Feature

OpenAI-Compatible API

Drop-in compatibility with the OpenAI request shape.

21 providers 268 APIs 18 declared variants

The endpoint mirrors the OpenAI API surface, so existing clients and frameworks work by changing a base URL. Removes almost all switching cost between model providers.

21 API providers on the APIs.io network offer openai-compatible api. The highest-rated are NVIDIA NIM, Vapi, Cloudflare, Mistral AI, OpenRouter.

Providers

Ranked by API Evangelist rating — Exemplar and Strong are expanded by default.

Exemplar 4 Complete, well-documented, and agent-ready
NVIDIA NIM NVIDIA NIM (NVIDIA Inference Microservices) is a catalog of GPU-accelerated, containerized AI inference mic... 11 APIs 75.7 Vapi Vapi is a San Francisco-based voice AI platform that lets developers build real-time, low-latency voice age... 15 APIs 75.7 Cloudflare Cloudflare is a global network designed to make everything you connect to the Internet secure, private, fas... 87 APIs 69.9 Mistral AI Mistral AI provides state-of-the-art large language models and AI APIs for developers and enterprises. 11 APIs 68.3
Strong 6 Solid coverage with minor gaps
OpenRouter OpenRouter is an API platform that provides unified access to multiple AI language models through a single ... 7 APIs 65.4 Hyperbolic Hyperbolic is an open-access AI cloud and decentralized GPU marketplace serving 200,000+ builders with affo... 6 APIs 65.0 Perplexity Perplexity AI is an answer engine that delivers accurate answers to complex questions using large language ... 12 APIs 64.3 arcade-dev Arcade.dev (formerly Arcade AI) is the MCP runtime for production AI agents — a platform that lets agents s... 8 APIs 58.5 AIMLAPI AIMLAPI is a unified AI model API gateway providing access to 400+ state-of-the-art AI models from OpenAI, ... 10 APIs 56.3 Parasail Parasail is an AI Supercloud — a pay-per-token GPU inference platform aimed at AI startups and developers. ... 7 APIs 56.3
Developing 3 Usable, with meaningful gaps to close
cohere Generates a text response to a user message and streams it down, token by token. 9 APIs 46.1 ACI.dev ACI.dev (Aipolabs Agent-Computer Interface) is an open-source tool-calling platform that hooks AI agents in... 4 APIs 43.5 Bifrost Bifrost is a high-performance open-source AI gateway that unifies access to 20+ AI providers through a sing... 4 APIs 43.4
Thin 3 Limited public surface area
Langflow Langflow is an open-source low-code visual builder for AI agents, RAG pipelines, and LangChain-based workfl... 15 APIs 41.1 AI Gateway An API Evangelist landscape index of AI gateways — the LLM routers, prompt firewalls, model fallback proxie... 38 APIs 34.8 Apache Jclouds Apache jclouds is an open-source multi-cloud toolkit for the Java platform that provides a portable abstrac... 2 APIs 28.4
Emerging 3 Early or largely undocumented
Glama Glama is an all-in-one AI workspace combining an MCP server marketplace and registry, a managed MCP gateway... 7 APIs 27.2 io.net io.net is a decentralized GPU network for AI compute, built on Solana, that aggregates idle consumer and da... 8 APIs 20.1 Refact.ai Refact.ai is an open-source, local-first AI coding assistant and autonomous software-engineering agent buil... 2 APIs 17.4
Minimal 2 Almost no public developer surface
AutoGen Studio AutoGen Studio is a low-code / no-code developer GUI from Microsoft Research for rapidly prototyping, compo... 8.5 OctoAI OctoAI (formerly OctoML) was a Seattle-based AI inference platform founded in 2019 as a University of Washi... 5 APIs 8.5

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.

Bring-your-own model — any OpenAI-compatible endpoint (OpenAI, Azure OpenAI, Anthropic, vLLM, Ollama, local models) via declarative `model_client` config; AutoGen Extensions provides first-party clientsChats API (text channel) and OpenAI-compatible /chat/responsesIO Intelligence — OpenAI-compatible inference API for 15+ open-source models including Llama 3.3 70BLocal model providers — Ollama, LM Studio, vLLM, custom OpenAI-compatible endpointsOpenAI-Compatible APIOpenAI-Compatible InferenceOpenAI-compatible /v1/chat/completions, /v1/completions, /v1/embeddings, /v1/modelsOpenAI-compatible AI gateway at `https://gateway.glama.ai/v1`OpenAI-compatible Chat CompletionsOpenAI-compatible Chat Completions APIOpenAI-compatible Chat Completions endpointOpenAI-compatible REST API at https://api.hyperbolic.xyz/v1 — drop-in replacement requiring only api_key and base_url changesOpenAI-compatible REST surface — /v1/chat/completions, /v1/completions, /v1/embeddings, /v1/models, /v1/rankingOpenAI-compatible Responses endpoint (/api/v1/responses) so OpenAI clients can target a Langflow flowOpenAI-compatible and Anthropic-compatible function-definition output formatsOpenAI-compatible chat completions endpoint with attached toolsProvider AbstractionWorkers AI catalog of 78+ open-source models with OpenAI-compatible endpoints

Scroll for all 18