Feature
Function Calling & Tool Use
Structured tool definitions LLMs can invoke.
18 providers
249 APIs
17 declared variants
Capabilities are exposed as tool or function definitions an LLM can call with structured arguments. The mechanism behind most agentic integrations today.
18 API providers on the APIs.io network offer function calling & tool use. The highest-rated are NVIDIA NIM, Vapi, Anthropic, Exa, Claude.
Providers
Ranked by API Evangelist rating — Exemplar and Strong are expanded by default.
Exemplar 7 Complete, well-documented, and agent-ready
NVIDIA NIM
NVIDIA NIM (NVIDIA Inference Microservices) is a catalog of GPU-accelerated, containerized AI inference mic...
Vapi
Vapi is a San Francisco-based voice AI platform that lets developers build real-time, low-latency voice age...
Anthropic
Anthropic is an AI safety company and creator of the Claude family of large language models (Opus, Sonnet, ...
Exa
Exa is a web search API and AI research platform built specifically for LLMs and agents — semantic and keyw...
Claude
Anthropic's Claude AI assistant API for natural language processing and conversation.
OpenAI
APIs for accessing OpenAI's artificial intelligence models including GPT, DALL-E, Whisper, and Embeddings.
Mistral AI
Mistral AI provides state-of-the-art large language models and AI APIs for developers and enterprises.
Strong 5 Solid coverage with minor gaps
OpenRouter
OpenRouter is an API platform that provides unified access to multiple AI language models through a single ...
Hyperbolic
Hyperbolic is an open-access AI cloud and decentralized GPU marketplace serving 200,000+ builders with affo...
Perplexity
Perplexity AI is an answer engine that delivers accurate answers to complex questions using large language ...
Lakera
Lakera is an AI-native security platform that protects GenAI applications, agents, and workforces from prom...
arcade-dev
Arcade.dev (formerly Arcade AI) is the MCP runtime for production AI agents — a platform that lets agents s...
Developing 4 Usable, with meaningful gaps to close
Gemini
Google's Gemini API provides access to state-of-the-art generative AI models for text generation, multimoda...
Lunar Energy
Lunar Energy is a Mountain View, California-based residential clean-energy company founded in August 2020 b...
cohere
Generates a text response to a user message and streams it down, token by token.
Docling
Docling is an open-source toolkit for parsing diverse document formats — PDF, DOCX, PPTX, XLSX, HTML, image...
Thin 1 Limited public surface area
Minimal 1 Almost no public developer surface
What Providers Actually Declared
This feature is a canonical term. These are the free-text strings
providers wrote in their own apis.yml that map onto it.
AI Agent Security — runtime protection for autonomous agents and tool useFunction CallingFunction calling and tool useFunction calling, JSON mode, tool use, and structured outputs across compatible LLMsMCP runtime engine for secure, multi-user AI agent tool callingMCP server (docling-mcp) exposes parsing as agent tools for Claude, Cursor, Gemini and other clientsMessages API with text, vision, tool use, extended thinking, streaming, structured outputsRemote MCP server exposes the Customer API as agent toolsStreaming, tool/function calling, structured JSON output, vision input on supported modelsStructured Outputs for JSON-schema-constrained extraction from callsStructured output (JSON schema)Structured outputs with web-grounded citationsTool UseTool use / function calling (model-dependent)Tool use and function callingTravel Agent ToolsVision, tool use, structured outputs, and function calling
Scroll for all 17