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

# OpenAI SDK

> Use the official OpenAI Python or TypeScript SDK with OpenCompress.

OpenCompress is fully compatible with the OpenAI SDK. Change `base_url` and `api_key` — everything else stays the same.

## Python

```bash theme={null}
pip install openai
```

```python theme={null}
from openai import OpenAI

client = OpenAI(
    base_url="https://www.opencompress.ai/api/v1",
    api_key="sk-occ-your-key-here",
)

# Non-streaming
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a senior software engineer."},
        {"role": "user", "content": "Review this code and suggest improvements..."},
    ],
)

print(response.choices[0].message.content)
print(f"Tokens used: {response.usage.total_tokens}")
```

## TypeScript / Node.js

```bash theme={null}
npm install openai
```

```typescript theme={null}
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://www.opencompress.ai/api/v1",
  apiKey: "sk-occ-your-key-here",
});

const response = await client.chat.completions.create({
  model: "claude-sonnet-4-6",
  messages: [
    { role: "system", content: "You are a senior software engineer." },
    { role: "user", content: "Review this code and suggest improvements..." },
  ],
});

console.log(response.choices[0].message.content);
```

## Streaming

<CodeGroup>
  ```python Python theme={null}
  stream = client.chat.completions.create(
      model="gpt-4o",
      messages=[{"role": "user", "content": "Write a haiku about compression."}],
      stream=True,
  )

  for chunk in stream:
      if chunk.choices[0].delta.content:
          print(chunk.choices[0].delta.content, end="")
  ```

  ```typescript TypeScript theme={null}
  const stream = await client.chat.completions.create({
    model: "gpt-4o",
    messages: [{ role: "user", content: "Write a haiku about compression." }],
    stream: true,
  });

  for await (const chunk of stream) {
    const content = chunk.choices[0]?.delta?.content;
    if (content) process.stdout.write(content);
  }
  ```
</CodeGroup>

<Note>
  Streaming works identically to the OpenAI API. Compression happens before the stream starts — there is no additional latency during token generation.
</Note>

## Switching between models

You can use any supported model by changing the `model` parameter. No other code changes needed.

```python theme={null}
# OpenAI
client.chat.completions.create(model="gpt-4o", ...)

# Anthropic
client.chat.completions.create(model="claude-sonnet-4-6", ...)

# Google
client.chat.completions.create(model="gemini-2.5-pro", ...)

# Meta (via OpenRouter)
client.chat.completions.create(model="meta-llama/llama-4-maverick", ...)
```