# Eden AI Documentation

- [Eden AI Documentation](https://www.edenai.co/docs/index.md): One API. 500+ AI models. Use any LLM or AI feature with fallback, routing, and cost tracking built in.
- [First LLM Call](https://www.edenai.co/docs/v3/quickstart/first-llm-call.md): Make your first call to Eden AI's OpenAI-compatible LLM endpoint and start building with 500+ models.
- [First Expert Model call](https://www.edenai.co/docs/v3/quickstart/first-expert-model-call.md): Get started with Eden AI's Universal AI endpoint for expert models (OCR, image analysis, text processing, and more).
- [Batch OCR Table Extraction](https://www.edenai.co/docs/v3/quickstart/batch-ocr-tables.md): Extract tables from many documents with Eden AI's async OCR endpoint, then flatten the results into a single CSV. Includes Python, R, and cURL samples.
- [What is an AI Gateway?](https://www.edenai.co/docs/v3/overview/ai-gateway.md): Eden AI is a unified AI gateway that gives you access to 500+ AI models from 50+ providers through a single API.
- [LLMs vs Expert Models](https://www.edenai.co/docs/v3/overview/llms-vs-expert-models.md): Eden AI V3 provides two main endpoints. Both share the same base URL (https://api.
- [Plans & Pricing](https://www.edenai.co/docs/v3/overview/plans-prices.md): Eden AI charges no markup on provider pricing. You pay exactly what the underlying provider charges, plus a 5.
- [Rate Limits](https://www.edenai.co/docs/v3/overview/rate-limits.md): Eden AI applies a per-account rate limit on requests to the API. The limit can be raised based on the volume and pattern of traffic you need to support.
- [List LLM Models](https://www.edenai.co/docs/v3/llms/listing-models.md): Use the /v3/models endpoint to retrieve all LLM models available through Eden AI, along with their capabilities: input modalities, reasoning, web search, and function calling.
- [Chat completions](https://www.edenai.co/docs/v3/llms/chat-completions.md): Build conversational AI applications using Eden AI's OpenAI-compatible chat completions endpoint.
- [Responses](https://www.edenai.co/docs/v3/llms/responses.md): Eden AI supports the OpenAI Responses API — a stateful alternative to chat completions that stores conversation history server-side, so you don't need to resend the full message history on each turn.
- [Embeddings](https://www.edenai.co/docs/v3/llms/embeddings.md): Turn text into vectors with one OpenAI-compatible API. Run RAG, semantic search, clustering, and recommendations across 200+ models on Eden AI.
- [File upload](https://www.edenai.co/docs/v3/llms/file-upload.md): Learn how to upload and manage files with V3's persistent file storage system.
- [Structured Output](https://www.edenai.co/docs/v3/llms/structured-output.md): Structured output lets you constrain LLM responses to valid JSON that follows a specific format.
- [Web Search](https://www.edenai.co/docs/v3/llms/web-search.md): Web search lets LLMs access real-time information from the internet when generating responses.
- [Prompt Caching](https://www.edenai.co/docs/v3/llms/prompt-caching.md): Reuse stable prompt prefixes to reduce LLM latency and input-token cost while still generating a fresh response on every request.
- [Provider Routing](https://www.edenai.co/docs/v3/llms/provider-routing.md): Name a model without a provider and Eden AI picks which provider serves it, by price, speed or latency, with health-aware failover.
- [Request Metadata](https://www.edenai.co/docs/v3/llms/request-metadata.md): Opt in to a per-request report of what Eden AI decided: which provider served you, what was tried before it, which region, and whether your own key was used.
- [Streaming](https://www.edenai.co/docs/v3/llms/streaming.md): Learn how to handle streaming responses from the V3 LLM endpoint using Server-Sent Events (SSE).
- [Image Generation](https://www.edenai.co/docs/v3/llms/image-generation.md): Generate and edit images with the OpenAI-compatible /v3/images endpoints.
- [Video Generation](https://www.edenai.co/docs/v3/llms/video-generation.md): Generate video with the OpenAI-compatible /v3/videos endpoints.
