# Eden AI (slim)

> 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.

- Full: https://www.anchorterminal.com/tools/eden-ai.md (~9,650 tokens) · this version ~1,480 tokens · JSON https://www.anchorterminal.com/tools/eden-ai.json · canonical https://www.anchorterminal.com/tools/eden-ai
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07 · pricing https://www.anchorterminal.com/tools/eden-ai#pricing · reviews https://www.anchorterminal.com/tools/eden-ai#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**C · 59.9/100 · rank #672 of 1486 · #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

- Kind: Model router · vendor: Eden AI SAS · category: Model APIs & inference · legal entity: Eden AI SAS · provenance 44/100
- Endpoint: `https://mcp.edenai.run/mcp` (HTTP, Streamable HTTP)
- Auth: API key · pricing: Pay per use · x402: no · licence: unknown
- Benchmark probes: not run yet, so Performance is pending
- Live, from our pollers (not part of the score): up at 2026-11-07 18:20 UTC · uptime 30 days 100.0% (200 probes) · p50 50 ms · p95 129 ms over 24 hours
- 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
- Prices: Platform fee on credit purchases 5.5% percentage fee

- Scores: Reliability 33, Performance pending, Schema & documentation 81, Agent ergonomics 75, Security & auth 82, Payments & pricing 30, Task success pending, Maintenance & community 58, Transparency & trust 55 · total over the 7 assessed categories
- Why: Reliability, Router, read on the hosted lines. · Schema & documentation, Router, scored on the API lines. · Agent ergonomics, Router, read on the model lines. · Security & auth, Router, read on the model lines. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, Closed service, read on the model lines. · Transparency & trust, Editorial half only.
- Sources: 14, open questions: 5, both in the full twin
- Capabilities: inference.router, inference.llm, embed.text, translate.text, translate.documents, docs.ocr, speech.stt, speech.tts, image.generate, guard.moderation
- JSON: https://www.anchorterminal.com/api/v1/tools/eden-ai.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/eden-ai.svg` or a link to https://www.anchorterminal.com/tools/eden-ai from a page on edenai.co or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.
- Support: https://www.edenai.co/contact; https://www.edenai.co/docs; more in the full twin

## Before you call it

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

```bash
curl https://api.edenai.run/v3/models
```

```bash
claude mcp add edenai --transport http https://mcp.edenai.run/mcp --header "Authorization: Bearer $EDENAI_API_KEY"
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Tencent Cloud TokenHub | C | 59.5 | inference.router, inference.llm, embed.text, image.generate, speech.tts, speech.stt, translate.text | https://www.anchorterminal.com/tools/tencent-tokenhub.min.md |
| Cloudflare Workers AI | B | 69.2 | inference.llm, embed.text, image.generate, speech.stt, speech.tts | https://www.anchorterminal.com/tools/cloudflare-workers-ai.min.md |
| DeepInfra | B | 63.7 | inference.llm, embed.text, image.generate, speech.stt, speech.tts | https://www.anchorterminal.com/tools/deepinfra.min.md |
| SiliconFlow | E | 42.9 | inference.llm, embed.text, image.generate, speech.tts, speech.stt | https://www.anchorterminal.com/tools/siliconflow.min.md |
| Vercel AI Gateway | B | 67.8 | inference.router, inference.llm, embed.text, image.generate | https://www.anchorterminal.com/tools/vercel-ai-gateway.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)