# Eden AI > Eden AI is a French AI gateway with one OpenAI-compatible API key for about 1,000 chat and expert models from 80 or more providers, including OCR, speech, translation and image analysis, with an EU-only endpoint and a hosted MCP server. - Canonical: https://www.anchorterminal.com/tools/eden-ai - Pricing: https://www.anchorterminal.com/tools/eden-ai#pricing - Reviews: https://www.anchorterminal.com/tools/eden-ai#reviews - Markdown: https://www.anchorterminal.com/tools/eden-ai.md (~9,650 tokens) - Slim: https://www.anchorterminal.com/tools/eden-ai.min.md (~1,480 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/eden-ai.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key) - DNS: dig +short TXT eden-ai.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.. and .vs.. under the zone, and the same under grade.letme.dev) - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) - Updated: 2026-11-07 ## Overview **Grade C · 59.9/100 · rank #675 of 1510 · #22 in Model APIs & inference · not agent-ready · confidence medium** ## Assessment Eden AI gives one OpenAI-compatible key to about 1,000 models and expert models such as OCR, speech and translation, with an EU-only endpoint, per-key guardrails and no stored content by default. No status page, SLA or changelog was found, and its own pages disagree on the default rate limit. ## Facts | Field | Value | | --- | --- | | Vendor | Eden AI SAS (https://www.edenai.co) | | Kind | Model router | | Category | Model APIs & inference (https://www.anchorterminal.com/categories/inference) | | Transport | HTTP, Streamable HTTP | | Endpoint | `https://mcp.edenai.run/mcp` | | Auth | API key · Bearer key created in the dashboard at app.edenai.run after a browser signup. Keys carry budgets, expiry and attribution, can be managed through a key API, and can be limited to chosen models by deny-by-default guardrails. The MCP server takes the same key in the Authorization header. | | Pricing | Pay per use (5.5% fee) · Provider list prices with no markup plus a 5.5% platform fee applied when buying credits. Prepaid credits through Stripe by card, PayPal or bank transfer, with optional auto-refill. Some models are billed $0 for tests. The Advanced plan is by quote. | | x402 | No · No x402, MPP or L402 in llms.txt, the OpenAPI spec, the pricing pages or the agent catalogue (checked 2026-11-06). Credits are bought through Stripe. | | Licence | unknown | | Docs | https://www.edenai.co/docs | | llms.txt | https://www.edenai.co/llms.txt | | Last release | 2026-11-05 | | Surface listed | The v3 API at api.edenai.run (and api.eu.edenai.run) and the hosted MCP server at mcp.edenai.run, read from llms.txt, the docs, the OpenAPI spec, the pricing, terms, DPA, security and about pages and the edenai/docs repository on 6 November 2026. No account was made, no key was used and no MCP session was opened | | Category | Listed under model APIs and inference as a router. Translation, which the sweep suggested, is two of about 40 expert models | | Endpoints | Chat completions, Responses, Anthropic Messages, embeddings, rerank, images, audio, videos, batches, moderations, search, a Universal AI endpoint for expert models, and management routes for keys, members, groups and routing policies | | Expert models | OCR and parsers (invoices, IDs, resumes, tables), speech-to-text and text-to-speech, translation and document translation, image generation and detection, text moderation and NER, web search, scraping and crawling | | Rate limits | 10 requests a second per account on the rate-limits page, 7 raisable to 15 on the plans page, shared across keys; higher on the Advanced plan | | Data handling | No content stored by default, metadata logged for billing, opt-in log retention, async results 7 days, enforceable Zero Data Retention and region rules | | Company | Founded and headquartered in Lyon, France, 25 or more employees and $4.5 million raised, per the about page | | Legal entity | Eden AI SAS, 19 rue Louis Guérin, 69100 Villeurbanne, France, under French law with courts in Lyon | | Capabilities | inference.router, inference.llm, embed.text, translate.text, translate.documents, docs.ocr, speech.stt, speech.tts, image.generate, guard.moderation | | Tags | hosted, router, openai-compatible, usage-priced, prepaid, mcp, remote-mcp, api-key, llms-txt, openapi, eu, eu-region, soc2, iso27001, batch, closed-source | | JSON | https://www.anchorterminal.com/api/v1/tools/eden-ai.json | ## Score breakdown (methodology v0.7, October 2026 research run) Assessed 2026-11-06 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 33 | 6.6 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 81 | 13.2 | | Agent ergonomics | 13% | 16.2 | 75 | 12.2 | | Security & auth | 14% | 17.5 | 82 | 14.3 | | Payments & pricing | 10% | 12.5 | 30 | 3.8 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 58 | 5.1 | | Transparency & trust (editorial 65, provenance 44) | 7% | 8.8 | 55 | 4.8 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **59.9 → C** | ### Why each score - Reliability 33 (checked 2026-11-06): Router, read on the hosted lines. No status page is linked from the site or docs, and status.edenai.co didn't resolve for us on 6 November 2026 (0). No incident history to read (5). The rate-limits page gives 10 requests a second per account, shared across keys, while the plans page gives 7 a second, raisable to 15, so the figure is documented but inconsistent (10). Fallback retries the next model or provider on a 429 or error inside one request, but no client-facing 429 or Retry-After guidance was found (8). No SLA published; 'Dedicated support & SLA' is listed only for the custom Advanced plan, and the pricing page's '99.99%' uptime is a claim without a status page behind it (0). The v3 API is GA (10). 0+5+10+8+0+10 = 33. - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 81 (checked 2026-11-06): Router, scored on the API lines. OpenAPI 3.1 document for v3 (version 3.0.0, 46 paths) at api.edenai.run/v3/docs/openapi.json, plus a management API spec (25). llms.txt on the site and in the docs, llms-full.txt and Markdown pages (10). llms.txt states when to use Eden AI and when not to, and the docs separate chat models from expert models (17). Requests follow the OpenAI shape, and expert-model tools on the MCP server carry JSON Schema inputs (12). Examples throughout, but the spec documents only 200, 201, 202, 302 and 422, while llms.txt names 401 and 451 for region refusals (10). Versioned /v3 path, but no public changelog was found (7). 25+10+17+12+10+7 = 81. - Agent ergonomics 75 (checked 2026-11-06): Router, read on the model lines. Chat completions, Responses and an Anthropic Messages route in the OpenAI shape, with tool calling depending on the routed model (14 of 20) and structured output likewise (10 of 15). Caching is named in the terms as part of the service, without a per-model price table we read (8 of 15). Context depends on the model; the keyless /v3/models catalogue lists capabilities, prices and regions per model so an agent can choose (12 of 15). A Batches API (10 of 10). No SDK of its own; the docs use the OpenAI Python and TypeScript SDKs, and a hosted MCP server exposes about 40 expert-model tools plus upload_file, check_job and list_models (21 of 25). 14+10+8+12+10+21 = 75. - Security & auth 82 (checked 2026-11-06): Router, read on the model lines. Bearer keys with per-key budgets, expiry and attribution, a key management API, and deny-by-default guardrails that limit models per member, role or key (25). The data retention page says request and response content isn't stored and data isn't used to train models by default (18). Content logging is opt-in, async results are deleted after 7 days, and an organisation can enforce Zero Data Retention and region rules; the EU endpoint refuses non-EU models with 451 (13). Cost and provider per response, and a monitoring dashboard by key (12). The security page says Eden AI is SOC 2 and ISO 27001 certified and links a trust centre; /.well-known/security.txt returns 404 and no disclosure policy was found (14). 25+18+13+12+14 = 82. - Payments & pricing 30 (checked 2026-11-06): No x402, MPP or L402 (0). Provider prices with no markup plus a 5.5% platform fee, published per model in the keyless catalogue (20). llms.txt says some models are billed $0 for tests, but whether a new account can call them without buying credits isn't stated (10). A person signs up in a browser and buys credits through Stripe (0). 