Browse

Run LLM inference

Find documented model inference and chat completion operations.

Services are ordered by documented operations, attributed reports and current documentation. 26 interfaces are classified here. Each card shows the interfaces a service offers; open it for access requirements and sources.

Categories · Tasks · Interfaces · How listings are checked

Together AI

AI inference and GPU cloud for open-source models, with an OpenAI-compatible API and a CLI.

ai models · Developer tools

API · Access documentation verifiedCLI · Access documentation verified

Mistral AI

Frontier AI models and platform: Mistral API, hosted MCP server and the Vibe coding CLI.

ai models · Developer tools

CLI · Access documentation verifiedMCP · Access documentation verifiedAPI · Access documentation verified

Anthropic

AI safety company and maker of Claude; the Claude API gives programmatic access to Claude models and Claude Managed Agents.

ai models · Developer tools

API · Access documentation verified

OpenRouter

Unified API and MCP server for accessing many AI models from different providers.

Developer tools · ai models

API · Access documentation verifiedMCP · Access documentation verified

Groq

Fast AI inference (GroqCloud) with an OpenAI-compatible API for chat, speech and models.

ai models · Developer tools

API · Documentation checked: 2026-10-06

Fireworks AI

Fast inference and training platform for open models, with an OpenAI-compatible API and the firectl CLI.

ai models · Developer tools

API · Documentation checked: 2026-10-06CLI · Documentation checked: 2026-10-06

Chutes

Hosted AI inference API with OpenAI-compatible chat completions across Chutes models.

artificial-intelligence · Developer tools · api

API · Access documentation verified

Wolfram|Alpha

Wolfram|Alpha computes answers to natural-language questions and provides an LLM API for model-ready results.

Public data · ai-ml

API · Access documentation verified

AI/ML API

An AI model platform and API provider offering chat, reasoning, image, audio, video, and other model services with an MCP server for connected agents.

artificial-intelligence · Developer tools · mcp

MCP · Access documentation verified

webclaw

webclaw’s hosted cloud REST API extracts content from a single URL into Markdown or other documented output formats.

web scraping · content extraction · api

API · Access documentation verified

Jina AI

Search foundation APIs including Reader (URL to LLM-ready text) and web Search.

Research and knowledge · Developer tools

API · Access documentation verifiedAPI · Access documentation verified

URLpipe

URLpipe turns a supplied web page URL into clean Markdown for prompts and retrieval-augmented generation pipelines.

Developer tools · web-content · API

API · Access documentation verified

LangWatch

LangWatch helps teams observe and evaluate LLM applications, including tracking selected-text events from user interactions.

Developer tools · analytics

API · Access documentation verified

Helicone

Helicone is an LLM observability platform with an AI Gateway that routes OpenAI-compatible chat-completion requests across models.

Developer tools · artificial-intelligence · Observability

API · Access documentation verified

Brave Search API

Independent web search API for developers and AI agents: web, news, images, LLM context and answers.

Research and knowledge · Developer tools

API · Documentation checked: 2026-10-06API · Access documentation verified

Plaid

Financial data network and API for connecting bank accounts to apps, with an API, a CLI and a remote MCP server.

Finance and economic data · Developer tools

CLI · Access documentation verifiedAPI · Access documentation verifiedMCP · Access documentation verified

SambaNova

SambaNova Cloud API for generating chat completions from structured messages.

artificial-intelligence · chat-completions · api

API · Documentation checked: 2026-10-09

AI21

AI21 provides foundation models including Jamba, with an API for chat completion requests.

artificial intelligence · language models · API

API · Documentation checked: 2026-10-10

Tellers

Tellers is AI video-editing software with a remote MCP server for creating, editing, inspecting, previewing, and exporting video timelines through an AI agent.

video · creative-tools · Developer tools

MCP · Documentation checked: 2026-10-10

MiniMax

MiniMax provides AI models and developer APIs for text generation and other modalities.

artificial-intelligence · Developer tools · language-models

API · Documentation checked: 2026-10-09

You.com Web Search API

You.com’s Web Search API returns ranked web and news results in structured JSON for applications.

search · Developer tools · artificial intelligence

API · Documentation checked: 2026-10-09

OpenMayhem

OpenMayhem is a peer-to-peer marketplace for AI inference with an OpenAI-compatible API for chat completions and other model tasks.

ai · api · inference · Developer tools

API · Documentation checked: 2026-10-11

Z.AI

Z.AI provides hosted language models through a REST API for chat completions.

artificial intelligence · Developer tools

API · Documentation checked: 2026-10-09

Eden AI

Eden AI provides a unified API for accessing AI models from multiple providers.

artificial-intelligence · Developer tools · language-models

API · Documentation checked: 2026-10-09