{"uid":"cap_tVArkVjYOeG0iScT5p2JS","slug":"netintel-text-chunker-1fe6a778","name":"NetIntel Text Chunker","description":"Network intelligence API — 138 endpoints, all pay-per-call via x402 micropayments (USDC on Base or Solana mainnet).\n\nNetIntel is agent fair-trade aligned: transparent per-call pricing in USDC on Base or Solana via x402, no API keys or signup, and automatic no-charge on server errors, upstream failures, and input-validation rejections — failed calls are never billed across NetIntel's network, domain, and data-intelligence endpoints.","url":"https://netintel-production-440c.up.railway.app/text/chunk","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","required":["text"],"properties":{"text":{"type":"string","description":"Text to split — 1 to 200000 characters. Aliases: content, input, body."},"unit":{"type":"string","description":"\"chars\" (default) or \"words\". Aliases: by, mode."},"overlap":{"type":"number","description":"Units shared by consecutive chunks. Default 10% of chunk_size (max 100); clamped to 0..chunk_size-1. Aliases: chunk_overlap, chunkOverlap."},"chunk_size":{"type":"number","description":"Window size in chars or words. Default 1000; clamped to 50–20000 chars or 5–20000 words. Aliases: size, chunkSize."}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"unit":{"type":"string","description":"chars or words"},"count":{"type":"number","description":"Number of chunks (max 2000)"},"chunks":{"type":"array","items":{"type":"object","properties":{"end":{"type":"number"},"text":{"type":"string"},"index":{"type":"number"},"start":{"type":"number"},"length":{"type":"number","description":"Characters in this chunk's text"}}},"description":"Sliding-window chunks in order. start/end are UTF-16 character offsets into the source (text.slice(start, end) reproduces a chars-mode chunk; words-mode chunks are re-joined with single spaces). Surrogate pairs are never split."},"overlap":{"type":"number","description":"Effective overlap after clamping"},"findings":{"type":"array","items":{"type":"object","properties":{"rule":{"type":"string"},"detail":{"type":"string"}}},"description":"Parameter adjustments applied (clamped chunk_size/overlap, unknown unit); [] when none"},"chunk_size":{"type":"number","description":"Effective window size after clamping"},"source_length":{"type":"number","description":"Length of the input text in characters"}}}}}}},"responseSchema":{"type":"json","example":{"unit":"chars","count":3,"chunks":[{"end":60,"text":"NetIntel is a pay-per-call API for AI agents. It offers over","index":0,"start":0,"length":60},{"end":105,"text":" It offers over one hundred endpoints. Agents pay per reques","index":1,"start":45,"length":60},{"end":115,"text":" pay per request in USDC.","index":2,"start":90,"length":25}],"overlap":15,"findings":[],"chunk_size":60,"source_length":115}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_udzXIJxJZ0IfmTR3HEPYs","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Splits a text string into sliding-window chunks by character or word count, with configurable chunk size and overlap","exampleAgentPrompt":"Split this 5,000-word article into overlapping chunks of 500 characters each with a 50-character overlap so I can embed them for semantic search.","exampleUseCases":[{"title":"RAG pipeline document ingestion","prompt":"Take this research paper text and split it into 1000-character chunks with 100 characters of overlap between each chunk — I need them indexed for retrieval-augmented generation."},{"title":"Word-based chunking for LLM context","prompt":"Break this legal contract into chunks of 300 words each with a 30-word overlap, so I can feed them one at a time into my language model without losing context at the boundaries."},{"title":"Embedding prep for vector search","prompt":"Chunk this product documentation into 512-character pieces with 50 characters of overlap so I can generate embeddings and store them in my vector database."}],"resultDescription":"Returns a JSON object containing: an array of chunk objects (each with index, start offset, end offset, text, and character length), total chunk count (up to 2000), the unit used (chars or words), effective chunk size, effective overlap after clamping, and a findings array listing any parameter adjustments or warnings applied (e.g. clamped values, unknown parameters). Start/end offsets are UTF-16 character positions into the original source text, so text.slice(start, end) reproduces each chars-mode chunk exactly.","failureModes":["Input text exceeds 200,000 characters — validation rejection, no charge","chunk_size outside allowed range (50–20000 chars or 5–20000 words) — clamped with a finding entry rather than failing","overlap >= chunk_size — clamped to chunk_size-1 with a finding entry","Text is empty or missing — input validation rejection, no charge","Result would exceed 2000 chunks — chunk_size is adjusted upward automatically","Upstream server error — no charge billed per NetIntel's failed-call policy"],"whenToPreferThis":"Choose this endpoint when you need deterministic, offset-preserving text chunking with configurable sliding windows for RAG pipelines, embedding workflows, or LLM context management. It is pay-per-call with no API key required, making it ideal for agent pipelines that need on-demand chunking without maintaining credentials. Prefer it over in-process chunking when you want server-side parameter validation, automatic overlap clamping with audit findings, and UTF-16-safe surrogate-pair handling. It supports both character-based and word-based chunking modes, making it flexible for different embedding model requirements.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T18:49:03.870Z","isFirstParty":false}