0+20+10+0 = 30. - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 58 (checked 2026-11-06): Closed service, read on the model lines. The docs repository changed on 5 and 6 November 2026, including retiring Nova Reel and Veo from video generation, and the terms were updated 22 October (30). No public changelog, so dated API changes in the last 90 days come only from docs commits (12 of 20). Chat support within 48 working hours, no public changelog (8). No SDK of its own, and the MCP server isn't in the official MCP registry (5). Nothing to judge package health by beyond the docs repository (3). 30+12+8+5+3 = 58. - Transparency & trust 55 (checked 2026-11-06): Editorial half only. Closed service under terms last updated 22 October 2026, naming Eden AI SAS and French law with courts in Lyon (15). The data retention page, terms and DPA agree that content isn't stored by default, and the docs carry a per-provider table of training, retention and ZDR (27). No deprecation policy found; models are dropped in docs updates without dated notice that we found (5). The DPA's Annex 2 names operational subprocessors (AWS EMEA, ClickHouse, Sentry, Metabase, Stripe, Brevo and others) with their roles, and the EU endpoint keeps routing in the EU (18). 15+27+5+18 = 65. Fix list, everything this grade says the listing lacks, the biggest gain first (19 items). What it covers is at https://www.anchorterminal.com/fixes/eden-ai.md (JSON https://www.anchorterminal.com/fixes/eden-ai.json). The whole list for a coding agent comes from `POST https://www.anchorterminal.com/api/v1/fix-list` with `{"listing": "eden-ai", "plan": "read"}`, free while the beta runs ### What we couldn't check - unchecked: whether a status page exists elsewhere; none is linked and status.edenai.co didn't resolve on 6 November 2026 - The default rate limit differs between the rate-limits page (10 requests a second) and the plans page (7, raisable to 15) - unchecked: whether the $0 test models can be called before any credit purchase - Category changed from the sweep's translation to inference, because the main surface is an OpenAI-compatible model gateway and translation is two of about 40 expert models - Founders aren't named on the about page, and investor logos carry no names ### Sources - site llms.txt: (seen 2026-11-06) - docs llms.txt: (seen 2026-11-06) - OpenAPI v3: (seen 2026-11-06) - rate limits: (seen 2026-11-06) - plans and pricing: (seen 2026-11-06) - MCP server: (seen 2026-11-06) - data retention: (seen 2026-11-06) - fallback: (seen 2026-11-06) - pricing: (seen 2026-11-06) - terms of service: (seen 2026-11-06) - DPA: (seen 2026-11-06) - security page: (seen 2026-11-06) - about page: (seen 2026-11-06) - docs repository history: (seen 2026-11-06) ## Score history Every move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/eden-ai/history.json - 2026-11-06: graded 59.9 C (methodology 0.7) ## Who's behind it (provenance 44/100, checked 2026-11-06) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | Eden AI SAS | 20/20 | | Domain age | edenai.co, no registry record we could read | 0/15 | | Endpoint on the vendor's domain | mcp.edenai.run is not on edenai.co | 0/15 | | Terms of service | read, states 6 of the 7 things a reader expects | 9.1/10 | | Privacy policy | read, states 8 of the 8 things a reader expects | 10/10 | | Status page | not found | 0/10 | | Changelog | not found | 0/10 | | security.txt | not found | 0/10 | | People named | 2 named with their role, none with a public profile | 7/10 | | Support route | help pages | 5/5 | The terms, last updated 22 October 2026, name Eden AI SAS, share capital €4,992, 19 rue Louis Guérin, 69100 Villeurbanne, France, under French law with courts in Lyon. The API and MCP server run on edenai.run, a second domain of the same company, while the site and docs are on edenai.co. robots.txt on www.edenai.co allows all agents and carries `Content-Signal: search=yes, ai-input=yes, ai-train=yes`. /.well-known/security.txt returns 404. No status page is linked, and status.edenai.co didn't resolve on 6 November 2026. RDAP for edenai.co wasn't read: rdap.org rate-limited us and the .co registry server wasn't tried. