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

# Call the Flatkey API directly

> Use the REST API with plain HTTP, no SDK required. Covers the base URL, authentication, the endpoints available, and error handling.

Base URL: `https://router.flatkey.ai`

Flatkey exposes an OpenAI-compatible REST API. If you already have an HTTP client, you do not need an SDK. This page is the shortest path from a key to a working request.

## Authenticate

Every request carries your key as a bearer token:

```http theme={"dark"}
Authorization: Bearer YOUR_FLATKEY_API_KEY
```

Create a key in the [console](https://console.flatkey.ai). Keys start with `sk-fk-`. Store it in an environment variable and keep it out of source control and browser code.

```bash theme={"dark"}
export FLATKEY_API_KEY="sk-fk-..."
```

## Send a request

```bash theme={"dark"}
curl --fail-with-body -sS https://router.flatkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $FLATKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'
```

A successful call returns the standard chat completion object with `choices` and `usage`.

## Available endpoints

| Endpoint                      | Purpose                                                                    |
| ----------------------------- | -------------------------------------------------------------------------- |
| `POST /v1/chat/completions`   | [Text and chat generation](/api-reference/chat-completions)                |
| `POST /v1/responses`          | [Responses API](/api-reference/responses), for OpenAI models               |
| `POST /v1/images/generations` | [Image generation and editing](/api-reference/image-generation)            |
| `POST /v1/videos`             | [Video generation](/api-reference/seedance-video-generation), asynchronous |
| `GET /v1/videos/{task_id}`    | Poll a video task                                                          |
| `GET /v1/models`              | [List available models](/api-reference/models)                             |
| `GET /v1/credits`             | Remaining balance                                                          |

<Warning>
  `POST /v1/responses` currently works with OpenAI models. Other families return an error on this endpoint — use `POST /v1/chat/completions` for them.
</Warning>

## Check your balance

```bash theme={"dark"}
curl --fail-with-body -sS https://router.flatkey.ai/v1/credits \
  -H "Authorization: Bearer $FLATKEY_API_KEY"
```

```json theme={"dark"}
{ "remaining": 34.18, "used": 185.13 }
```

## Handle errors

Errors return a JSON body with a message you can act on:

```json theme={"dark"}
{ "error": { "message": "No available channel for model ..." } }
```

| Status       | Meaning                    | What to do                                            |
| ------------ | -------------------------- | ----------------------------------------------------- |
| `400`        | Malformed request          | Read the message; it names the offending field        |
| `401`        | Invalid key                | Check the `Authorization` header and key value        |
| `429`        | Too many requests          | Back off and retry                                    |
| `500`, `503` | Model or route unavailable | Switch models. Retrying the same one rarely clears it |

Full list in the [error reference](/api-reference/errors).

## Next steps

<CardGroup cols={2}>
  <Card title="API reference" icon="code" href="/api-reference/overview">
    Every endpoint, parameter, and response field.
  </Card>

  <Card title="Use an SDK instead" icon="plug" href="/guides/openai-sdk">
    Keep your OpenAI or Anthropic client and change one line.
  </Card>
</CardGroup>