# NativePort Docs

## Instructions for AI Agents

- For clean Markdown of any page, append `.md` to the page URL
- For section-specific indexes, append `/llms.txt` to any section URL
- For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nativeport.ai/_mcp/server

## Docs

- [NativePort](https://docs.nativeport.ai/overview.md): One API key and one prepaid balance reach 30+ search, scraping, browser, voice, document and model APIs through their own native endpoints.
- [Quickstart](https://docs.nativeport.ai/quickstart.md): Point an existing client at api.nativeport.ai, send your bearer token and get a real Google search back as JSON. Python, TypeScript and cURL shown.
- [Authentication](https://docs.nativeport.ai/authentication.md): Send a single NativePort token. The gateway holds each upstream credential server-side and attaches it per request, so no provider key touches your code.
- [Agent API](https://docs.nativeport.ai/agent-api.md): Four read-only routes: search the endpoint catalog by keyword, read the exact amount a call debits, fetch a ready-to-send request, and check a key's balance.
- [Set up with MCP](https://docs.nativeport.ai/mcp.md): Add api.nativeport.ai/mcp to your agent and sign in with your NativePort account, or use an API key. Four tools find an endpoint, inspect its price, run the call and report your balance.
- [Set up with CLI](https://docs.nativeport.ai/cli.md): npx nativeport stores your key once, then searches the catalog, prints what a call costs, runs it natively and reports your balance. Zero dependencies.
- [Inference API](https://docs.nativeport.ai/inference.md): Reach admitted OpenAI, Anthropic, xAI and Hugging Face models through one Chat Completions contract, JSON or streaming, with every rate in one catalog.
- [Anthropic](https://docs.nativeport.ai/anthropic.md): Claude's Messages API relayed as Anthropic serves it, for the models on the gateway's allowlist, with token counting free and usage billed from the response.
- [Apify](https://docs.nativeport.ai/apify.md): Start any Apify actor or saved task, wait for it or poll it, and fetch the dataset it produced. A run stays with the key that began it and is priced from its own reported cost.
- [Brave Search](https://docs.nativeport.ai/brave.md): Query Brave's own web index across the web, image, video, news, suggest and spellcheck verticals with your NativePort key. Charged per request.
- [Bright Data](https://docs.nativeport.ai/brightdata.md): Bright Data's Web Unlocker and SERP API on one direct endpoint, your NativePort token standing in for theirs. Each request draws on the same prepaid balance.
- [Browserbase](https://docs.nativeport.ai/browserbase.md): Create a Browserbase session, update a running one or read its details through the gateway, then drive the browser over Browserbase's own connection.
- [Browserless](https://docs.nativeport.ai/browserless.md): Four fixed browser actions: render a screenshot or a PDF, return the page's HTML, or pull fields out with CSS selectors. Allowlisted fields, priced per call.
- [Crawlbase](https://docs.nativeport.ai/crawlbase.md): Two routes decide which Crawlbase token the gateway injects: ordinary HTML fetches, or headless-browser fetches for pages that need JavaScript.
- [DataForSEO](https://docs.nativeport.ai/dataforseo.md): The instant-response DataForSEO endpoints on one route: Google SERPs, keyword volume and on-page audits, each billed from the cost DataForSEO reports itself.
- [ElevenLabs](https://docs.nativeport.ai/elevenlabs.md): Generate audio from text and browse the voice and model catalog on one gateway route, with ElevenLabs' own request and response shapes kept intact.
- [Exa](https://docs.nativeport.ai/exa.md): Search Exa's neural index, pull page contents, find similar pages or ask for a cited answer. Each call is billed from the dollar cost Exa reports for it.
- [Firecrawl](https://docs.nativeport.ai/firecrawl.md): Turn a URL into clean markdown, list a site's links, or start a crawl, batch or AI extraction and poll it by id. Jobs are billed from the credits they report.
- [Fish Audio](https://docs.nativeport.ai/fishaudio.md): Text to speech with reference-clip voice cloning, transcription and voice design on four fixed routes. Speech is metered from the bytes of text you send.
- [Grok](https://docs.nativeport.ai/grok.md): xAI's Grok text models through the gateway: chat completions, deferred completions, Responses and tokenization, billed from the usage xAI reports per call.