- [MCP Server](https://www.edenai.co/docs/v3/expert-models/mcp-server.md): Eden AI's expert models are available as MCP tools, so any MCP client or LLM agent loop can call OCR, web search, speech, translation and more.
- [Webhooks](https://www.edenai.co/docs/v3/expert-models/webhooks.md): Webhooks let you receive results from async Universal AI jobs via HTTP callbacks instead of polling.
- [List Expert Models](https://www.edenai.co/docs/v3/expert-models/listing-models.md): Use the /v3/info endpoints to discover all available expert model features, providers, and models.
- [Provider Parameters](https://www.edenai.co/docs/v3/expert-models/provider-parameters.md): The provider_params field lets you pass provider-specific parameters that aren't part of Eden AI's unified schema.
- [Text AI Content Detection](https://www.edenai.co/docs/v3/expert-models/features/text/ai-detection.md): The AI Detection API is a tool designed to determine whether a given text was generated by an artificial intelligence chatbot, or a Language Model (LLM).
- [Text Moderation](https://www.edenai.co/docs/v3/expert-models/features/text/moderation.md): Text moderation scans text for offensive, sexually explicit or suggestive content, it also checks if there is any content of self-harm, violence, racist or hate speech.
- [Grammar Spell Check](https://www.edenai.co/docs/v3/expert-models/features/text/spell-check.md): Spell Check analyzes the inputted text by comparing it to a dictionary of correctly spelled words to identify and highlight any spelling errors or grammatical mistakes.
- [Topic Extraction](https://www.edenai.co/docs/v3/expert-models/features/text/topic-extraction.md): Topic analysis is a Natural Language Processing (NLP) technique that allows us to automatically extract meaning from text by identifying recurrent themes or topics.
- [Named Entity Recognition](https://www.edenai.co/docs/v3/expert-models/features/text/named-entity-recognition.md): Named Entity Recognition (also called entity identification or extraction) is an information extraction technique that automatically identifies named entities in a text and classifies them into
- [Plagiarism Detection](https://www.edenai.co/docs/v3/expert-models/features/text/plagia-detection.md): The Plagiarism Detection API is a tool designed to scan a content string for plagiarism using a plagiarism detection module
- [Web Scraping](https://www.edenai.co/docs/v3/expert-models/features/web/scraping.md): Fetch a single URL and return its clean content as markdown, text, or HTML, with optional JavaScript rendering.
- [Site Map](https://www.edenai.co/docs/v3/expert-models/features/web/map.md): Discover and return the list of URLs on a site (a sitemap-style link map).
- [Web Search](https://www.edenai.co/docs/v3/expert-models/features/web/search.md): Search the web for a query and return ranked results (title, URL, and a snippet or the page content).
- [Web Crawl](https://www.edenai.co/docs/v3/expert-models/features/web/crawl-async.md): Crawl a site from a starting URL and return the content of its pages. Runs as an async job.
- [Batch Web Scraping](https://www.edenai.co/docs/v3/expert-models/features/web/batch-scrape-async.md): Scrape many URLs in one request and return each page's content. Runs as an async job.
- [Structured Extraction](https://www.edenai.co/docs/v3/expert-models/features/web/structured-extraction-async.md): Extract structured data from one or more web pages against a schema or prompt. Runs as an async job.
- [Deep Research](https://www.edenai.co/docs/v3/expert-models/features/web/research-async.md): Run deep, multi-step web research on a query and return a synthesized answer with sources. Runs as an async job.
- [Text Detection (OCR)](https://www.edenai.co/docs/v3/expert-models/features/ocr/ocr.md): Optical Character Recognition or Reader (OCR) is the electronic or mechanical conversion of images of typed, handwritten or printed text into machine-encoded text.
- [OCR Multipage](https://www.edenai.co/docs/v3/expert-models/features/ocr/ocr-async.md): OCR or Optical Character Recognition is also referred to as text recognition or text extraction. It allows users to extract text data from PDFs with multiple pages.
