{"uid":"cap_aktbiJqbXS9_fXSke6jJ_","slug":"defi-intel-agent-gateway-semantic-text-chunker-e96f61e3","name":"DeFi Intel Agent Gateway – Semantic Text Chunker","description":"Chunk long text for embedding pipelines by paragraphs/sentences, honoring a token budget. Deterministic, no API calls. Returns chunks with char/token counts. — $0.0015 USDC/call on Base. Pay-per-call via x402 — no API key, no account. Free samples daily.","url":"https://defi-intel-agent-gateway.gg-neo15.workers.dev/v1/text/semantic-chunker","method":"POST","headers":{},"bodySchema":null,"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.0015","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":"$0.0015/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0015","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0015","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_U0Iym54L1qSa8BSfj4lEA","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.0015","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Splits long text into paragraph- or sentence-level chunks that fit within a token budget, returning each chunk with character and token counts — no external API calls, fully deterministic.","exampleAgentPrompt":"Take this 10,000-word research report and chunk it by paragraph, keeping each chunk under 512 tokens, so I can embed it into my vector database.","exampleUseCases":[{"title":"RAG pipeline document ingestion","prompt":"I have a long PDF transcript I've converted to text — can you split it into sentence-level chunks, each under 256 tokens, so I can embed and store them for retrieval-augmented generation?"},{"title":"Embedding batch preparation for blog archive","prompt":"I need to chunk all these blog posts by paragraph, with a 512-token budget per chunk, so I can run them through an embedding model and index them for semantic search."},{"title":"LLM context window fitting","prompt":"This legal document is way too long to fit in one LLM call — can you break it into paragraph chunks that each stay under 1024 tokens so I can process them one at a time?"}],"resultDescription":"An array of text chunks, each accompanied by its character count and token count, segmented by the chosen method (paragraph or sentence) and constrained to the specified token budget. No external calls are made; output is fully deterministic for the same input.","failureModes":["Missing or empty input text returns an error","Invalid or unsupported chunking method returns a validation error","Token budget set to zero or negative value may cause empty or error response","Extremely short text with budget larger than the full text returns a single chunk","Malformed JSON body returns a 400-level error","Payment not fulfilled via x402 returns a 402 Payment Required response"],"whenToPreferThis":"Choose this endpoint when you need a fast, deterministic, cost-predictable way to split text for embedding pipelines without relying on an external LLM or tokenizer service. It is ideal for RAG ingestion workflows, vector database preparation, and any pipeline where reproducibility matters. Prefer it over LLM-based chunkers when you want no randomness and over local libraries when you need a simple pay-per-call hosted API with no setup.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:45:39.109Z","isFirstParty":false}