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service** (https://www.edenai.co/terms), read 2026-11-06, dated 2026-10-22, states 6 of the 7 things a reader expects. - To know. Says access can be ended without notice or for any reason. "11.1 You may stop using the Service and close your account at any time." - Gives the date it was last updated. Last updated 2026-10-22. - Names the governing law or courts. Disputes go to the courts of Lyon, France. - States a limit on its liability. Capped at the fees paid in the 12 months before the claim. - Not found in the text. Says how changes to the terms are announced. **Privacy policy** (https://www.edenai.co/privacy), read 2026-11-06, dated 2026-10-22, states 8 of the 8 things a reader expects. - Gives the date it was last updated. Last updated 2026-10-22. - Says how long data is kept. Names a period of seven days. - Says whether personal data is sold or shared for advertising. Says it does not sell personal data. - Says where data is transferred or stored. Relies on standard contractual clauses. ## Humans behind the project (researched 2026-11-06 from public pages, not part of the grade) ### Key people - Taha Zemmouri, Co-founder and CEO - Samy Melaine, Co-founder and CTO - Note: Eden AI's own seed post names Taha Zemmouri (CEO) and Samy Melaine (CTO) as co-founders, and its byline calls Taha Zemmouri CEO and co-founder; the March 2022 press release on its blog also names Taha Zemmouri as CEO. The about page, read on 6 November 2026, says the company was founded in Lyon and has raised $4.5 million; the terms name Eden AI SAS of Villeurbanne. Investors come from Eden AI's two funding posts: the €1.5M round of March 2022, backed by the 50 Partners accelerator and business angels, and the €3M seed led by Galion.exe with 50 Partners and angels, which tech.eu dated 21 November 2024 (the post itself carries only its republication date). Journal du Net described that round as €2M of equity and €1M of debt; only the company's figure is used. No valuation was stated. Personal accounts weren't linked from the pages read. - Eden AI: LinkedIn https://www.linkedin.com/company/edenai X https://x.com/EdenAIco GitHub https://github.com/edenai ### Ownership and investors - Raised: $4.5M in total, as of November 2026 (source https://www.edenai.co/about) - Backed by: Galion.exe, 50 Partners, Olivier Pomel, Sébastien Pahl, Alix de Sagazan, Nicolas Dessaigne, Julien Lemoine, Benjamin Fabre, Laurent Letourmy, Jean-Baptiste Aviat, Georges Gomes, Thomas Grange ### Getting support - Help: https://www.edenai.co/contact - Help: https://www.edenai.co/docs - Sources: https://www.edenai.co/about, https://www.edenai.co/terms, https://www.edenai.co/pricing, https://www.edenai.co/docs/v3/overview/plans-prices.md, https://www.edenai.co/post/eden-ai-raises-1-5-million-to-build-the-future-of-ai-as-a-service, https://www.edenai.co/post/eden-ai-raises-eu3m-to-bridge-the-gap-between-ai-models-and-business-needs, https://tech.eu/2024/11/21/eden-ai-raises-3m-seed-for-ai-interoperability/ ## Live (updated 2026-11-07 22:55 UTC) - Right now: up, HTTP 405, 89 ms, checked 2026-11-07 22:55 UTC (get on `https://mcp.edenai.run/mcp`) - Uptime 24h 100.0% (244 probes) · 30 days 100.0% (246 probes) · p50 51 ms · p95 129 ms - security.txt: none - Watching privacy - Watching terms - Tools it lists (42, about 10,725 tokens of context, `tools/list` without credentials over MCP 2025-11-25, checked 2026-11-07 01:44 UTC): - `list_models`: List available providers/models and their pricing. - `list_voices`: List the voices a text-to-speech model accepts, for audio_tts's 'voice'. The model's default voice comes first. - `upload_file`: Upload a file to Eden AI and get a file ID to use in other tools. Only needed for local file content. If you already have a public URL for the file, pass that… - `check_job`: Get the status/result of an async job started by a long-running tool. - `manage_collections`: Create and manage collections: stored sets of items (e.g. faces) that a tool searches against. Tools that take a collection_id: image_face_recognition. Flow:… - `audio_speech_to_text`: 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… - `audio_tts`: Text-to-speech (TTS) is a technology that converts