# Apertis Documentation

> Apertis is an AI API gateway: one API key reaches models from many providers through OpenAI- and Anthropic-compatible endpoints. Each link below is the clean Markdown version of a documentation page; /llms-full.txt holds all of them in one file, and the docs MCP server at https://docs.apertis.ai/mcp searches and reads the same pages.

## Getting Started

- [Quick Overview](https://docs.apertis.ai/intro.md): A tour of the Apertis console: sign in, create an API key, add credits and review your request logs.
- [Quick Start](https://docs.apertis.ai/getting-started/quick-start.md): Get up and running with the Apertis API in under 5 minutes.
- [Models](https://docs.apertis.ai/installation/models.md): Access models from OpenAI, Google, Anthropic, Meta, Microsoft, Mistral, Alibaba, NVIDIA, xAI, Amazon, DeepSeek, Perplexity, Allen AI, and other providers through Apertis.
- [Why Choose Apertis?](https://docs.apertis.ai/principles.md): Why teams choose Apertis: price and performance routing, an OpenAI-compatible API, unified billing and automatic failover across providers.
- [Models Intro](https://docs.apertis.ai/usage.md): Leading large language model providers on the market include OpenAI, Anthropic, Google, Meta, Microsoft, Mistral, and Alibaba.

## Account & Access

- [Organizations, Members, Projects, Groups, and Roles](https://docs.apertis.ai/authentication/organizations.md): Organizations let you manage shared API usage, billing, members, projects, API keys, and access control from one dashboard.
- [API Keys](https://docs.apertis.ai/authentication/api-keys.md): API keys are used to authenticate requests to the Apertis API.
- [Subscription Plans](https://docs.apertis.ai/billing/subscription-plans.md): Apertis offers flexible subscription plans designed to meet different usage needs.
- [Quota Management](https://docs.apertis.ai/billing/quota-management.md): Understanding how quota works is essential for managing your API usage and costs effectively.
- [Pay-As-You-Go (PAYG)](https://docs.apertis.ai/billing/payg.md): Pay-As-You-Go allows you to use the Apertis API without a subscription by paying for what you use.
- [Payment Methods](https://docs.apertis.ai/billing/payment-methods.md): Apertis supports multiple payment methods to accommodate users worldwide.
- [Rate Limits](https://docs.apertis.ai/billing/rate-limits.md): Apertis implements rate limits to ensure fair usage and maintain service quality for all users.

## Integrations

- [Claude Code](https://docs.apertis.ai/installation/claude-code.md): Claude Code is an agentic terminal tool that understands codebases and accelerates development by automating routine tasks, analyzing complex code, and managing git workflows through natural language commands.
- [OpenCode](https://docs.apertis.ai/installation/opencode.md): OpenCode is an AI coding agent that provides both CLI and IDE integration capabilities for AI-powered development tasks.
- [Crush](https://docs.apertis.ai/installation/crush.md): Crush is a terminal-based AI coding agent (CLI + TUI) that supports multiple models for code generation, debugging, and file operations.
- [Goose](https://docs.apertis.ai/installation/goose.md): Goose is an AI agent platform supporting local and desktop environments with CLI capabilities.
- [Cline (prev. Claude Dev)](https://docs.apertis.ai/installation/cline.md): Configure the Cline VS Code extension to use Apertis models through its OpenAI Compatible API provider.
- [Cursor IDE](https://docs.apertis.ai/installation/cursor.md): You can integrate Apertis into Cursor to use its models.
- [Continue Dev](https://docs.apertis.ai/installation/continue.md): Continue Dev is an extension designed for VSCode and Cursor IDE that simplifies interactions with large language models such as ChatGPT.
- [Roo Code (prev. Roo Cline)](https://docs.apertis.ai/installation/roocode.md): Roo Code is a solution that enables developers to easily integrate Apertis into their projects.
- [Kilo Code](https://docs.apertis.ai/installation/kilo-code.md): Kilo Code is a VS Code extension enhanced by MCP (Model Context Protocol) support, enabling direct code generation, debugging, and project management within the editor.
- [Kilo CLI](https://docs.apertis.ai/installation/kilo-cli.md): Kilo CLI is the terminal-based AI coding agent from Kilo Code, providing agentic coding capabilities directly in your terminal with multi-model support, MCP integration, and customizable agent workflows.
- [Chatbox AI](https://docs.apertis.ai/installation/chatbox.md): Chatbox AI is a graphical chat interface designed for interacting with APIs via API Keys in a user-friendly UI.
- [Immersive Translation](https://docs.apertis.ai/installation/translate.md): This is a bilingual translation extension.
- [bolt.diy (prev. oTToDev)](https://docs.apertis.ai/installation/bolt_diy.md): bolt.diy is a solution that enables developers to easily integrate Apertis into their projects.