- [Table Extraction](https://www.edenai.co/docs/v3/expert-models/features/ocr/ocr-tables-async.md): OCR Table (Optical Character Recognition for tabular documents)  allows users to analyze documents containing tables and returns a structured representation of the detected tables in the form of a
- [Identity Parser](https://www.edenai.co/docs/v3/expert-models/features/ocr/identity-parser.md): ID Document parsing technology allows users to automatically extract information from an ID Document such as passport, ID card, driving license and more.
- [Financial Parser](https://www.edenai.co/docs/v3/expert-models/features/ocr/financial-parser.md): Financial Parser API is a powerful and versatile tool designed to streamline your financial data extraction process.
- [Resume Parser](https://www.edenai.co/docs/v3/expert-models/features/ocr/resume-parser.md): Resume Parser enables users to extract various information from resumes (curriculum vitae, CV) that could be in a variety of formats and returns structured data (name, job list, education, skills) to
- [Background removal](https://www.edenai.co/docs/v3/expert-models/features/image/background-removal.md): Background removal is a digital image processing technique designed to seamlessly eliminate the backdrop of a photo, leaving behind only the main subject.
- [Image generation](https://www.edenai.co/docs/v3/expert-models/features/image/generation.md): Image Generation is an advanced feature that generates compelling images based on a given text prompt.
- [AI Image Detection](https://www.edenai.co/docs/v3/expert-models/features/image/ai-detection.md): Determine whether an image was generated by AI or is a real photograph or artwork.
- [Object Detection](https://www.edenai.co/docs/v3/expert-models/features/image/object-detection.md): Object Detection is a computer vision technique that allows users to identify and locate (with bounding boxes) objects in an image.
- [Face Detection](https://www.edenai.co/docs/v3/expert-models/features/image/face-detection.md): Face Detection is a computer technology being used in a variety of applications that identifies human faces in digital images with different attributes like landmarks, sentiments and physical attire
- [Explicit Content Detection](https://www.edenai.co/docs/v3/expert-models/features/image/explicit-content.md): Explicit Content Detection detects adult only content in images, that is generally inappropriate for people under the age of 18 and includes nudity, sexual activity, pornography, violence, gore
- [Image Anonymization](https://www.edenai.co/docs/v3/expert-models/features/image/anonymization.md): Image Anonymization API, also known as image de-identification or image de-personalization, refers to the process of automatically removing personal or sensitive information from images.
- [Deepfake Detection](https://www.edenai.co/docs/v3/expert-models/features/image/deepfake-detection.md): Detect whether a face in a real photo has been swapped or manipulated (face-swap deepfakes). For fully AI-generated images, use AI Image Detection instead.
- [Face Comparison](https://www.edenai.co/docs/v3/expert-models/features/image/face-compare.md): Compare two faces and decide whether they are from the same person. The API expects 2 images, reference and query, where the former is the ground truth (e.g.
- [Logo Detection](https://www.edenai.co/docs/v3/expert-models/features/image/logo-detection.md): Logo Detection is a powerful technology that enables the automatic identification and recognition of popular logos within an image.
- [Face Recognition](https://www.edenai.co/docs/v3/expert-models/features/image/face-recognition.md): Recognizing a face in an image is a more advanced feature than just detecting the face in the image.
- [Text Translation](https://www.edenai.co/docs/v3/expert-models/features/translation/automatic-translation.md): Automatic translation or machine translation (MT) is the process of automatically translating a text from one language to another language.
- [Document Translation](https://www.edenai.co/docs/v3/expert-models/features/translation/document-translation.md): Document Translation API translates whole documents in supported languages and various file formats (like pdf or doc) while keeping their structure intact.
- [Text to Speech](https://www.edenai.co/docs/v3/expert-models/features/audio/tts.md): Text-to-speech (TTS) is a technology that converts written text into spoken audio, enabling computers and digital devices to "read" text aloud.
- [Speech To Text](https://www.edenai.co/docs/v3/expert-models/features/audio/speech-to-text-async.md): Speech Recognition (or speech to text or voice to text) can recognize and transcribe spoken words (voice),  that will be converted to text with or without diarization.
