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

# Overview

> Run LLM inference on Pinata with an OpenAI-compatible API

Pinata Inference is a hosted, OpenAI-compatible LLM endpoint. Enable it on your account, then use it two ways:

* **API** — point any OpenAI-compatible client at Pinata and call [chat completions](https://docs.pinata.cloud/inference/chat-completions.md) directly, no agent required.
* **Agents app** — the same hosted models show up alongside your other providers in an agent's [Models](https://docs.pinata.cloud/agents/models.md) list (connect the **Pinata** provider in the [Secrets Vault](https://docs.pinata.cloud/agents/secrets.md#connect-a-provider)).

Either way, requests run against the [models](https://docs.pinata.cloud/inference/models.md) Pinata hosts, and usage is metered and drawn down from your [credit balance](https://docs.pinata.cloud/inference/credits.md).

> [!NOTE]
>
> Inference is billed through credits. Before your first request, make sure your workspace has a credit balance and (optionally) [auto top-up](https://docs.pinata.cloud/inference/credits.md#auto-top-up) enabled so requests don't fail on an empty balance.

## Enable inference

Turn Pinata-hosted inference on for your account with a single call, authenticated with your standard Pinata JWT:

```bash theme={null}
curl -X POST https://agents.pinata.cloud/v0/llm/enable \
  -H "Authorization: Bearer $PINATA_JWT"
```

```json Response theme={null}
{
  "success": true,
  "privateKey": "<your-inference-key>"
}
```

Enabling generates an Ed25519 key pair: the **private key is returned once** in this response and also stored encrypted in your [secrets](https://docs.pinata.cloud/agents/secrets.md) as `PINATA_LLM_KEY`; the public key is kept for request validation.

> [!WARNING]
>
> The `privateKey` is your inference credential — it's what authenticates [chat completions](https://docs.pinata.cloud/inference/chat-completions.md), **not** your Pinata JWT. Save it now; it isn't returned again.

Once enabled, the [chat completions endpoint](https://docs.pinata.cloud/inference/chat-completions.md) accepts requests and usage starts drawing down your [credit balance](https://docs.pinata.cloud/inference/credits.md).

> [!TIP]
>
> Prefer the dashboard? Connecting the **Pinata** provider in the [Secrets Vault](https://docs.pinata.cloud/agents/secrets.md#connect-a-provider) does the same thing, and is also how Pinata-hosted models become selectable inside your agents.

### Check status

```bash theme={null}
curl https://agents.pinata.cloud/v0/llm/status \
  -H "Authorization: Bearer $PINATA_JWT"
```

```json Response theme={null}
{ "enabled": true, "createdAt": "2026-06-29T00:00:00.000Z" }
```

## Disable inference

```bash theme={null}
curl -X DELETE https://agents.pinata.cloud/v0/llm/disable \
  -H "Authorization: Bearer $PINATA_JWT"
```

```json Response theme={null}
{ "success": true }
```

Disabling revokes the inference key and removes the associated secrets. New requests to the chat completions endpoint are rejected and Pinata-hosted models are no longer selectable in agents — any running agents using the managed key are automatically flipped to the [free tier](https://docs.pinata.cloud/agents/models.md#free-tier-agents) fallback so they don't break. Your credit balance is untouched — disabling does not refund or expire credits — and you can re-enable at any time (which mints a **new** `privateKey`).

> [!WARNING]
>
> Disabling takes effect immediately. Any in-flight requests may be cut off, and anything pointing at the endpoint will start getting errors until you re-enable.

## Authentication

There are two credentials, used for different routes:

| Routes | Credential |
| - | - |
| **Management** — `enable`, `disable`, `status` | Your **Pinata JWT** (from [Account → API Keys](https://docs.pinata.cloud/account-management/api-keys.md)) |
| **Inference** — `chat/completions` | The **`privateKey`** returned when you enabled (stored as the `PINATA_LLM_KEY` secret) |
| **Catalog** — `models` | None — public |

```http theme={null}
# Management
Authorization: Bearer <PINATA_JWT>

# Inference
Authorization: Bearer <PINATA_LLM_KEY>
```

## Next steps

> [card] [Chat Completions](https://docs.pinata.cloud/inference/chat-completions.md)
>
> Call the OpenAI-compatible endpoint

> [card] [Models](https://docs.pinata.cloud/inference/models.md)
>
> See which models Pinata hosts

> [card] [Credits](https://docs.pinata.cloud/inference/credits.md)
>
> Fund usage and set auto top-up


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.