New in week 43

Unified OpenAI-compatible API in front of hundreds of LLMs, with routing, fallbacks and cost tracking.

Web Scraper API that returns structured data from public websites, with CAPTCHA and JavaScript rendering handled.

Web search, extract, monitor and research APIs for AI agents and applications.

Real-time web search API that returns ranked results as structured data, with domain, language and region filters.

Managed search database for AI agents and apps, covering semantic, sparse, full-text and hybrid queries.

Hosted platform for deploying and scaling Pipecat voice and multimodal agents, with autoscaling and observability.

Managed auth and 10,000+ prebuilt tools for AI agents, across 3,000+ APIs.

Context engine that indexes, retrieves and extracts entities from documents for agents.

All-in-one cloud platform to deploy, network, scale and monitor apps and agents.

Agentic document platform for parsing, extracting, splitting, classifying and editing documents.

Cloud platform for deploying apps, agents, databases and background jobs with managed infrastructure.

AI gateway and OpenAI-compatible router for 600+ models, with routing, failover, caching and observability.

Platform to build, test, deploy and monitor AI voice and chat agents, with telephony, prompts, tools and analytics.

Code execution API that lets LLM-generated code run in isolation and returns its output.

Isolated Linux devboxes for running AI agents and their code, with snapshots and reusable blueprints.

Inference cloud for large open models on SambaNova dataflow hardware, with per-token pricing.

Scraping API that handles proxies, browsers and CAPTCHAs for public websites, with structured data endpoints.

Web scraping, cloud browser, screenshot, extraction and crawler APIs under one API key, with managed proxies.

Web scraping API that handles proxies, headless Chrome and anti-bot defenses, returning JSON or Markdown extractions.

Real-time SERP API for scraping Google results as JSON, with pay-per-successful-search pricing.

Scrape Google and other search engines through an API that returns structured results.

Google Search API that returns SERP results in JSON, including organic results and a knowledge graph.

One API for open and commercial LLM and multimodal models, with pay-as-you-go pricing and fast inference.

Connects AI agents to thousands of MCP tools, handling auth, credentials and sessions.

Persistent, hardware-isolated Linux VMs for AI agents that hibernate when idle and wake quickly.

Open source vector database for AI apps, built on Postgres with pgvector and available self-hosted or managed.

Voice AI agents for enterprise phone calls, with in-house telephony and a Build, Evaluate, Launch, Learn workflow.

Web access API for AI agents with real-time search, extraction, crawling and research endpoints.

Voice AI agents on Telnyx carrier infrastructure, with telephony, speech, LLM inference and orchestration on one platform.

Cloud platform for running, fine-tuning and serving open-source AI models behind an OpenAI-compatible API.

Hybrid retrieval engine built on object storage, with semantic, keyword, dense, sparse and multi-vector search.

Enterprise AI gateway for 1000+ LLMs with governance, observability, guardrails and an MCP gateway.

Self-hosted MCP gateway and management platform with audit trails, DLP features and an AI kill-switch.

Search database for vector and full-text queries, built on object storage and available as a Python client.

Voice AI for customer calls, with Twilio handling speech-to-text and text-to-speech over a WebSocket API and your choice of LLM.

Serverless vector database with dense, sparse and hybrid indexes for semantic and keyword search.

Search API and agents for knowledge work, returning passages with links to filings, papers, trials and the web.

Developer platform for building voice AI agents that make and receive phone calls.

GPU cloud marketplace for renting and hosting GPU compute.

Enterprise AI platform for managed, grounded agents that answer from your data with citations.

Platform for deploying apps and AI agents, with an AI Gateway, sandboxes and fluid compute.

Managed gateway with one API key for 400+ models across providers, with fallbacks and no token markup.

Governed platform for every agent, model and tool a company runs, deployable in its own cloud.

Web Search API for AI applications, returning live web and news results with citations and timestamps.

Web data infrastructure for agents: Fetch, Extract, Crawl, Batch and Browser Sessions over API, CLI, MCP or SDK.

Context layer that unifies business data, documents and conversations into governed context for agents.

Fully managed Milvus vector database service with serverless and dedicated deployment options.

AI gateway on the same platform as your APIs, with multi-provider routing, per-team budgets and guardrails.

Web scraping API with automatic ban handling, browser rendering, sessions and extraction, plus a Python client.