- [Video Generation](https://www.edenai.co/docs/v3/expert-models/features/video/generation-async.md): The Video Generation API enables easy creation of high-quality videos from text,and images, perfect for marketing, education, and more—all through one integration.
- [Video Deepfake Detection](https://www.edenai.co/docs/v3/expert-models/features/video/deepfake-detection-async.md): Detect deepfake and synthetically manipulated video. Returns an overall deepfake score and prediction, along with per-frame scores when the provider supplies them.
- [Fallback](https://www.edenai.co/docs/v3/general/fallback.md): Eden AI automatically handles fallback on both LLM and Universal AI / expert model requests.
- [Caching](https://www.edenai.co/docs/v3/general/caching.md): Eden AI automatically caches responses for repeated identical requests. When a request matches a previous one (same model and same input), the cached response is returned at no additional cost.
- [Buying Credits & Auto-Refill](https://www.edenai.co/docs/v3/general/buying-credits.md): Eden AI uses a pay-per-use credit system. Every API response includes a cost field showing the charge in USD for that request, so you always know exactly what you are spending.
- [Sandbox](https://www.edenai.co/docs/v3/general/sandbox.md): Sandbox tokens let you test your integration without real provider calls and at no cost.
- [Custom API Keys](https://www.edenai.co/docs/v3/general/custom-api-keys.md): Custom API keys let you create additional keys beyond your main account key. Each key can have its own budget, expiration, and type, giving you fine-grained control over access and spending.
- [Monitoring](https://www.edenai.co/docs/v3/general/monitoring.md): Learn how to track your Eden AI API consumption and costs with the Management API usage endpoints.
- [Support](https://www.edenai.co/docs/v3/general/support.md): Eden AI offers several support channels depending on the nature of your question and your plan.
- [BYOK (Bring Your Own Key)](https://www.edenai.co/docs/v3/general/byok.md): Eden AI lets you use your own provider API keys (OpenAI, Google, Anthropic, etc.
- [Users & Organisation](https://www.edenai.co/docs/v3/organization/users-organisation.md): Eden AI provides team and organisation management features for companies that need structured access control, role-based permissions, and governance over their AI usage.
- [Guardrails](https://www.edenai.co/docs/v3/organization/guardrails.md): Guardrails are reusable usage policies that control which models your team can call, how often, and how much a member can spend. Create them in the dashboard and attach them to roles, members, or API tokens.
- [Management API](https://www.edenai.co/docs/v3/organization/management-api.md): Programmatically create and manage your organization's inference keys with a durable issuer key, without a dashboard round-trip.
- [Provider Data Use & Retention](https://www.edenai.co/docs/v3/data-governance/provider-data-policies.md): Whether each AI provider trains on your data, how long they keep it, and which ones offer Zero Data Retention (ZDR), for every model available through Eden AI.
- [Servers location](https://www.edenai.co/docs/v3/data-governance/servers-location.md): Eden AI's infrastructure is hosted in secure European data centers to ensure optimal performance and compliance.
- [EU Endpoint](https://www.edenai.co/docs/v3/data-governance/eu-endpoint.md)
- [Static IP](https://www.edenai.co/docs/v3/data-governance/static-ip.md): Have Eden AI fetch your file URLs from a fixed European IP address you can whitelist on your own servers.
- [Data retention](https://www.edenai.co/docs/v3/data-governance/data-retention.md): Learn about Eden AI's data retention policies and log retention options.
- [OpenAI Python SDK](https://www.edenai.co/docs/v3/integrations/openai-sdk-python.md): Use the official OpenAI Python SDK with Eden AI to access 500+ AI models through a familiar interface.
- [OpenAI TS/JS SDK](https://www.edenai.co/docs/v3/integrations/openai-sdk-typescript.md): Use the official OpenAI TypeScript/JavaScript SDK with Eden AI for seamless multi-provider access.
- [LangChain](https://www.edenai.co/docs/v3/integrations/langchain.md): Integrate Eden AI with LangChain for building powerful LLM applications with access to 500+ models.
