---
title: "Werk API · Alran Code Docs"
url: https://alran.dev/en/docs/api
locale: en
updated: 2026-11-16
---

[Docs](https://alran.dev/en/docs)Models

# Werk API

Werk 1.1 in your own product, through the Ottili AI Platform. OpenAI-compatible: change the base URL and the model name.

On this page

[How do I get an API key?](#key) [First request](#first) [Endpoints](#endpoints) [Werk 1.1 at a glance](#spec) [Common questions](#faq)

## How do I get an API key? {#key}

Sign up on the [Ottili AI Platform](https://ai.ottili.one) and create a key under [API keys](https://ai.ottili.one/api-keys). Keys start with `sk-ottili-`. Keep them in an environment variable or a secret store, never in code.

## First request {#first}

```python
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://ai.ottili.one/v1",
    api_key=os.environ["OTTILI_API_KEY"],
)
reply = client.chat.completions.create(
    model="ottili/werk-1.1",
    messages=[{"role": "user", "content": "Summarize this ticket."}],
)
print(reply.choices[0].message.content)
```

```ts
import OpenAI from 'openai';

const client = new OpenAI({ baseURL: 'https://ai.ottili.one/v1', apiKey: process.env.OTTILI_API_KEY });
const reply = await client.chat.completions.create({
  model: 'ottili/werk-1.1',
  messages: [{ role: 'user', content: 'Summarize this ticket.' }],
});
console.log(reply.choices[0].message.content);
```

```bash
curl https://ai.ottili.one/v1/chat/completions \
  -H "Authorization: Bearer $OTTILI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "ottili/werk-1.1", "messages": [{"role": "user", "content": "Hello"}]}'
```

## Endpoints {#endpoints}

| Endpoint | Shape |
| `POST /v1/chat/completions` | OpenAI Chat Completions |
| `POST /v1/responses` | OpenAI Responses |
| `POST /v1/messages` | Anthropic Messages |
| `GET /v1/models` | The models your key can use |

All under `https://ai.ottili.one`, with the same key.

## Werk 1.1 at a glance {#spec}

|  |  |
| Model id | `ottili/werk-1.1` |
| Context window | 1,000,000 tokens |
| Longest answer | 256,000 tokens |
| Streaming, tool calls, reasoning | Yes |
| Input | Text |
| Price per 1M tokens | $0.50 input, $0.03 cached input, $1.50 output |
| Processed in | The United States |

More about the model on the [Werk 1.1 page](https://alran.dev/en/werk).

## Common questions {#faq}

How do I get an API key?

Sign up on the Ottili AI Platform and create a key under API keys. Keys start with sk-ottili-. Keep them in an environment variable or a secret store, never in code.

How do I call Werk 1.1 from my own code?

The endpoint is OpenAI-compatible: use the base URL https://ai.ottili.one/v1, the model id ottili/werk-1.1 and your key in the OTTILI_API_KEY environment variable, then call POST /v1/chat/completions. The same key also works for POST /v1/responses, POST /v1/messages and GET /v1/models under https://ai.ottili.one.

What can Werk 1.1 do, and what does it cost?

The context window is 1,000,000 tokens, the longest answer 256,000 tokens, the input is text, and streaming, tool calls and reasoning are supported. The price per 1M tokens is $0.50 input, $0.03 cached input and $1.50 output, and it is processed in the United States.

[PreviousYour own provider](https://alran.dev/en/docs/byok) [NextCLI commands](https://alran.dev/en/docs/cli)
