> ## 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.

# Quick Start

> Start compressing LLM calls in under 2 minutes. Two lines of code.

## Get your API key

<Steps>
  <Step title="Create an account">
    Sign up at [opencompress.ai/dashboard](https://www.opencompress.ai/dashboard).
  </Step>

  <Step title="Add funds">
    Deposit credits via Stripe. Start with \$10 to test.
  </Step>

  <Step title="Generate an API key">
    Go to the API Keys section and create a new key. Copy it — it's shown only once.
  </Step>
</Steps>

Your API key starts with `sk-occ-` and works like any other LLM API key.

## Integration

OpenCompress is a **drop-in replacement** for any OpenAI-compatible endpoint. Change two values:

| Setting  | Before                      | After                                |
| -------- | --------------------------- | ------------------------------------ |
| Base URL | `https://api.openai.com/v1` | `https://www.opencompress.ai/api/v1` |
| API Key  | `sk-...` (OpenAI)           | `sk-occ-...` (OpenCompress)          |

Everything else — model names, message format, streaming, tool calls — stays identical.

***

## Code examples

<CodeGroup>
  ```python Python (OpenAI SDK) theme={null}
  from openai import OpenAI

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

  response = client.chat.completions.create(
      model="gpt-4o-mini",
      messages=[
          {"role": "system", "content": "You are a helpful assistant."},
          {"role": "user", "content": "Explain quantum computing in simple terms."},
      ],
  )

  print(response.choices[0].message.content)
  ```

  ```typescript TypeScript (OpenAI SDK) 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: "gpt-4o-mini",
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: "Explain quantum computing in simple terms." },
    ],
  });

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

  ```bash cURL theme={null}
  curl https://www.opencompress.ai/api/v1/chat/completions \
    -H "Authorization: Bearer sk-occ-your-key-here" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gpt-4o-mini",
      "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms."}
      ]
    }'
  ```
</CodeGroup>

<Note>
  Your prompts are compressed transparently before reaching the model. The response you receive is identical in format to a direct OpenAI API call.
</Note>

## What happens behind the scenes

```
Your App                    OpenCompress                     LLM Provider
   │                            │                                │
   │─── POST /chat/completions ─│                                │
   │    (original prompt)       │                                │
   │                            │── compress prompt ──┐          │
   │                            │                     │          │
   │                            │◄─ compressed ───────┘          │
   │                            │                                │
   │                            │─── forward compressed ────────►│
   │                            │                                │
   │                            │◄── response ──────────────────│
   │◄── response ───────────────│                                │
   │                            │                                │
   │                            │── calculate savings            │
   │                            │── deduct balance               │
```

## Supported models

OpenCompress works with any model available on OpenRouter:

<CardGroup cols={3}>
  <Card title="OpenAI" icon="bolt">
    GPT-4o, GPT-4o-mini, GPT-4.1, GPT-4.1-mini, GPT-4.1-nano
  </Card>

  <Card title="Anthropic" icon="message">
    Claude Opus 4.6, Claude Sonnet 4.6, Claude Haiku 4.5
  </Card>

  <Card title="Google" icon="wand-magic-sparkles">
    Gemini 2.5 Pro, Gemini 2.5 Flash
  </Card>

  <Card title="Meta" icon="meta">
    Llama 4 Maverick, Llama 4 Scout
  </Card>

  <Card title="DeepSeek" icon="magnifying-glass">
    DeepSeek V3, DeepSeek R1
  </Card>

  <Card title="BYOK" icon="key">
    Use your own API key with any provider
  </Card>
</CardGroup>

## Next steps

<CardGroup cols={2}>
  <Card title="How It Works" icon="gear" href="/how-it-works">
    Understand the compression pipeline
  </Card>

  <Card title="BYOK Mode" icon="key" href="/features/byok-mode">
    Use your own LLM API key
  </Card>
</CardGroup>