- [Hugging Face](https://docs.nativeport.ai/huggingface.md): One chat-completions endpoint over Hugging Face's Inference Providers, each model pinned to a backing provider so its per-token rate is known first.
- [Jina](https://docs.nativeport.ai/jina.md): Read a URL as clean markdown, search, embed, rerank or classify with one key. Every Jina response reports the tokens it spent, and those set the price.
- [Linkup](https://docs.nativeport.ai/linkup.md): Linkup's Search API through one gateway route, standard or deep, sources attached to every answer. One key, a charge per query, no plan to keep alive.
- [LlamaParse](https://docs.nativeport.ai/llamaparse.md): Start a parse, poll the job by id, and get page text or markdown at one of four tiers. The page bound you declare settles to what the parse really used.
- [Mistral](https://docs.nativeport.ai/mistral.md): Turn a PDF or image into page-level markdown and pull named fields out with a JSON schema on the same call. Pages are declared up front, so the price is too.
- [OpenAI](https://docs.nativeport.ai/openai.md): OpenAI's native routes for admitted models: Responses, Chat Completions, embeddings and moderation, plus the files and vector stores your own key created.
- [Oxylabs](https://docs.nativeport.ai/oxylabs.md): Oxylabs' Web Scraper API in realtime mode on one route, with target, geo and rendering set in the request body. One key, per-request charges, no commitment.
- [Parallel](https://docs.nativeport.ai/parallel.md): Parallel's Search API behind the gateway, base and pro processors on the same path, results shaped for agent consumption. Pay per search from one balance.
- [ScraperAPI](https://docs.nativeport.ai/scraperapi.md): One request returns the page; add render=true for JavaScript sites or a premium proxy for hard targets. Each attempt is billed from the credits in a header.
- [Scrapfly](https://docs.nativeport.ai/scrapfly.md): Fetch protected pages using Scrapfly's ASP bypass and browser rendering. Each response carries the credits it consumed, and that number sets the price.
- [ScrapingBee](https://docs.nativeport.ai/scrapingbee.md): Scrape with JavaScript rendering, CSS extraction rules or AI extraction on a single route. Each call is billed from the credit cost ScrapingBee returns.
- [SearchAPI.io](https://docs.nativeport.ai/searchapi.md): Pass engine and the rest of the query string exactly as SearchAPI.io documents it; the gateway supplies the api_key and debits one balance per search.
- [SerpApi](https://docs.nativeport.ai/serpapi.md): One GET reaches SerpApi's engine roster, from Google and Bing to Amazon and YouTube, with every engine parameter yours to set. No SerpApi plan to buy.
- [Serper](https://docs.nativeport.ai/serper.md): Google web, news, images, videos, places, maps, scholar, patents and shopping results as JSON, plus a page-text scraper, behind a single bearer token.
- [Spider](https://docs.nativeport.ai/spider.md): Spider's scrape, crawl, search and link-extraction actions on one route. Every response states its per-page dollar cost, and the charge is priced from it.
- [Steel](https://docs.nativeport.ai/steel.md): Steel's Browser Tools on three fixed routes: page content, a rendered screenshot, or a PDF. Each takes a closed set of fields and is billed on its own.
- [Tavily](https://docs.nativeport.ai/tavily.md): Tavily's answer-oriented search plus its extract, crawl and map endpoints on one route, each response reporting the credits it used, which set the price.
- [TypeSafe](https://docs.nativeport.ai/typesafe.md): Send state and a map of typed questions — yes/no, pick-one, rate-against-levels — and get answers your code can branch on, each with a probability distribution and a confidence. Input tokens only.
- [You.com](https://docs.nativeport.ai/youcom.md): Send a query to You.com's own index through one route and get its ranked results back unchanged. No You.com account, no minimum, a charge per request.
- [ZenRows](https://docs.nativeport.ai/zenrows.md): ZenRows' Universal Scraper API with premium proxies and JavaScript rendering as plain query parameters. Each call is billed from the cost ZenRows reports.
- [Zyte](https://docs.nativeport.ai/zyte.md): Zyte API on one route, from plain HTTP fetches to browser rendering, screenshots and automatic product extraction. Charged per request, no tier to pick.
- [API reference](https://docs.nativeport.ai/api-reference.md): Which prefix reaches which upstream, where the credential is injected, which routes relay a response untouched, and how a call meters your balance.