- [Pydantic AI](https://www.edenai.co/docs/v3/integrations/pydantic-ai.md): Use Pydantic AI with Eden AI to build type-safe agents on 500+ AI models through one API.
- [aisuite](https://www.edenai.co/docs/v3/integrations/aisuite.md): Use aisuite with Eden AI to call 500+ AI models through one unified, OpenAI-style interface.
- [Haystack](https://www.edenai.co/docs/v3/integrations/haystack.md): Use Eden AI with Haystack (deepset) to build LLM and RAG pipelines on 500+ AI models through one EU-hosted API key.
- [Atomic Agents](https://www.edenai.co/docs/v3/integrations/atomic-agents.md): Use Atomic Agents with Eden AI to build agents on 500+ AI models through an OpenAI-compatible, Instructor-powered interface.
- [Repowise](https://www.edenai.co/docs/v3/integrations/repowise.md): Run Repowise codebase intelligence on Eden AI, for both the LLM and the embedder, with an EU endpoint.
- [any-llm](https://www.edenai.co/docs/v3/integrations/any-llm.md): Use any-llm (Mozilla AI) with Eden AI to call 500+ AI models through one unified Python interface.
- [Bifrost](https://www.edenai.co/docs/v3/integrations/bifrost.md): Use Bifrost with Eden AI to route to 500+ AI models through one OpenAI-compatible gateway.
- [Lynkr](https://www.edenai.co/docs/v3/integrations/lynkr.md): Use Lynkr with Eden AI to route your gateway to 500+ AI models with tier-based cost optimisation.
- [open-connector](https://www.edenai.co/docs/v3/integrations/open-connector.md): Use open-connector with Eden AI to expose 500+ AI models through a self-hosted gateway with SDK, CLI, MCP and HTTP access.
- [Plano](https://www.edenai.co/docs/v3/integrations/plano.md): Route Plano, the AI-native proxy for agentic apps, through Eden AI and reach 500+ models behind one key.
- [Claude Code](https://www.edenai.co/docs/v3/integrations/claude-code.md): Configure Claude Code, Anthropic's official CLI coding agent, to use Eden AI for access to 500+ models behind a single API key.
- [Cline](https://www.edenai.co/docs/v3/integrations/cline.md): Configure Cline, the autonomous AI coding agent for VS Code, to use Eden AI for access to +300 LLM models.
- [Codex CLI](https://www.edenai.co/docs/v3/integrations/codex-cli.md): Configure Codex CLI, OpenAI's open-source local coding agent, to use Eden AI for access to 500+ models behind a single API key.
- [Continue.dev](https://www.edenai.co/docs/v3/integrations/continue-dev.md): Configure Continue.dev, the open-source AI code assistant, to use Eden AI for access to 500+ models.
- [OpenCode](https://www.edenai.co/docs/v3/integrations/opencode.md): Configure OpenCode, the AI-powered terminal coding assistant, to use Eden AI for access to 500+ models.
- [Open Code Review](https://www.edenai.co/docs/v3/integrations/open-code-review.md): Use Open Code Review with Eden AI to review your code with 500+ AI models through one API.
- [Pi](https://www.edenai.co/docs/v3/integrations/pi.md): Use Pi with Eden AI to power your coding agent (and Flue) with 500+ AI models through one API.
- [Kilo Code](https://www.edenai.co/docs/v3/integrations/kilo-code.md): Configure Kilo Code, the open-source AI coding agent for VS Code and the terminal, to use Eden AI for 500+ models behind one API key.
- [Hermes Agent](https://www.edenai.co/docs/v3/integrations/hermes.md): Connect Hermes Agent to Eden AI and run the self-hosted, persistent agent on 500+ models with automatic fallbacks and a single API key.
- [OpenClaw](https://www.edenai.co/docs/v3/integrations/openclaw.md): Connect OpenClaw to Eden AI and route your agent through 500+ models with automatic fallbacks and a single API key.