## Configuration

- [Base URL and API Key Connection Guide](https://docs.apertis.ai/installation/connection.md): Apertis AI provides BASE_URL and API Key configurations for integrating with custom projects.
- [Call Apertis via OpenAI SDK](https://docs.apertis.ai/installation/scripts.md): Apertis provides OpenAI Compatible APIs, so you can use the OpenAI package in Python and modify the model variable to call all supported models.

## Help & Security

- [Security Best Practices](https://docs.apertis.ai/security/best-practices.md): Protecting your API keys and data is critical.
- [Frequently Asked Questions](https://docs.apertis.ai/help/faq.md): Quick answers to common questions about the Apertis API.
- [Troubleshooting](https://docs.apertis.ai/help/troubleshooting.md): This guide helps you diagnose and resolve common issues when using the Apertis API.
- [Error Codes](https://docs.apertis.ai/help/error-codes.md): This reference documents all error codes returned by the Apertis API, along with their meanings and recommended solutions.
- [Migration Guides](https://docs.apertis.ai/help/migration-guides.md): This guide helps you migrate to Apertis from other API providers or update between API versions.

## Resources

- [Open-Source Models](https://docs.apertis.ai/opensource.md): At Apertis AI, we specialize in offering a variety of cutting-edge open-source large language model services.
- [Web Chat Service](https://docs.apertis.ai/stimachat.md): Chat is an advanced conversation system developed by Apertis AI, featuring a bidirectional multi-turn dialogue mode and supporting interactions with 100+ large language models.

## API Reference

- [API Reference](https://docs.apertis.ai/api/index.md): Complete API reference documentation for Apertis AI

## Text Generation

- [Chat Completion](https://docs.apertis.ai/api/text-generation/chat-completions.md): Generate a model response for a conversation with the OpenAI-compatible POST /v1/chat/completions endpoint.
- [Responses API](https://docs.apertis.ai/api/text-generation/responses.md): The Responses API is compatible with OpenAI's Responses API format, providing a streamlined interface for generating AI responses.
- [Messages API (Native Anthropic)](https://docs.apertis.ai/api/text-generation/messages.md): The Messages API is a native Anthropic endpoint that routes directly to Anthropic-type channels.
- [Streaming Output](https://docs.apertis.ai/api/text-generation/streaming.md): Stream a chat completion token by token through the OpenAI-compatible API by setting stream to true.
- [Structured Output](https://docs.apertis.ai/api/text-generation/structured-output.md): Through Apertis's structured output feature, developers can convert API responses into specific JSON formats, which is particularly useful for application scenarios requiring specific data structures.
- [Prompt Cache](https://docs.apertis.ai/api/text-generation/prompt-cache.md): Apertis includes a powerful Prompt Cache feature that significantly improves system performance, reduces processing time for repeated requests, and lowers API costs.
- [Context Compression](https://docs.apertis.ai/api/text-generation/context-compression.md): Context compression automatically summarizes older conversation history to reduce token usage and cost, while preserving recent context.

## Search

- [Web Search](https://docs.apertis.ai/api/search/web-search.md): Enable real-time web search for any model by adding the :web suffix to the model name.

## Vision & Images

- [Read Image with LLM](https://docs.apertis.ai/api/vision/read-image.md): Send an image URL in a chat completion request so a vision-capable model can describe or analyze it.
- [Using Image Generation API](https://docs.apertis.ai/api/vision/image-generation.md): Apertis provides Image Generation API for developers to generate images, primarily focusing on GPT-4o Image Generation, Gemini 2.0 Flash Expanded Image Generation and Grok 3 Image Generation.
- [Using GPT Image Models](https://docs.apertis.ai/api/vision/dalle.md): Generate images with GPT image models through the OpenAI-compatible /v1/images/generations endpoint.
- [Images API](https://docs.apertis.ai/api/vision/images-api.md): The Images API generates images from text prompts using GPT image models such as gpt-image-2.

## Audio & Video

- [Audio API](https://docs.apertis.ai/api/audio-video/audio.md): The Audio API enables speech-to-text transcription, audio translation, text-to-speech synthesis, and audio-input chat completions.
- [Video API](https://docs.apertis.ai/api/audio-video/video.md): Video generation endpoints are not currently available on the Apertis API.

## Embeddings & Rerank

- [Embedding API](https://docs.apertis.ai/api/embeddings/guide.md): Apertis provides the Embedding API for developers to convert text into vectors and find similar text through vector search.
- [Embedding API](https://docs.apertis.ai/api/embeddings/embeddings-api.md): Apertis provides the Embedding API for developers to convert text into vectors and find similar text through vector search.
- [Rerank API](https://docs.apertis.ai/api/embeddings/rerank.md): The /v1/rerank endpoint is not currently available on the Apertis API.