- [Changelog](https://docs.nativeport.ai/changelog/llms.txt)

## API Docs

- API Reference [Query a Brave Search vertical](https://docs.nativeport.ai/api-reference/api-reference/brave-search.md)
- API Reference > Catalog [Model Context Protocol endpoint (Streamable HTTP, stateless)](https://docs.nativeport.ai/api-reference/api-reference/catalog/mcp.md)
- API Reference > Catalog [List the endpoint catalog, or rank it by keywords](https://docs.nativeport.ai/api-reference/api-reference/catalog/list.md)
- API Reference > Catalog [One catalog entry with a ready-to-send request](https://docs.nativeport.ai/api-reference/api-reference/catalog/get.md)
- API Reference > Catalog [The agent skill, generated from the catalog](https://docs.nativeport.ai/api-reference/api-reference/catalog/skill-markdown.md)
- API Reference > Catalog [Balance and status of the calling key](https://docs.nativeport.ai/api-reference/api-reference/catalog/account-get.md)
- API Reference > Serper [Search Serper, query-string form (alias of /serper/search)](https://docs.nativeport.ai/api-reference/api-reference/serper/search-alias.md)
- API Reference > Serper [Search Serper, JSON-body form (alias of /serper/search)](https://docs.nativeport.ai/api-reference/api-reference/serper/search-alias-post.md)
- API Reference > Serper [Invoke a Serper endpoint (query-string form)](https://docs.nativeport.ai/api-reference/api-reference/serper/endpoint-get.md)
- API Reference > Serper [Invoke a Serper endpoint (JSON-body form)](https://docs.nativeport.ai/api-reference/api-reference/serper/endpoint-post.md)
- API Reference > Scraper API [Scrape a target URL](https://docs.nativeport.ai/api-reference/api-reference/scraper-api/scrape.md)
- API Reference > Scraper API [Form submission passthrough (POST)](https://docs.nativeport.ai/api-reference/api-reference/scraper-api/post.md)
- API Reference > Scraper API [Form submission passthrough (PUT)](https://docs.nativeport.ai/api-reference/api-reference/scraper-api/put.md)
- API Reference > Serp API [Run a SerpApi search](https://docs.nativeport.ai/api-reference/api-reference/serp-api/search.md)
- API Reference > Eleven Labs [Relay an ElevenLabs GET](https://docs.nativeport.ai/api-reference/api-reference/eleven-labs/get.md)
- API Reference > Eleven Labs [Relay an ElevenLabs POST](https://docs.nativeport.ai/api-reference/api-reference/eleven-labs/post.md)
- API Reference > Search API Io [Run a SearchAPI.io search](https://docs.nativeport.ai/api-reference/api-reference/search-api-io/searchapi-search.md)
- API Reference > You Com [Run a You.com search](https://docs.nativeport.ai/api-reference/api-reference/you-com/youcom-search.md)
- API Reference > Data for Seo [Relay a DataForSEO POST](https://docs.nativeport.ai/api-reference/api-reference/data-for-seo/post.md)
- API Reference > Tavily [Invoke a Tavily endpoint](https://docs.nativeport.ai/api-reference/api-reference/tavily/proxy.md)
- API Reference > Exa [Invoke an Exa endpoint](https://docs.nativeport.ai/api-reference/api-reference/exa/proxy.md)
- API Reference > Linkup [Run a Linkup search](https://docs.nativeport.ai/api-reference/api-reference/linkup/search.md)
- API Reference > Parallel [Run a Parallel search](https://docs.nativeport.ai/api-reference/api-reference/parallel/search.md)
- API Reference > Type Safe [Answer typed questions about supplied state](https://docs.nativeport.ai/api-reference/api-reference/type-safe/system-one.md)
- API Reference > Jina [Relay a Jina GET](https://docs.nativeport.ai/api-reference/api-reference/jina/get.md)
- API Reference > Jina [Relay a Jina POST](https://docs.nativeport.ai/api-reference/api-reference/jina/post.md)
- API Reference > Firecrawl [Relay a Firecrawl GET](https://docs.nativeport.ai/api-reference/api-reference/firecrawl/get.md)
- API Reference > Firecrawl [Relay a Firecrawl POST](https://docs.nativeport.ai/api-reference/api-reference/firecrawl/post.md)