- [nanobot](https://www.edenai.co/docs/v3/integrations/nanobot.md): Run nanobot, the self-hosted personal AI agent framework, on Eden AI and reach 500+ models with a single API key.
- [LibreChat](https://www.edenai.co/docs/v3/integrations/librechat.md): Configure LibreChat, the open-source ChatGPT alternative, to use Eden AI for access to 500+ AI models.
- [Open WebUI](https://www.edenai.co/docs/v3/integrations/open-webui.md): Configure Open WebUI (formerly Ollama WebUI) to use Eden AI for accessing 500+ AI models through a sleek interface.
- [DeepTutor](https://www.edenai.co/docs/v3/integrations/deeptutor.md): Use DeepTutor with Eden AI to run your self-hosted study and research app on 500+ AI models through one API.
- [PyGPT](https://www.edenai.co/docs/v3/integrations/py-gpt.md): Configure PyGPT, the desktop AI assistant, to use Eden AI for 500+ models behind one API key.
- [n8n](https://www.edenai.co/docs/v3/integrations/n8n.md): Connect n8n to Eden AI using the official community node, and plug +300 LLM models from 50+ providers into any AI Agent or Chain workflow.
- [List Features](https://www.edenai.co/docs/api-reference/info/list-features.md): List all available features and their subfeatures.
- [List Subfeatures](https://www.edenai.co/docs/api-reference/info/list-subfeatures.md): List all subfeatures for a specific feature.
- [Get Feature Info](https://www.edenai.co/docs/api-reference/info/get-feature-info.md): Get detailed information for a specific feature/subfeature.
- [Chat Completions](https://www.edenai.co/docs/api-reference/chat/chat-completions.md): OpenAI-compatible chat completions endpoint (v3).
- [Create Response](https://www.edenai.co/docs/api-reference/responses/create-response.md): Create a model response.
- [Retrieve Response](https://www.edenai.co/docs/api-reference/responses/retrieve-response.md): Retrieve a stored model response by ID.
- [Delete Response](https://www.edenai.co/docs/api-reference/responses/delete-response.md): Delete a stored model response by ID.
- [Create Moderation](https://www.edenai.co/docs/api-reference/moderations/create-moderation.md): OpenAI-compatible content moderation endpoint.
- [List Moderation Models](https://www.edenai.co/docs/api-reference/moderations/list-moderation-models.md): List available moderation models.
- [Create Embeddings](https://www.edenai.co/docs/api-reference/embeddings/create-embeddings.md): OpenAI-compatible embeddings endpoint.
- [List Embeddings Models](https://www.edenai.co/docs/api-reference/embeddings/list-embeddings-models.md): List available embeddings models.
- [Create Anthropic Message](https://www.edenai.co/docs/api-reference/anthropic-messages/create-anthropic-message.md): Anthropic Messages API — native pass-through via litellm.
- [Count Anthropic Tokens](https://www.edenai.co/docs/api-reference/anthropic-messages/count-anthropic-tokens.md): Count input tokens for an Anthropic-format request without running the model.
- [Image Generations](https://www.edenai.co/docs/api-reference/images/image-generations.md): OpenAI-compatible image generation endpoint.
- [Image Edits](https://www.edenai.co/docs/api-reference/images/image-edits.md): OpenAI-compatible image-edit endpoint.
- [List Image Models](https://www.edenai.co/docs/api-reference/images/list-image-models.md): List image-generation / image-edit models available in the caller's region.
- [Audio Transcriptions](https://www.edenai.co/docs/api-reference/audio/audio-transcriptions.md): OpenAI-compatible speech-to-text endpoint.
- [List Transcription Models](https://www.edenai.co/docs/api-reference/audio/list-transcription-models.md): List speech-to-text models available in the caller's region.
- [Audio Speech](https://www.edenai.co/docs/api-reference/audio/audio-speech.md): OpenAI-compatible text-to-speech endpoint.
- [List Speech Models](https://www.edenai.co/docs/api-reference/audio/list-speech-models.md): List text-to-speech models available in the caller's region.
