> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.kontinent.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.kontinent.ai/_mcp/server.

# Models & sovereignty

Models are identified in `provider/model` form, e.g.
`mistral/mistral-large-latest`. List everything available to your organization
with [`GET /v1/models`](/api-reference).

```json
{
  "object": "list",
  "data": [
    {
      "id": "mistral/mistral-large-latest",
      "object": "model",
      "owned_by": "mistral",
      "kind": "chat",
      "context_length": 128000,
      "sovereignty": "strict",
      "pricing": {
        "input_micro_eur_per_mtok": 1800000,
        "output_micro_eur_per_mtok": 5400000
      }
    }
  ]
}
```

## Sovereignty tiers

Each model declares a `sovereignty` tier so you can choose how strict your data
residency requirements are:

| Tier        | Meaning                                                                  |
| ----------- | ------------------------------------------------------------------------ |
| `strict`    | Served by an **EU-owned** provider.                                      |
| `pragmatic` | Served from an **EU region** of a provider with a non-EU parent company. |

## Model kinds

| Kind        | Endpoint                                      |
| ----------- | --------------------------------------------- |
| `chat`      | [`POST /v1/chat/completions`](/api-reference) |
| `embedding` | [`POST /v1/embeddings`](/api-reference)       |

Sending an embeddings model to the chat endpoint (or vice versa) is rejected;
an unknown or disabled id returns `404 model_not_found`.

## Pricing and the money unit

Money everywhere in Kontinent is **integer micro-EUR**:

> 1 EUR = 1,000,000 µEUR

Model prices are quoted **per million tokens**, split into input and output
rates. In the example above, input costs `1,800,000` µEUR/Mtok = **€1.80 per
million input tokens**, and output costs **€5.40 per million output tokens**.

Using integers avoids floating-point rounding in billing — see
[Rate limits & credits](/rate-limits) for how spend is metered.