- API Reference > Firecrawl [Relay a Firecrawl DELETE](https://docs.nativeport.ai/api-reference/api-reference/firecrawl/delete.md)
- API Reference > Scraping Bee [Scrape a page with ScrapingBee](https://docs.nativeport.ai/api-reference/api-reference/scraping-bee/scrape.md)
- API Reference > Scraping Bee [Scrape a POST target with ScrapingBee](https://docs.nativeport.ai/api-reference/api-reference/scraping-bee/post.md)
- API Reference > Scrapfly [Scrape a page with Scrapfly](https://docs.nativeport.ai/api-reference/api-reference/scrapfly/scrape.md)
- API Reference > Scrapfly [Scrape a POST target with Scrapfly](https://docs.nativeport.ai/api-reference/api-reference/scrapfly/post.md)
- API Reference > Scrapfly [PUT through to the target](https://docs.nativeport.ai/api-reference/api-reference/scrapfly/put.md)
- API Reference > Scrapfly [PATCH through to the target](https://docs.nativeport.ai/api-reference/api-reference/scrapfly/patch.md)
- API Reference > Scrapfly [HEAD through to the target](https://docs.nativeport.ai/api-reference/api-reference/scrapfly/head.md)
- API Reference > Zen Rows [Scrape a page with ZenRows](https://docs.nativeport.ai/api-reference/api-reference/zen-rows/scrape.md)
- API Reference > Zen Rows [Scrape a POST target with ZenRows](https://docs.nativeport.ai/api-reference/api-reference/zen-rows/post.md)
- API Reference > Crawlbase [Crawl a page (Normal token)](https://docs.nativeport.ai/api-reference/api-reference/crawlbase/scrape.md)
- API Reference > Crawlbase [POST through to the target site (Normal token)](https://docs.nativeport.ai/api-reference/api-reference/crawlbase/post.md)
- API Reference > Crawlbase [Crawl a page (JavaScript token)](https://docs.nativeport.ai/api-reference/api-reference/crawlbase/js-scrape.md)
- API Reference > Crawlbase [POST through to the target site (JavaScript token)](https://docs.nativeport.ai/api-reference/api-reference/crawlbase/js-post.md)
- API Reference > Oxylabs [Scrape on Oxylabs' realtime endpoint](https://docs.nativeport.ai/api-reference/api-reference/oxylabs/proxy.md)
- API Reference > Bright Data [Send a Web Unlocker / SERP request](https://docs.nativeport.ai/api-reference/api-reference/bright-data/brightdata-proxy.md)
- API Reference > Spider [Relay a Spider POST](https://docs.nativeport.ai/api-reference/api-reference/spider/post.md)
- API Reference > Apify [Start an asynchronous actor run](https://docs.nativeport.ai/api-reference/api-reference/apify/start-actor-run.md)
- API Reference > Apify [Start an asynchronous saved-task run](https://docs.nativeport.ai/api-reference/api-reference/apify/start-task-run.md)
- API Reference > Apify [Poll an asynchronous run](https://docs.nativeport.ai/api-reference/api-reference/apify/get-run.md)
- API Reference > Apify [Abort an asynchronous run](https://docs.nativeport.ai/api-reference/api-reference/apify/abort-run.md)
- API Reference > Apify [Read the items an asynchronous run produced](https://docs.nativeport.ai/api-reference/api-reference/apify/get-dataset-items.md)
- API Reference > Browserbase [Relay a Browserbase GET](https://docs.nativeport.ai/api-reference/api-reference/browserbase/get.md)
- API Reference > Browserbase [Relay a Browserbase POST](https://docs.nativeport.ai/api-reference/api-reference/browserbase/post.md)
- API Reference > Zyte [Scrape or extract with Zyte](https://docs.nativeport.ai/api-reference/api-reference/zyte/proxy.md)
- API Reference > Fish Audio [Synthesize speech (Text to Speech)](https://docs.nativeport.ai/api-reference/api-reference/fish-audio/fishaudio-tts.md)
- API Reference > Fish Audio [Synthesize speech with word-level timestamps (streaming)](https://docs.nativeport.ai/api-reference/api-reference/fish-audio/fishaudio-tts-stream-with-timestamp.md)
- API Reference > Fish Audio [Transcribe audio (Speech to Text)](https://docs.nativeport.ai/api-reference/api-reference/fish-audio/fishaudio-asr.md)
