> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.cohere.com/v1/docs/model-vault/standard/api-access/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.cohere.com/_mcp/server.

# Calling a Standard Vault over the API

> Call a Standard Vault with the Cohere SDK, raw HTTP, or an OpenAI-compatible client by pointing requests at your vault endpoint URL.

Once your Standard Vault is set up in the Model Vault app, use the **Vault endpoint URL** and **model
name** shown in the model card (see [Managing Vaults](../../../docs/model-vault/managing-vaults)) in your API
calls. You authenticate with your Cohere API key.

You can call a Standard Vault three ways: the **Cohere SDK**, **raw HTTP**, or an **OpenAI-compatible**
client. In every case you point the request directly at your vault endpoint instead of the default
Cohere API base URL.

> **Note**
>
> This page covers **Standard Vaults**, where clients connect directly to the vault endpoint. An
> **Encrypted Vault** uses the same request and response shapes, but traffic must go through an
> attestation-verifying client or proxy. See
> [Calling an Encrypted Vault over the API](../../../docs/model-vault/encrypted/api-usage).

## Cohere SDK

Point the Cohere SDK at your vault endpoint with `base_url`:

**`PYTHON`**

```python PYTHON
import cohere

co = cohere.ClientV2(
    api_key="<COHERE_API_KEY>",
    base_url="<YOUR_VAULT_ENDPOINT_URL>",
)

response = co.chat(
    model="<YOUR_VAULT_MODEL_NAME>",
    messages=[{"role": "user", "content": "Hello from Model Vault!"}],
)

print(response.message.content[0].text)
```

## Raw HTTP

If you don't use the SDK, call the vault endpoint directly over HTTP. Send your API key as a bearer
token and use the same request body as the Cohere API:

**`cURL`**

```bash cURL
curl "<YOUR_VAULT_ENDPOINT_URL>/v2/chat" \
  -H "Authorization: bearer <COHERE_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<YOUR_VAULT_MODEL_NAME>",
    "messages": [{"role": "user", "content": "Hello from Model Vault!"}]
  }'
```

## OpenAI-compatible API

For existing OpenAI integrations, point an OpenAI-compatible client at your vault's compatibility base
URL (`<YOUR_VAULT_ENDPOINT_URL>/compatibility/v1`) and use your Cohere API key:

**`PYTHON`**

```python PYTHON
from openai import OpenAI

client = OpenAI(
    api_key="<COHERE_API_KEY>",
    base_url="<YOUR_VAULT_ENDPOINT_URL>/compatibility/v1",
)

response = client.chat.completions.create(
    model="<YOUR_VAULT_MODEL_NAME>",
    messages=[{"role": "user", "content": "Hello from Model Vault!"}],
)

print(response.choices[0].message.content)
```

## Chat, Embed, and Rerank

The chat example above points the SDK at your vault. Embed and Rerank requests work the same way:
keep the `base_url` pointed at your vault endpoint and call `co.embed(...)` or `co.rerank(...)` with
your vault's model name.

## Next steps

* [Calling an Encrypted Vault over the API](../../../docs/model-vault/encrypted/api-usage)
* [Managing Vaults](../../../docs/model-vault/managing-vaults)
* [Monitoring](../../../docs/model-vault/monitoring)

> Cohere's API documentation helps developers easily integrate natural language processing and generation into their products.