> ## Documentation Index
> Fetch the complete documentation index at: https://docs.valkyrieapp.azumo.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Inference API

> Call your deployed Valkyrie models over an OpenAI- or Anthropic-compatible API.

Valkyrie's public, client-facing API is the **inference API**: once you've
[deployed a model](/guides/deploy-model), you call it over a standard,
OpenAI-compatible (and Anthropic-compatible) endpoint from any client or SDK.

<Info>
  This is the only externally-supported programmatic surface. **Operating Valkyrie**,
  creating deployments, launching fine-tuning jobs, managing datasets, is done
  through the [dashboard](/dashboard/overview) or the [MCP server](/mcp/overview),
  not a public REST API. There is no public control-plane API to program against.
</Info>

## Base URL

```
https://valkyrie-back.azumo.com
```

<Note>
  Use the API base URL for your environment. If your organization runs a separate
  environment, substitute its host. API keys are environment-specific.
</Note>

## Endpoints

A ready deployment is addressed by its **slug**, `deployment-{id}` (for example
`deployment-213`), or by an [alias](/guides/aliases):

```
# OpenAI-compatible
POST /{deployment_slug}/v1/chat/completions
POST /{account_slug}/{alias}/v1/chat/completions

# Anthropic-compatible (Messages API)
POST /{deployment_slug}/v1/messages
POST /{deployment_slug}/v1/messages/count_tokens
POST /{account_slug}/{alias}/v1/messages
```

* **OpenAI-compatible** follows the Chat Completions contract, see
  [Chat Completions](/api-reference/chat-completions).
* **Anthropic-compatible** follows the Messages contract, so Claude clients work, see
  [Connect Claude Code](/connect/claude-code).

## Authentication

Send a **deployment API key** (`vk_dep_`):

| Header                        | Notes                                                                 |
| ----------------------------- | --------------------------------------------------------------------- |
| `X-API-Key: <key>`            | Simplest for scripts and cURL                                         |
| `Authorization: Bearer <key>` | What the OpenAI SDKs send, set the SDK `api_key` to your Valkyrie key |
| `x-api-key: <key>`            | What the Anthropic SDKs send                                          |

See [Authentication](/api-reference/authentication).

## Compatibility

Because the inference API is OpenAI- and Anthropic-compatible, you can use the
official SDKs, LangChain, and most third-party clients by pointing them at your
deployment's base URL. See [Connect a model](/connect/overview).