- [List Videos](https://www.edenai.co/docs/api-reference/videos/list-videos.md): List your video generation jobs, newest first.
- [Create Video](https://www.edenai.co/docs/api-reference/videos/create-video.md): Start a video generation job.
- [List Video Models](https://www.edenai.co/docs/api-reference/videos/list-video-models.md): List the video models available in the caller's region.
- [Retrieve Video](https://www.edenai.co/docs/api-reference/videos/retrieve-video.md): Get a video job. Poll until `status` is `completed` or `failed`.
- [Delete Video](https://www.edenai.co/docs/api-reference/videos/delete-video.md): Delete a finished video job. Jobs still in progress cannot be deleted.
- [Download Video Content](https://www.edenai.co/docs/api-reference/videos/download-video-content.md): Download the finished mp4.
- [List Models](https://www.edenai.co/docs/api-reference/models/list-models.md): List available LLM models with extended metadata.
- [Universal Ai](https://www.edenai.co/docs/api-reference/universal-ai/universal-ai.md): Universal AI endpoint for synchronous non-LLM AI features.
- [List Async Jobs](https://www.edenai.co/docs/api-reference/universal-ai/list-async-jobs.md): List async jobs for the authenticated user.
- [Create Async Job](https://www.edenai.co/docs/api-reference/universal-ai/create-async-job.md): Create an async job for long-running AI operations.
- [Get Async Job](https://www.edenai.co/docs/api-reference/universal-ai/get-async-job.md): Get details for a specific async job.
- [Delete Async Job](https://www.edenai.co/docs/api-reference/universal-ai/delete-async-job.md): Delete an async job. Users can only delete their own jobs.
- [List Collections](https://www.edenai.co/docs/api-reference/collections/list-collections.md): List the user's collections.
- [Create Collection](https://www.edenai.co/docs/api-reference/collections/create-collection.md): Create a collection on a provider.
- [Get Collection](https://www.edenai.co/docs/api-reference/collections/get-collection.md): Get one of the user's collections. Free, gateway-side only, and — like the other gateway resource reads — not registered in the request history.
- [Delete Collection](https://www.edenai.co/docs/api-reference/collections/delete-collection.md): Delete a collection.
- [List Items](https://www.edenai.co/docs/api-reference/collections/list-items.md): List the item ids stored in a collection (live from the provider).
- [Add Item](https://www.edenai.co/docs/api-reference/collections/add-item.md): Add an item to a collection.
- [Delete Item](https://www.edenai.co/docs/api-reference/collections/delete-item.md): Delete one item from a collection (by its provider-side item id).
- [List Files](https://www.edenai.co/docs/api-reference/files-management/list-files.md): List uploaded files for the authenticated user.
- [Upload File](https://www.edenai.co/docs/api-reference/files-management/upload-file.md): Upload a file for persistent storage.
- [Delete All Files](https://www.edenai.co/docs/api-reference/files-management/delete-all-files.md): Delete all uploaded files for the authenticated user.
- [Delete Files By Ids](https://www.edenai.co/docs/api-reference/files-management/delete-files-by-ids.md): Delete specific files by their IDs.
- [List management keys](https://www.edenai.co/docs/api-reference/management-keys/list-management-keys.md): Lists the organization's management keys, newest first, including revoked ones. Secrets are never returned. Requires the `manage:mint` scope.
- [Create a management key](https://www.edenai.co/docs/api-reference/management-keys/create-a-management-key.md): Creates a management key with the `manage:read` and/or `manage:write` scopes, so an automated system can manage the organization without a person in the loop. The `manage:mint` scope cannot be granted here; keys with that scope are created from the dashboard. The response includes the key's `secret`…
- [Revoke a management key](https://www.edenai.co/docs/api-reference/management-keys/revoke-a-management-key.md): Permanently revokes a `manage:read`/`manage:write` management key of the organization. Keys with the `manage:mint` scope cannot be revoked here and return 403; revoke them from the dashboard. Revoking an already revoked key is a no-op. Returns the revoked key. Requires the `manage:mint` scope.