## SDKs & Libraries

- [@apertis/ai-sdk-provider](https://docs.apertis.ai/api/sdks/ai-sdk-provider.md): Official Vercel AI SDK Provider for Apertis, enabling access to the models available to your Apertis API key through a standardized AI SDK interface.
- [@apertis/agent](https://docs.apertis.ai/api/sdks/agent-sdk.md): @apertis/agent is a TypeScript agent runtime for the Apertis API.
- [Apertis Python SDK](https://docs.apertis.ai/api/sdks/python-sdk/index.md): Official Python SDK for the Apertis AI API, providing a comprehensive interface to the models available to your Apertis API key through a unified, type-safe library.
- [Chat Completions](https://docs.apertis.ai/api/sdks/python-sdk/chat-completions.md): Generate text responses using chat-based models with the familiar OpenAI-compatible interface.
- [Streaming](https://docs.apertis.ai/api/sdks/python-sdk/streaming.md): Receive responses in real-time as they are generated, enabling responsive user interfaces and faster time-to-first-token.
- [Tool Calling](https://docs.apertis.ai/api/sdks/python-sdk/tool-calling.md): Enable AI models to call functions and interact with external systems, enabling the creation of AI agents and automated workflows.
- [Embeddings](https://docs.apertis.ai/api/sdks/python-sdk/embeddings.md): Generate vector embeddings for text, enabling semantic search, clustering, and retrieval-augmented generation (RAG) applications.
- [Vision (Images)](https://docs.apertis.ai/api/sdks/python-sdk/vision.md): Analyze images using multimodal models, enabling visual understanding, image description, and visual question answering.
- [Audio](https://docs.apertis.ai/api/sdks/python-sdk/audio.md): Process audio input and generate audio output, enabling voice-based applications, transcription, and text-to-speech.
- [Video](https://docs.apertis.ai/api/sdks/python-sdk/video.md): Analyze video content using multimodal models, enabling video understanding, scene analysis, and temporal reasoning.
- [Web Search](https://docs.apertis.ai/api/sdks/python-sdk/web-search.md): Enable AI models to search the web in real-time, providing up-to-date information with citations and source attribution.
- [Reasoning & Extended Thinking](https://docs.apertis.ai/api/sdks/python-sdk/reasoning.md): Enable chain-of-thought reasoning and extended thinking capabilities for complex problem-solving, analysis, and multi-step tasks.
- [Messages API](https://docs.apertis.ai/api/sdks/python-sdk/messages-api.md): Use Anthropic's native message format for interacting with Claude models, providing access to Claude-specific features and optimal performance.
- [Responses API](https://docs.apertis.ai/api/sdks/python-sdk/responses-api.md): Use OpenAI's Responses API format for enhanced capabilities including built-in tools, web search, and file handling.
- [Rerank](https://docs.apertis.ai/api/sdks/python-sdk/rerank.md): client.rerank.create() calls /v1/rerank, which is not currently available on the Apertis API.
- [Async Patterns](https://docs.apertis.ai/api/sdks/python-sdk/async.md): Use asynchronous programming for high-performance applications, concurrent requests, and efficient I/O handling.
- [LangChain](https://docs.apertis.ai/api/sdks/langchain.md): Use Apertis models in LangChain through the langchain-openai ChatOpenAI client and the Apertis base URL.
- [LlamaIndex](https://docs.apertis.ai/api/sdks/llamaindex.md): LlamaIndex has native support for Apertis through the llama-index-llms-apertis package.
- [LiteLLM](https://docs.apertis.ai/api/sdks/litellm.md): LiteLLM provides a unified interface to call 100+ LLMs.
- [Apertis MCP Server](https://docs.apertis.ai/api/sdks/mcp-server.md): @apertis/mcp-server is an MCP server that lets agents (Claude Code, OpenCode, or any MCP-compatible client) manage your Apertis account and query the API gateway at runtime — list models, check quota, create API keys, ask for task-aware model recommendations, and delegate bulk grunt work to a cheap coworker model.
- [@apertis/cli](https://docs.apertis.ai/api/sdks/cli.md): @apertis/cli is a small terminal tool for the Apertis API gateway.

## Utilities

- [Models](https://docs.apertis.ai/api/utilities/models.md): Returns available models in OpenAI-compatible format.
- [Recommend](https://docs.apertis.ai/api/utilities/recommend.md): Returns an opinionated, task-aware model recommendation with live pricing.
- [Fallback Models](https://docs.apertis.ai/api/utilities/fallback-models.md): Apertis provides a powerful fallback model mechanism that automatically switches to backup models when the primary model request fails, ensuring high availability and service stability.
- [Billing Credits](https://docs.apertis.ai/api/utilities/billing-credits.md): Returns your current billing balance, including PAYG credits (in USD) and subscription cycle quota.

## Other

- [Ideas](https://docs.apertis.ai/help/ideas.md): Apertis includes a built-in community feedback platform where you can submit feature requests, report issues, and vote on proposals that matter to you.