canonical: https://jentic.com/apis/eurouter.ai/eurouter

# EUrouter API

The EUrouter API is a single gateway to AI models from OpenAI, Anthropic, Google, and other providers. It serves chat completions, text completions, structured responses, embeddings, document reranking, and speech synthesis and transcription through one endpoint and one key. Routing rules direct requests to chosen models or regions, including EU data residency, and the API also manages keys, bring-your-own-key provider credentials, and the account's credit balance.

## For AI agents

Run chat, completion, embedding, rerank, and audio requests against many LLM providers through one endpoint, and manage routing rules, keys, and credits. Authenticated with a bearer API key; model and provider listings are public.

## Scope

Does not handle model training or fine-tuning. Use for routing inference requests such as chat, embeddings, and audio across LLM providers only.

## Capabilities

- Run chat completions against models from OpenAI, Anthropic, Google, and other providers through one endpoint
- Generate text completions, structured responses, and embeddings from a single API
- Rerank documents and transcribe or synthesize audio through the same gateway
- List available models and providers and read the model count before routing a request
- Create routing rules that direct requests to chosen models or keep them in the EU for data residency
- Manage API keys and bring-your-own-key provider credentials, and read the remaining credit balance

## Use cases

### Unified Multi-Provider LLM Access

An application wants one integration for several model providers instead of wiring each separately. The EUrouter API exposes chat completions, text completions, structured responses, and embeddings through a single endpoint and key, so switching from one provider's model to another is a change of the model parameter rather than a new integration.

Example prompt: Create a chat completion against a chosen model through the chat completions endpoint, then retry the same request against a different provider's model

### EU Data-Residency Routing

A team under EU data rules needs model calls to stay in-region. The EUrouter API lets you create routing rules and read EU residency data, so requests are directed to compliant models and regions, with a dry-run available to test a rule before it takes effect.

Example prompt: Create a routing rule that keeps requests in the EU, then dry-run a routing test to confirm it before applying it

### AI Agent Model Access via Jentic

An AI agent reaches many model providers through Jentic without holding the EUrouter key itself. It searches by intent, receives the matching operation and its input schema, and runs completions or embeddings with the credential injected at run time, so a workflow can call the best model for each step through one gateway.

Example prompt: Search Jentic for 'run a chat completion', load the chat completions schema, and send a request to a chosen model with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/api/v1/chat/completions` | Create a chat completion |
| POST | `/api/v1/completions` | Create a text completion |
| POST | `/api/v1/embeddings` | Create embeddings |
| POST | `/api/v1/rerank` | Rerank documents against a query |
| POST | `/api/v1/audio/transcriptions` | Transcribe audio to text |
| GET | `/api/v1/models` | List available models |
| POST | `/api/v1/routing-rules` | Create a routing rule |
| GET | `/api/v1/credits` | Read the account credit balance |

## Key resources

- **Inference** — Run chat, completion, response, embedding, rerank, and audio requests via `/api/v1/chat/completions`, `/api/v1/completions`, `/api/v1/responses`, `/api/v1/embeddings`, `/api/v1/rerank`, and `/api/v1/audio`/*
- **Models and Providers** — List models and providers via `/api/v1/models` and `/api/v1/providers`
- **Routing and Keys** — Manage routing rules, API keys, BYOK credentials, and credits via `/api/v1/routing-rules`, `/api/v1/keys`, `/api/v1/byok`, and `/api/v1/credits`

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 67 / 100
- **Maturity:** AI-Aware
- **Dimensions:**
  - Foundational Compliance: 93 / 100
  - Developer Experience & Jentic Compatibility: 50 / 100
  - AI-Readiness & Agent Experience: 56 / 100
  - Agent Usability: 94 / 100
  - Security: 60 / 100
  - AI Discoverability: 78 / 100
- **View full report:** https://jentic.com/apis/eurouter.ai/eurouter/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring EUrouter by hand means managing its bearer key, choosing models and providers, and building routing rules for data residency yourself. Through Jentic you install once, import EUrouter from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** Limit the agent to the operations it needs, such as chat completions and embeddings, so key deletion, BYOK credential changes, and routing-rule edits are not included unless you add them. EUrouter puts key, credential, and rule ids in the URL path for its management operations, so those can be scoped by path as well.
- **Credential handling:** Your EUrouter key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'run a chat completion' or 'generate embeddings', and Jentic returns the matching EUrouter operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **OpenRouter API** — Another unified gateway routing requests to many LLM providers
- **OpenAI API** — Call OpenAI models directly when you do not need multi-provider routing
- **Mistral AI API** — A provider whose models EUrouter can route to

## FAQ

### What authentication does the EUrouter API use?

The EUrouter API authenticates with a bearer API key in the Authorization header per its OpenAPI spec. Some read operations, such as listing models, the model count, and providers, are public and need no key. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never reaches the agent.

### Which providers and models can I reach through the EUrouter API?

The EUrouter API routes to models from OpenAI, Anthropic, Google, and other providers through one endpoint. The list-models and list-providers operations return what is currently available, and the model-count operation gives the total, so an agent can discover options before sending a request.

### What are the rate limits for the EUrouter API?

The OpenAPI spec does not specify rate limits for the EUrouter API. Usage is governed by your credit balance, which the credits operation reports, so check the EUrouter documentation for current throughput limits and monitor credits to pace requests.

### How do I run a chat completion with the EUrouter API through Jentic?

Search Jentic for 'run a chat completion' and it returns the EUrouter chat completions operation with its input schema. Load the schema, set the model and messages, and the key is injected at run time. To run it on your own infrastructure, install Jentic One from its GitHub repo.

### Can I limit what my agent is allowed to do with the EUrouter API?

Yes. Write a rule that allows only the inference operations, such as chat completions and embeddings, so the agent can run models but cannot delete keys, change BYOK credentials, or edit routing rules. You choose which operations it may call, and the calls it makes are logged by your own instance.

### Is there an EUrouter API MCP server?

You don't need an MCP server to give your agent the EUrouter API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the completion, embedding, and audio operations it needs without a separate server to install.