- [Inspect the calling management key](https://www.edenai.co/docs/api-reference/management-keys/inspect-the-calling-management-key.md): Returns the organization, scopes and expiry of the management key used to authenticate the request. Any valid management key can call this endpoint, which makes it a convenient connectivity check. The key's secret is never returned.
- [List groups](https://www.edenai.co/docs/api-reference/groups/list-groups.md): Lists the organization's groups synced from its identity provider (via directory sync), ordered by name, with the emails of their active members. Groups are managed in the identity provider and are read-only here. Requires the `manage:read` scope.
- [Retrieve a group](https://www.edenai.co/docs/api-reference/groups/retrieve-a-group.md): Returns one group of the organization by its identity-provider id, with the emails of its active members. A group that belongs to another organization returns 404. Requires the `manage:read` scope.
- [List API keys](https://www.edenai.co/docs/api-reference/api-keys/list-api-keys.md): Lists every API key of the organization, including revoked ones (marked with `revoked: true`). Secrets are never returned; use `masked` to identify a key. Requires the `manage:read` scope.
- [Create an API key](https://www.edenai.co/docs/api-reference/api-keys/create-an-api-key.md): Creates a new API key for the organization, optionally attributed to a member and with spending controls. The response includes the key's `secret` exactly once; it cannot be retrieved afterwards. Returns 409 if the name is already used by one of the owner's active keys and 403 if the plan's key limi…
- [Retrieve an API key](https://www.edenai.co/docs/api-reference/api-keys/retrieve-an-api-key.md): Returns one API key of the organization by its `key_id`. A key that belongs to another organization returns 404. Requires the `manage:read` scope.
- [Revoke an API key](https://www.edenai.co/docs/api-reference/api-keys/revoke-an-api-key.md): Revokes an API key. This is permanent: the key stops authenticating immediately and cannot be re-enabled, but it stays listed with `revoked: true` for your records. Revoking an already revoked key is a no-op. Returns the revoked key. Requires the `manage:write` scope.
- [Update an API key](https://www.edenai.co/docs/api-reference/api-keys/update-an-api-key.md): Updates the display name and spending controls of an API key. Only the fields you send are changed. The environment (`token_type`) cannot be changed. Returns 409 if the new name is already used by one of the owner's active keys. Requires the `manage:write` scope.
- [Rotate an API key](https://www.edenai.co/docs/api-reference/api-keys/rotate-an-api-key.md): Replaces the secret of an API key while keeping its identity, name, budget and settings. The previous secret stops working immediately and the new one is returned exactly once in this response. A revoked key cannot be rotated and returns 404. Requires the `manage:write` scope.
- [Get an API key's usage](https://www.edenai.co/docs/api-reference/usage/get-an-api-keys-usage.md): Returns the consumption of one API key over a date window, as a time series at the requested granularity, optionally narrowed by feature, subfeature, provider or phase. A key that belongs to another organization returns 404. Without `begin`/`end` the last 7 days are returned. Requires the `manage:re…
- [Get organization usage](https://www.edenai.co/docs/api-reference/usage/get-organization-usage.md): Returns the organization's aggregated consumption over a date window, as a time series per API key at the requested granularity. Narrow it by feature, provider, member or API key, or get one total per member with `group_by=user`. Without `begin`/`end` the last 7 days are returned. Requires the `mana…
- [List members](https://www.edenai.co/docs/api-reference/members/list-members.md): Lists the organization's active members, including the owner, ordered by email. Each member includes their role, rate limits, directory groups and API keys. Requires the `manage:read` scope.
- [Set a member's role](https://www.edenai.co/docs/api-reference/members/set-a-members-role.md): Assigns a role to a member of the organization, identified by email, and returns the updated member. Role-based access control must be enabled for the organization (otherwise 409). The organization owner's role cannot be changed (403), and a management key can only assign roles limited to member man…

## OpenAPI Specs

- [openapi](https://api.edenai.run/v2/info/splitted-schema/management_api/openapi.json)
- [openapi](https://api.edenai.run/v3/docs/openapi.json)