ministries, universities, hospitals, banks, schools and the public — and it carries the commercial model: baht-denominated pricing, prepaid credit through PromptPay and local bank rails, and free access for education.
- Market entry, distribution and institutional onboarding
- Baht pricing, prepaid credit, PromptPay and local bank rails
- The Thai contributor programme behind the training loop
XTNDDYNAMICSXTND Dynamics builds the product. Part of XTND Group, it takes the PrivateGPT-Asia platform and turns it into four shipping surfaces — a mobile app, a Windows and web workspace, a developer API and a training platform — then engineers the Thai layer that no general-purpose platform provides, including the router and the multimodal pipeline.
- Mobile, desktop and web applications on the platform
- Thai segmentation, normalisation, register, dialect and speech services
- The router, the multimodal pipeline and the consent ledger
PrivateGPTASIAPrivateGPT-Asia is the platform underneath, and the regional home of PrivateGPT. It is the complete private-AI application layer — retrieval with citations, document ingestion, tools, MCP, skills and text-to-SQL — behind a Claude-API-shaped interface, deployable in-country, on-premise or fully air-gapped, with no data leaving the environment it runs in.
- Retrieval, ingestion and citation-traceable answers
- Tools, MCP, skills and text-to-SQL over your own data
- Drop-in API compatibility and air-gap-capable deployment
Who owns what
Hover a partner above, or a layer below, to see where their work sits. ThaiGPT+ is the commercial platform layer — it deliberately does not own the models or the datacentre.
The application platform is PrivateGPT-Asia — the same private-AI layer deployed across the region, run in-country for Thailand.
Pre-release programme
Pick the way you want in.
Three cohorts are open. Choosing one sets up the form below — you can change it there.
Pre-release · Signup open now
Join the pre-release.
Three fields. Tell us who you are and where to write, and we'll email you when your invitation is ready.
- Three fields, nothing you have to look up
- Two consents, separable, neither pre-ticked
- A queue position back immediately
Works on 3G · ภาษาไทย / English