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

# Enterprise LLM Endpoint

> A dedicated, OpenAI-compatible LLM endpoint for one model at a fixed enterprise price. Use any OpenAI SDK by changing only the base URL and API key.

An Enterprise LLM Endpoint gives your team one large language model behind a private API key, at a fixed enterprise price. The endpoint is **OpenAI-compatible**: any OpenAI SDK, framework, or tool works when you change the base URL and the API key.

> [!NOTE]
>
> Your plan is set to **one model**. The server always uses that model, whatever value you send in `model`. The response's `model` field shows the model that answered.

## Quick start

| Setting | Value |
| - | - |
| Base URL | `https://modelslab.com/api/v1/enterprise/proxy/v1` |
| API key | Your enterprise API key, sent as `Authorization: Bearer <key>` |
| Model | Any value. The server uses your plan's model |

```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}}
from openai import OpenAI

client = OpenAI(
    base_url="https://modelslab.com/api/v1/enterprise/proxy/v1",
    api_key="YOUR_ENTERPRISE_API_KEY",
)

response = client.chat.completions.create(
    model="default",
    messages=[{"role": "user", "content": "Write a haiku about GPUs."}],
)
print(response.choices[0].message.content)
```

```javascript Node.js theme={"theme":{"light":"github-light","dark":"github-dark"}}
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://modelslab.com/api/v1/enterprise/proxy/v1",
  apiKey: "YOUR_ENTERPRISE_API_KEY",
});

const response = await client.chat.completions.create({
  model: "default",
  messages: [{ role: "user", content: "Write a haiku about GPUs." }],
});
console.log(response.choices[0].message.content);
```

```bash cURL theme={"theme":{"light":"github-light","dark":"github-dark"}}
curl https://modelslab.com/api/v1/enterprise/proxy/v1/chat/completions \
  -H "Authorization: Bearer $ENTERPRISE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "default",
    "messages": [{"role": "user", "content": "Write a haiku about GPUs."}]
  }'
```

## What you get

* **The full request body passes through.** Streaming, tools and function calling, structured output (`response_format`), reasoning settings, and prompt caching (`cache_control`) all work as the model supports them.
* **Files, images and PDFs** in the messages, as a URL or base64. See [Files, Images and PDFs](https://docs.modelslab.com/enterprise-api/llm-endpoint/files.md).
* **Streaming** with `"stream": true` returns Server-Sent Events as the model generates tokens.
* **Usage in every response.** The `usage` object reports prompt, completion, and cached tokens.
* **A fixed price.** Your enterprise plan sets the price. You do not pay per token.

## What you cannot change

* **The model.** The server replaces `model` with your plan's model. It also removes the fields that pick other models (`models`, `route`) and saved presets (`preset`).
* **The endpoints.** By default the endpoint accepts `chat/completions`, `completions`, and `models`. Other paths return `404`.

## Limits

* A request that is **not streamed** must finish in about **110 seconds**. For long outputs, set `"stream": true`.
* A request can be at most **30 MB**, including files sent as base64.
* A trial plan stops at its expiry date. After that, requests return `403`. See [Errors](https://docs.modelslab.com/enterprise-api/llm-endpoint/errors.md).

## Endpoints

> [card] [Chat Completions](https://docs.modelslab.com/enterprise-api/llm-endpoint/chat-completions.md)
>
> Send messages and get a reply, with or without streaming.

> [card] [Files, Images and PDFs](https://docs.modelslab.com/enterprise-api/llm-endpoint/files.md)
>
> Send images, PDFs and audio in your messages.

> [card] [List Models](https://docs.modelslab.com/enterprise-api/llm-endpoint/list-models.md)
>
> Show the model that your plan uses.

> [card] [Errors](https://docs.modelslab.com/enterprise-api/llm-endpoint/errors.md)
>
> Status codes and what to do about each one.


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