written text into spoken audio, enabling computers and digital devices to "read" text aloud. It is also… - `image_ai_detection`: Determine whether an image was generated by AI or is a real photograph or artwork. File parameters accept a file ID from upload_file or a direct file URL — if… - `image_anonymization`: Image Anonymization API, also known as image de-identification or image de-personalization, refers to the process of automatically removing personal or… - `image_background_removal`: Background removal is a digital image processing technique designed to seamlessly eliminate the backdrop of a photo, leaving behind only the main subject. File… - `image_deepfake_detection`: 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.… - `image_explicit_content`: Explicit Content Detection detects adult only content in images, that is generally inappropriate for people under the age of 18 and includes nudity, sexual… - `image_face_compare`: 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.… - `image_face_detection`: Face Detection is a computer technology being used in a variety of applications that identifies human faces in digital images with different attributes like… - `image_face_recognition`: Recognizing a face in an image is a more advanced feature than just detecting the face in the image. It allows the user to search for the detected face from a… - `image_generation`: Image Generation is an advanced feature that generates compelling images based on a given text prompt. It can easily produce high-quality and original images… - `image_logo_detection`: Logo Detection is a powerful technology that enables the automatic identification and recognition of popular logos within an image. It provides accurate and… - `image_object_detection`: Object Detection is a computer vision technique that allows users to identify and locate (with bounding boxes) objects in an image. The detected objects can be… - `ocr`: Optical Character Recognition or Reader (OCR) is the electronic or mechanical conversion of images of typed, handwritten or printed text into machine-encoded… - `ocr_async`: 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… - `ocr_financial_parser`: Financial Parser API is a powerful and versatile tool designed to streamline your financial data extraction process. This cutting-edge API combines Optical… - `ocr_identity_parser`: ID Document parsing technology allows users to automatically extract information from an ID Document such as passport, ID card, driving license and more. This… - `ocr_resume_parser`: Resume Parser enables users to extract various information from resumes (curriculum vitae, CV) that could be in a variety of formats and returns structured… - `ocr_tables`: OCR Table (Optical Character Recognition for tabular documents) allows users to analyze documents containing tables and returns a structured representation of… - `text_ai_detection`: 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_anonymization`: The personally identifiable information (PII) detection feature can identify and redact sensitive information in unstructured text. For example: phone numbers,… - `text_moderation`: 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… - `text_named_entity_recognition`: Named Entity Recognition (also called entity identification or extraction) is an information extraction technique that automatically identifies named entities… - `text_plagia_detection`: The Plagiarism Detection API is a tool designed to scan a content string for plagiarism using a plagiarism detection module - `text_spell_check`: 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… - `text_topic_extraction`: Topic analysis is a Natural Language Processing (NLP) technique that allows us to automatically extract meaning from text by identifying recurrent themes or… - `translation_automatic_translation`: Automatic translation or machine translation (MT) is the process of automatically translating a text from one language to another language. The aim of it is to… - `translation_document_translation`: Document Translation API translates whole documents in supported languages and various file formats (like pdf or doc) while keeping their structure intact.