Segmenter API
Explore the API. Make a real request. Use the code in your application.
Tokenizer
tokenizerChoose the tokenizer used for counting and splitting.
Return tokens
return_tokensInclude token strings in the response.
Return chunks
return_chunksSplit text at semantic boundaries.
Maximum chunk length
max_chunk_lengthMaximum number of characters per chunk.
curl 'https://chatsax.com/v1/segment' \
-X 'POST' \
-H 'Content-Type: application/json' \
-H "Authorization: Bearer $CHATSAX_API_KEY" \
--data-binary '{
"content": "Chatsax is the search foundation for agents. Read the web, generate embeddings, and rerank results with one API.\n\n智能体可以使用相同的 API 搜索和理解信息。",
"tokenizer": "cl100k_base",
"return_tokens": true,
"return_chunks": true,
"max_chunk_length": 1000
}'Not connectedMake context manageable.
Inspect token counts and divide longer content into chunks before retrieval or model calls.
Token visibility
Choose a tokenizer and inspect token IDs when needed.
Document chunks
Split text using structural cues and a chunk-length setting.
Targeted slices
Request a head or tail token slice without using both at once.
From playground to production.
Use the same request contract in the browser, an HTTP client, or your agent tools. A Chatsax key keeps access and usage separate from the upstream provider account.
Usage & access
Know what your requests use.
Chatsax currently uses invitation-based access. Request limits are assigned to each key; provider usage is recorded when available. No public checkout or standard price plan is offered here.
Your limits
View the current key’s scopes, minute limit, and daily request limit in the dashboard.
Recorded usage
Inspect requests, response status, latency, and available token counts.
Provider costs
Different services count usage differently. A cancelled or long-running request may still consume upstream resources.
Frequently asked questions
Are characters the same as tokens?
No. Counts depend on the tokenizer and language. Chunk length and model context limits are different controls.
Does chunking generate embeddings?
No. Send the resulting chunks to the embedding endpoint as a separate step.
Is this late chunking?
No. Late chunking pools contextual token embeddings; this endpoint handles segmentation and tokenization.
Is Chatsax operated by Jina AI?
Chatsax is independently operated. Jina supplies the current underlying APIs; model names and source links identify that provider.