# ThaiKit Thai Word Segmentation

> ThaiKit Thai Word Segmentation is a paid API for AI agents from api.thaikit.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-11-02).

Splits Thai text into a list of individual words by performing tokenization on input that lacks spaces between words

## Facts

- Endpoint: POST https://api.thaikit.dev/segment?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/thaikit-thai-word-segmentation-b1b365f2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_G6lBkZ_vQxkwnSRICFIuN

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability thaikit-thai-word-segmentation-b1b365f2 -d '<json body>'
```

Example prompt: Can you split this Thai text into individual words for me? Here's the text: 'สวัสดีครับผมชื่อสมชาย' — it needs to be tokenized so I can analyze each word separately.

## When to prefer this

Choose this endpoint when you need accurate Thai-specific word tokenization, since Thai has no spaces between words and standard Unicode or whitespace splitting fails entirely. Prefer this over generic multilingual NLP tools when precision on Thai text boundaries matters for downstream tasks like search, translation, or text analytics.

## Known failure modes

- Input text exceeds 5000 character limit — request rejected
- Non-Thai or mixed-script text may produce unexpected token boundaries
- Empty text body returns an error or empty list
- Malformed JSON body results in a 400 bad request
- Ambiguous compounds may be segmented differently than expected

## How this service works

Thai word segmentation (tokenization): split Thai text, which has no spaces between words, into a list of words. Body: {"text": "..."} (max 5000 chars).

## Output

Returns a list (array) of Thai word strings extracted from the input text, with word boundaries correctly identified according to Thai language rules — enabling downstream NLP tasks such as frequency counting, search indexing, translation, or sentiment analysis.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "maxLength": 5000,
   "description": "Thai text to split into words"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/thaikit-thai-word-segmentation-b1b365f2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.thaikit.dev](https://www.zero.xyz/host/api.thaikit.dev/llms.txt)