> ## Documentation Index
> Fetch the complete documentation index at: https://docs.os3compute.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Your first call, in curl, Python and TypeScript.

Create a key in the portal (**Keys → Create key**) and keep it out of your code:

```bash theme={null}
export OS3_GATEWAY_KEY="os3_gw_..."
```

```bash curl theme={null}
curl https://gateway.os3compute.com/v1/chat/completions \
  -H "Authorization: Bearer $OS3_GATEWAY_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4.1-flash-1017",
    "reasoning_effort": "none",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
```

```python Python theme={null}
# pip install openai
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.os3compute.com/v1",
    api_key=os.environ["OS3_GATEWAY_KEY"],
)
reply = client.chat.completions.create(
    model="deepseek/deepseek-v4.1-flash-1017",
    reasoning_effort="none",  # answer without thinking
    messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)
```

```typescript TypeScript theme={null}
// npm install openai
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.os3compute.com/v1",
  apiKey: process.env.OS3_GATEWAY_KEY,
});
const reply = await client.chat.completions.create({
  model: "deepseek/deepseek-v4.1-flash-1017",
  reasoning_effort: "none", // answer without thinking
  messages: [{ role: "user", content: "Hello" }],
});
console.log(reply.choices[0].message.content);
```

## Next steps

| To | Do this |
| - | - |
| Think | Drop `reasoning_effort`, or send `low`, `high` or `max`. |
| Stream | Send `"stream": true`. |
| Use the [fast id](https://docs.os3compute.com/models/deepseek-v4-1-flash-1017.md#normal-and-fast) | Add `-fast` to the model id. |
| Use the Anthropic SDK | Base URL `https://gateway.os3compute.com` (no `/v1`). |
| Use the Responses API | `client.responses.create(...)`, sending the whole conversation each turn. |
| List your model ids | `GET /v1/models`. |


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