… - `video_deepfake_detection`: Detect deepfake and synthetically manipulated video. Returns an overall deepfake score and prediction, along with per-frame scores when the provider supplies… - `video_generation`: The Video Generation API enables easy creation of high-quality videos from text,and images, perfect for marketing, education, and more—all through one… - `web_batch_scrape`: Scrape many URLs in one request and return each page's content. Runs as an async job. Long-running: returns a job immediately; poll it with check_job(job_id)… - `web_crawl`: Crawl a site from a starting URL and return the content of its pages. Runs as an async job. Long-running: returns a job immediately; poll it with… - `web_map`: Discover and return the list of URLs on a site (a sitemap-style link map). - `web_research`: Run deep, multi-step web research on a query and return a synthesized answer with sources. Runs as an async job. Long-running: returns a job immediately; poll… - `web_scraping`: Fetch a single URL and return its clean content as markdown, text, or HTML, with optional JavaScript rendering. - `web_search`: Search the web for a query and return ranked results (title, URL, and a snippet or the page content). - `web_structured_extraction`: Extract structured data from one or more web pages against a schema or prompt. Runs as an async job. Long-running: returns a job immediately; poll it with… - How its tools read to an agent (0 errors, 49 warnings, 1 note, about 10,725 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score): - warn TC11 manage_collections: 1 parameter without a description: action - warn TC12 image_generation: no type for reference_images[] - warn TC13 web_research: schema (object with no properties) - warn TC13 web_structured_extraction: schema (object with no properties) - warn TC14 image_face_recognition: allowed values are in the description, not an enum: collection_id - warn TC14 image_generation: allowed values are in the description, not an enum: resolution - warn TC16 audio_speech_to_text: no readOnlyHint or destructiveHint - warn TC16 audio_tts: no readOnlyHint or destructiveHint - warn TC16 check_job: no readOnlyHint or destructiveHint - warn TC16 image_ai_detection: no readOnlyHint or destructiveHint - warn TC16 image_anonymization: no readOnlyHint or destructiveHint - warn TC16 image_background_removal: no readOnlyHint or destructiveHint - warn TC16 image_deepfake_detection: no readOnlyHint or destructiveHint - warn TC16 image_explicit_content: no readOnlyHint or destructiveHint - warn TC16 image_face_compare: no readOnlyHint or destructiveHint - warn TC16 image_face_detection: no readOnlyHint or destructiveHint - warn TC16 image_face_recognition: no readOnlyHint or destructiveHint - warn TC16 image_generation: no readOnlyHint or destructiveHint - warn TC16 image_logo_detection: no readOnlyHint or destructiveHint - warn TC16 image_object_detection: no readOnlyHint or destructiveHint - warn TC16 list_models: no readOnlyHint or destructiveHint - warn TC16 list_voices: no readOnlyHint or destructiveHint - warn TC16 manage_collections: no readOnlyHint or destructiveHint - warn TC16 ocr: no readOnlyHint or destructiveHint - Always current: https://www.anchorterminal.com/api/v1/live/eden-ai.json ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Prices | Item | Price | Unit | Note | | --- | --- | --- | --- | | Platform fee on credit purchases | 5.5% | percentage fee | On top of provider list prices, which carry no markup | Across all listings: https://www.anchorterminal.com/prices/index.md ## Strengths - OpenAI-compatible v3 API with an OpenAPI 3.1 spec and a keyless model catalogue with prices and regions - EU endpoint that refuses models not cleared for European processing with HTTP 451 - Content isn't stored or used for training by default, with opt-in logs and enforceable Zero Data Retention - Per-key budgets, expiry and deny-by-default guardrails, plus a key management API - Hosted MCP server exposing OCR, speech, translation, web search and other expert models as tools ## Weaknesses - No public status page, incident history or SLA found - The rate-limits page says 10 requests a second and the plans page says 7, raisable to 15 - No public changelog or