Do I need a separate search provider account?

No. The Web Search API uses your existing Telnyx API key as a Bearer token. One account covers search, voice, messaging, and inference.

What endpoints are available?

POST /v1/web_search for search results, POST /v1/contents for page extraction, POST /v1/research for cited answers, and GET /v1/research/:task_id for polling background research tasks.

How does background research work?

Set background: true on POST /v1/research. The response returns a task_id. Poll GET /v1/research/:task_id until status is complete, then read the cited answer.

What formats does /v1/contents return?

html, markdown, or metadata. Pass formats as an array. Set max_age (in seconds) to skip re-crawling pages cached within that window.

Can I scope search to specific domains?

Yes. Use include_domains to allow only listed domains, or exclude_domains to block them. Combining both returns 400.

What does livecrawl do?

When enabled, /v1/web_search fetches fresh page content for each result instead of returning cached snippets. Useful for time-sensitive queries.

How much does it cost?

$5 per 1,000 calls. Billed through your existing Telnyx account.

Which provider backs the search?

Telnyx owns the API surface and the backend is swappable without client-side updates.

Average 1,027ms per /v1/web_search call in our benchmark against Tavily, DuckDuckGo, and Brave. Zero errors across the test set.

Agent Platform

Web Search API for AI Agents

Search the web, fetch page content, and run deep research through one API. Same Telnyx key you use for voice, messaging, and inference. No separate search provider account.

Get started Read the docs

Web search API flow: query through POST /v1/web_search to structured results

USE CASES

What teams build with it

Voice agents, research agents, and competitive intelligence all need the same primitives.

Voice AI agents
Give your voice agent live web access. Look up flight status, check store hours, pull current prices, all in the same call.
Research agents
Run multi-source research with citations. Background mode handles long tasks; poll the task_id when ready.
Competitive intelligence
Track competitor pages, pricing, and announcements. Use include_domains to scope, freshness to control recrawl.
Content enrichment
Fetch URLs and convert to clean Markdown for RAG pipelines, summaries, or downstream LLM calls.

ENDPOINTS

Four endpoints, one auth header

Every endpoint uses your existing Telnyx API key as a Bearer token.

POST /v1/web_search
Search the web. Params: query, count (1-100), country, safesearch, freshness, include_domains, exclude_domains, livecrawl.
POST /v1/contents
Fetch page content. Params: urls (array, max 20), formats (html|markdown|metadata), crawl_timeout, max_age.
POST /v1/research
Run a research task. Params: query, research_effort (lite|standard|deep), max_sources, background (boolean).
GET /v1/research/:task_id
Poll a background research task. Returns status and the cited answer when ready.

HOW IT WORKS

From query to cited answer

Search, fetch, and research through the same Bearer token you already use.

EXPLORE DEV DOCS

# 1. Web search with snippets
curl -X POST "https://web-search.telnyx.com/v1/web_search" \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "latest Telnyx voice AI pricing",
    "count": 5,
    "country": "US",
    "safesearch": "moderate"
  }'

# 2. Fetch page content
curl -X POST "https://web-search.telnyx.com/v1/contents" \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "urls": ["https://telnyx.com/pricing/voice-ai-agents"],
    "formats": ["markdown"]
  }'

# 3. Deep research with citations
curl -X POST "https://web-search.telnyx.com/v1/research" \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "Compare Telnyx vs Twilio voice API pricing in 2026",
    "research_effort": "standard",
    "max_sources": 10
  }'

PRODUCTS

One platform for agent infrastructure.

Web Search API is one part of a full platform for agent infrastructure. Same API key, same network, same bill.

See all products

Inference
Run open-weight and proprietary models on Telnyx GPUs. No separate API key, no separate bill.
Learn more
Voice AI Agents
Build and deploy low-latency Voice AI agents in minutes on a full-stack, conversational AI platform.
Learn more
Functions
Deploy containerized code to the edge with one command. Any language, any runtime, bindings to storage and the Telnyx API.
Learn more
Cloud Storage
Discover low-latency, cost-effective storage for your AI applications. Store data and embeddings in one place.
Learn more