- API Reference > Fish Audio [Generate synthetic voice candidates (Voice Design)](https://docs.nativeport.ai/api-reference/api-reference/fish-audio/fishaudio-voice-design.md)
- API Reference > Browserless [Capture a screenshot with Browserless](https://docs.nativeport.ai/api-reference/api-reference/browserless/screenshot.md)
- API Reference > Browserless [Render a PDF with Browserless](https://docs.nativeport.ai/api-reference/api-reference/browserless/pdf.md)
- API Reference > Browserless [Fetch fully rendered HTML](https://docs.nativeport.ai/api-reference/api-reference/browserless/content.md)
- API Reference > Browserless [Extract structured data with CSS selectors](https://docs.nativeport.ai/api-reference/api-reference/browserless/scrape.md)
- API Reference > Steel [Scrape a page with Steel](https://docs.nativeport.ai/api-reference/api-reference/steel/scrape.md)
- API Reference > Steel [Capture a screenshot with Steel](https://docs.nativeport.ai/api-reference/api-reference/steel/screenshot.md)
- API Reference > Steel [Render a PDF with Steel](https://docs.nativeport.ai/api-reference/api-reference/steel/pdf.md)
- API Reference > Mistral [OCR a document or image (Document AI)](https://docs.nativeport.ai/api-reference/api-reference/mistral/ocr.md)
- API Reference > Llama Parse [Start a document parse](https://docs.nativeport.ai/api-reference/api-reference/llama-parse/create-parse.md)
- API Reference > Llama Parse [Read a parse job](https://docs.nativeport.ai/api-reference/api-reference/llama-parse/get-parse.md)
- API Reference > Open AI [OpenAI's own job-completion webhook (not client-facing)](https://docs.nativeport.ai/api-reference/api-reference/open-ai/webhook.md)
- API Reference > Open AI [Relay an OpenAI GET: models, files, vector stores, batches](https://docs.nativeport.ai/api-reference/api-reference/open-ai/get.md)
- API Reference > Open AI [Run OpenAI inference, or create a file, batch or job](https://docs.nativeport.ai/api-reference/api-reference/open-ai/post.md)
- API Reference > Open AI [Delete a file or vector store you own](https://docs.nativeport.ai/api-reference/api-reference/open-ai/delete.md)
- API Reference > Anthropic [Relay an Anthropic GET (models, or your own files/batches)](https://docs.nativeport.ai/api-reference/api-reference/anthropic/get.md)
- API Reference > Anthropic [Send a Messages request, count tokens, create a file](https://docs.nativeport.ai/api-reference/api-reference/anthropic/post.md)
- API Reference > Anthropic [Delete a file you own](https://docs.nativeport.ai/api-reference/api-reference/anthropic/delete.md)
- API Reference > Grok [Relay a Grok GET: models, responses, files, batches](https://docs.nativeport.ai/api-reference/api-reference/grok/get.md)
- API Reference > Grok [Run inference, tokenize, or create a file/batch](https://docs.nativeport.ai/api-reference/api-reference/grok/post.md)
- API Reference > Grok [Delete a stored response or file you own](https://docs.nativeport.ai/api-reference/api-reference/grok/delete.md)
- API Reference > Hugging Face [List the catalog, or look up one model](https://docs.nativeport.ai/api-reference/api-reference/hugging-face/huggingface-get.md)
- API Reference > Hugging Face [Run chat completion inference](https://docs.nativeport.ai/api-reference/api-reference/hugging-face/huggingface-post.md)
- API Reference > Inference [Run chat inference against any canonical model](https://docs.nativeport.ai/api-reference/api-reference/inference/chat-completions.md)
- API Reference > Inference [List every model your key can reach](https://docs.nativeport.ai/api-reference/api-reference/inference/list-models.md)
- API Reference > Inference [Look up one canonical model](https://docs.nativeport.ai/api-reference/api-reference/inference/get-model.md)

## OpenAPI Specification

The raw OpenAPI 3.1 specification for this API is available at:
- [OpenAPI JSON](https://docs.nativeport.ai/openapi.json)
- [OpenAPI YAML](https://docs.nativeport.ai/openapi.yaml)