deprecation policy - The OpenAPI spec documents few error responses - Credits are prepaid through Stripe with a 5.5% platform fee on every purchase ## Before you call it (notes for agents) 1. Read GET https://api.edenai.run/v3/models at run time for model ids, prices and regions instead of hard-coding them 2. Use https://api.eu.edenai.run/v3 when data must stay in the EU, and pick another model on a 451 region_not_allowed 3. Set max_tokens to 500 or more for reasoning models, or the answer can come back empty 4. Pass a fallbacks list so a provider 429 or error retries inside one request 5. Poll check_job for MCP tools marked long-running instead of calling them again ## Connect First request: ```bash curl https://api.edenai.run/v3/models ``` Claude Code: ```bash claude mcp add edenai --transport http https://mcp.edenai.run/mcp --header "Authorization: Bearer $EDENAI_API_KEY" ``` MCP client configuration: ```json { "mcpServers": { "edenai": { "headers": { "Authorization": "Bearer YOUR_EDENAI_API_KEY" }, "url": "https://mcp.edenai.run/mcp" } } } ``` ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | Tencent Cloud TokenHub | C | 59.5 | 703 | inference.router, inference.llm, embed.text, image.generate, speech.tts, speech.stt, translate.text | no | https://www.anchorterminal.com/tools/tencent-tokenhub.md | | Cloudflare Workers AI | B | 69.2 | 256 | inference.llm, embed.text, image.generate, speech.stt, speech.tts | no | https://www.anchorterminal.com/tools/cloudflare-workers-ai.md | | DeepInfra | B | 63.7 | 501 | inference.llm, embed.text, image.generate, speech.stt, speech.tts | no | https://www.anchorterminal.com/tools/deepinfra.md | | SiliconFlow | E | 42.9 | 1266 | inference.llm, embed.text, image.generate, speech.tts, speech.stt | no | https://www.anchorterminal.com/tools/siliconflow.md | | Vercel AI Gateway | B | 67.8 | 303 | inference.router, inference.llm, embed.text, image.generate | no | https://www.anchorterminal.com/tools/vercel-ai-gateway.md | | Lemonade | B | 63.9 | 494 | embed.text, speech.stt, speech.tts, image.generate | no | https://www.anchorterminal.com/tools/lemonade.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - EU endpoint https://api.eu.edenai.run/v3 refuses any model not cleared for European processing with HTTP 451 region_not_allowed before a provider is contacted (source: ) - Keyless model catalogue at GET https://api.edenai.run/v3/models with each model's capabilities, pricing and regions (source: ) - Every chat response adds `cost` in USD and the `provider` that served it to the OpenAI shape (source: ) - Request and response content isn't stored or used for training by default; async results are kept 7 days (source: ) - Hosted MCP server at https://mcp.edenai.run/mcp with one tool per expert feature plus upload_file, check_job and list_models (source: ) - The security page says Eden AI is SOC 2 and ISO 27001 certified (source: ) - #22 of 42 in Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md - All 830 models comparisons: https://www.anchorterminal.com/compare/inference/index.md ## Compare - [Amazon Bedrock vs Eden AI](https://www.anchorterminal.com/compare/amazon-bedrock-vs-eden-ai.md): A 81.7 vs C 59.9 - [Claude API vs Eden AI](https://www.anchorterminal.com/compare/anthropic-api-vs-eden-ai.md): BB 77.3 vs C 59.9 - [Azure OpenAI in Foundry Models vs Eden AI](https://www.anchorterminal.com/compare/azure-openai-vs-eden-ai.md): A 80 vs C 59.9 - [BlockRun.AI vs Eden AI](https://www.anchorterminal.com/compare/blockrun-ai-vs-eden-ai.md): A 78.9 vs C 59.9 - [Cerebras Inference vs Eden AI](https://www.anchorterminal.com/compare/cerebras-inference-vs-eden-ai.md): B 68.6 vs C 59.9 - [Cloudflare AI Gateway vs Eden AI](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-eden-ai.md): B 67.8 vs C 59.9 - [Cloudflare Workers AI vs Eden AI](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-eden-ai.md): B 69.2 vs C 59.9 - [Cohere Chat API (Command models) vs Eden AI](https://www.anchorterminal.com/compare/cohere-chat-vs-eden-ai.md): B 65.6 vs C 59.9 - [DeepInfra vs Eden AI](https://www.anchorterminal.com/compare/deepinfra-vs-eden-ai.md): B 63.7 vs C 59.9 - [DeepSeek API vs Eden AI](https://www.anchorterminal.com/compare/deepseek-api-vs-eden-ai.md): D 