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

> Invoke an LLM endpoint and return the generated text.

# AI_QUERY

Invokes a large language model (LLM) endpoint and returns the generated text as a `TEXT` value. Provide the endpoint identifier, a plain‑text prompt in `request`, and a `LOCATION` that holds AWS Bedrock credentials.

For setup guidance and end‑to‑end examples, see [Getting started with AI](/guides/ai/getting-started-with-ai).

<Note>
  Initially, this function uses Amazon Bedrock as its backend. The `location` must reference a Bedrock `LOCATION`. For now, the only supported model is Meta Llama 3.3 70B Instruct: the `endpoint` must contain the substring `'meta.llama3-3-70b-instruct-v1:0'`.
</Note>

## Syntax

```sql theme={"theme":{"light":"github-light","dark":"github-dark"}}
AI_QUERY(<endpoint>, <request>, <location> [, <null_on_error>])
```

## Parameters

| Parameter         | Description                                                                                                                                                                                 | Supported input types |
| :---------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | :-------------------- |
| `<endpoint>`      | The LLM endpoint to invoke. Provide a Bedrock model endpoint identifier. Must contain `'meta.llama3-3-70b-instruct-v1:0'`. The value is forwarded to Bedrock without further validation.    | `TEXT`                |
| `<request>`       | The plain‑text prompt to send to the model.                                                                                                                                                 | `TEXT`                |
| `<location>`      | The name of the `LOCATION` to use for AWS credentials. Must be a literal constant. See [CREATE LOCATION (Amazon Bedrock)](/reference-sql/commands/data-definition/create-location-bedrock). | `TEXT`                |
| `<null_on_error>` | Optional. Whether to return `NULL` instead of raising an error when a Bedrock invocation error occurs. Default `FALSE`. Must be a literal constant.                                         | `BOOL`                |

## Return Type

`TEXT`

* Returns the model’s generated text.
* If `<request>` is `NULL`, the function returns `NULL`.

## LLM Token Budget

Queries executed with `AI_QUERY` count towards your account’s daily LLM token budget. If your account exceeds its allotted token budget, invocations of `AI_QUERY` will fail until the budget is increased or the daily limit resets. For details on setting and monitoring your token budget, see [Set your LLM token budget](/guides/ai/getting-started-with-ai#set-your-llm-token-budget) and [Check your LLM token quota usage](/guides/ai/getting-started-with-ai#check-your-llm-token-quota-usage).

<Note>
  LLM token budget accounting is not available in Firebolt Core.
</Note>

## Example

```sql theme={"theme":{"light":"github-light","dark":"github-dark"}}
SELECT AI_QUERY(
    'us.meta.llama3-3-70b-instruct-v1:0',
    'What is AWS?',
    'my_bedrock_location') AS result;
```

**Returns (example):**

```text theme={"theme":{"light":"github-light","dark":"github-dark"}}
'AWS (Amazon Web Services) is a cloud computing platform by Amazon.'
```