46.7 vs C 59.9 - [Eden AI vs Glimpse](https://www.anchorterminal.com/compare/eden-ai-vs-elorian-glimpse.md): C 59.9 vs F 35.1 - [Eden AI vs Fireworks AI Inference](https://www.anchorterminal.com/compare/eden-ai-vs-fireworks-inference.md): C 59.9 vs B 69.3 - [Eden AI vs Gemini Developer API](https://www.anchorterminal.com/compare/eden-ai-vs-gemini-api.md): C 59.9 vs B 62.2 - [Eden AI vs GroqCloud](https://www.anchorterminal.com/compare/eden-ai-vs-groq.md): C 59.9 vs BB 74.5 - [Eden AI vs Inkling 2 Small](https://www.anchorterminal.com/compare/eden-ai-vs-inkling-2-small.md): C 59.9 vs D 52.1 - [Eden AI vs Jais 3](https://www.anchorterminal.com/compare/eden-ai-vs-jais-3.md): C 59.9 vs D 52.1 - [Eden AI vs Meta Model API](https://www.anchorterminal.com/compare/eden-ai-vs-meta-model-api.md): C 59.9 vs D 52.3 - [Eden AI vs MiniMax API](https://www.anchorterminal.com/compare/eden-ai-vs-minimax-api.md): C 59.9 vs C 55.3 - [Eden AI vs Mistral AI API](https://www.anchorterminal.com/compare/eden-ai-vs-mistral-api.md): C 59.9 vs B 65.7 - [Eden AI vs Muse Spark Open](https://www.anchorterminal.com/compare/eden-ai-vs-muse-spark-open.md): C 59.9 vs D 53.4 - [Eden AI vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/eden-ai-vs-nemotron-3-5-super-vl.md): C 59.9 vs C 59.3 - [Eden AI vs Novita AI](https://www.anchorterminal.com/compare/eden-ai-vs-novita-ai.md): C 59.9 vs D 53.9 - [Eden AI vs OpenAI API](https://www.anchorterminal.com/compare/eden-ai-vs-openai-api.md): C 59.9 vs A 83.9 - [Eden AI vs Prism Inference](https://www.anchorterminal.com/compare/eden-ai-vs-prism-inference.md): C 59.9 vs C 59.6 - [Eden AI vs Beam 1.0](https://www.anchorterminal.com/compare/eden-ai-vs-reflection-beam.md): C 59.9 vs D 53.4 - [Eden AI vs SambaCloud](https://www.anchorterminal.com/compare/eden-ai-vs-sambanova.md): C 59.9 vs B 64.9 - [Eden AI vs SiliconFlow](https://www.anchorterminal.com/compare/eden-ai-vs-siliconflow.md): C 59.9 vs E 42.9 - [Eden AI vs Simplismart](https://www.anchorterminal.com/compare/eden-ai-vs-simplismart.md): C 59.9 vs F 29.5 - [Eden AI vs StepFun API](https://www.anchorterminal.com/compare/eden-ai-vs-stepfun-api.md): C 59.9 vs E 44.3 - [Eden AI vs SWE-2 Flash](https://www.anchorterminal.com/compare/eden-ai-vs-swe-2-flash.md): C 59.9 vs F 36.4 - [Eden AI vs Together AI Inference](https://www.anchorterminal.com/compare/eden-ai-vs-together-inference.md): C 59.9 vs B 67.8 - [Eden AI vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/eden-ai-vs-vertex-ai.md): C 59.9 vs AA 88.7 - [Eden AI vs xAI API (Grok)](https://www.anchorterminal.com/compare/eden-ai-vs-xai-api.md): C 59.9 vs BB 71.7 - [Antseed vs Eden AI](https://www.anchorterminal.com/compare/antseed-vs-eden-ai.md): C 54.1 vs C 59.9 - [Eden AI vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/eden-ai-vs-hugging-face-inference-providers.md): C 59.9 vs C 54 - [Eden AI vs LiteLLM](https://www.anchorterminal.com/compare/eden-ai-vs-litellm.md): C 59.9 vs B 62.4 - [Eden AI vs OpenRouter](https://www.anchorterminal.com/compare/eden-ai-vs-openrouter.md): C 59.9 vs B 66.6 - [Eden AI vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/eden-ai-vs-ramp-router.md): C 59.9 vs D 53.7 - [Eden AI vs RouterPlus](https://www.anchorterminal.com/compare/eden-ai-vs-routerplus.md): C 59.9 vs D 50.3 - [Eden AI vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/eden-ai-vs-tencent-tokenhub.md): C 59.9 vs C 59.5 - [Eden AI vs Vercel AI Gateway](https://www.anchorterminal.com/compare/eden-ai-vs-vercel-ai-gateway.md): C 59.9 vs B 67.8 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on edenai.co or one of its subdomains. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "eden-ai", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html Eden AI on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Eden AI on Anchor Terminal](https://www.anchorterminal.com/badges/eden-ai.svg)](https://www.anchorterminal.com/tools/eden-ai) ``` Plain link: ```html Eden AI on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Eden AI is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/eden-ai-dark.png - Light: https://www.anchorterminal.com/assets/share/eden-ai-light.png --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp