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

# OpenAI

> Integrate OpenAI models through the Adaline Proxy for automatic telemetry and observability.

# OpenAI

Integrate OpenAI models through the Adaline Proxy to automatically capture telemetry — requests, responses, token usage, latency, and costs — with minimal code changes.

## Supported Models

**Chat Models**

| Model                    | Description                            |
| ------------------------ | -------------------------------------- |
| `gpt-5.3-codex`          | Latest Codex model                     |
| `gpt-5.2-pro`            | Latest flagship model                  |
| `gpt-5.2`                | High capability next-gen model         |
| `gpt-5.2-codex`          | GPT-5.2 Codex                          |
| `chatgpt-5.2`            | ChatGPT 5.2                            |
| `gpt-5.2-chat-latest`    | GPT-5.2 chat latest snapshot           |
| `gpt-5.1`                | Next-gen model                         |
| `gpt-5`                  | GPT-5 series base                      |
| `gpt-5-mini`             | Compact GPT-5                          |
| `gpt-5-nano`             | Ultra-compact GPT-5                    |
| `gpt-5-chat-latest`      | GPT-5 chat latest snapshot             |
| `gpt-4.1`                | Improved GPT-4 with enhanced reasoning |
| `gpt-4.1-mini`           | Compact GPT-4.1                        |
| `gpt-4.1-nano`           | Ultra-compact GPT-4.1                  |
| `gpt-4o`                 | Multimodal with vision support         |
| `gpt-4o-2024-08-06`      | GPT-4o August 2024 snapshot            |
| `gpt-4o-2024-05-13`      | GPT-4o May 2024 snapshot               |
| `chatgpt-4o-latest`      | ChatGPT-4o latest snapshot             |
| `gpt-4o-mini`            | Fast and cost-effective multimodal     |
| `gpt-4o-mini-2024-07-18` | GPT-4o Mini July 2024 snapshot         |
| `gpt-4-turbo`            | High capability with 128k context      |
| `gpt-4-turbo-2024-04-09` | GPT-4 Turbo April 2024 snapshot        |
| `gpt-4-turbo-preview`    | GPT-4 Turbo preview                    |
| `gpt-4`                  | Original GPT-4 model                   |
| `gpt-4-0613`             | GPT-4 June 2023 snapshot               |
| `gpt-4-0125-preview`     | GPT-4 January 2024 preview             |
| `gpt-4-1106-preview`     | GPT-4 November 2023 preview            |
| `gpt-3.5-turbo`          | Fast and cost-effective                |
| `gpt-3.5-turbo-0125`     | GPT-3.5 Turbo January 2024 snapshot    |
| `gpt-3.5-turbo-1106`     | GPT-3.5 Turbo November 2023 snapshot   |
| `o4-mini`                | Latest compact reasoning model         |
| `o4-mini-2025-04-16`     | O4 Mini April 2025 snapshot            |
| `o3`                     | Advanced reasoning model               |
| `o3-2025-04-16`          | O3 April 2025 snapshot                 |
| `o3-mini`                | Compact reasoning model                |
| `o3-mini-2025-01-31`     | O3 Mini January 2025 snapshot          |
| `o1`                     | Reasoning model for complex tasks      |
| `o1-2024-12-17`          | O1 December 2024 snapshot              |

**Embedding Models**

| Model                    | Description                |
| ------------------------ | -------------------------- |
| `text-embedding-3-large` | Highest quality embeddings |
| `text-embedding-3-small` | Balanced quality and cost  |
| `text-embedding-ada-002` | Legacy embedding model     |

## Proxy Base URL

```
https://gateway.adaline.ai/v1/openai/
```

## Prerequisites

1. An [OpenAI API key](https://platform.openai.com/api-keys)
2. An [Adaline API key](/docs/admin/create-api-keys), project ID, and prompt ID

## Chat Completions

### Complete Chat

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

  client = OpenAI(
      api_key="your-openai-api-key",
      base_url="https://gateway.adaline.ai/v1/openai/"
  )

  headers = {
      "adaline-api-key": "your-adaline-api-key",
      "adaline-project-id": "your-project-id",
      "adaline-prompt-id": "your-prompt-id"
  }

  response = client.chat.completions.create(
      model="gpt-4o",
      messages=[
          {"role": "system", "content": "You are a helpful assistant."},
          {"role": "user", "content": "What is machine learning?"}
      ],
      extra_headers=headers
  )

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

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

  const client = new OpenAI({
    apiKey: "your-openai-api-key",
    baseURL: "https://gateway.adaline.ai/v1/openai/",
  });

  const response = await client.chat.completions.create(
    {
      model: "gpt-4o",
      messages: [
        { role: "system", content: "You are a helpful assistant." },
        { role: "user", content: "What is machine learning?" },
      ],
    },
    {
      headers: {
        "adaline-api-key": "your-adaline-api-key",
        "adaline-project-id": "your-project-id",
        "adaline-prompt-id": "your-prompt-id",
      },
    }
  );

  console.log(response.choices[0].message.content);
  ```
</CodeGroup>

### Stream Chat

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

  client = OpenAI(
      api_key="your-openai-api-key",
      base_url="https://gateway.adaline.ai/v1/openai/"
  )

  headers = {
      "adaline-api-key": "your-adaline-api-key",
      "adaline-project-id": "your-project-id",
      "adaline-prompt-id": "your-prompt-id"
  }

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

  for chunk in stream:
      if chunk.choices[0].delta.content is not None:
          print(chunk.choices[0].delta.content, end="")
  ```

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

  const client = new OpenAI({
    apiKey: "your-openai-api-key",
    baseURL: "https://gateway.adaline.ai/v1/openai/",
  });

  const stream = await client.chat.completions.create(
    {
      model: "gpt-4o",
      messages: [
        { role: "system", content: "You are a helpful assistant." },
        { role: "user", content: "Explain quantum computing in simple terms." },
      ],
      stream: true,
      stream_options: { include_usage: true },
    },
    {
      headers: {
        "adaline-api-key": "your-adaline-api-key",
        "adaline-project-id": "your-project-id",
        "adaline-prompt-id": "your-prompt-id",
      },
    }
  );

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

## Embeddings

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

  client = OpenAI(
      api_key="your-openai-api-key",
      base_url="https://gateway.adaline.ai/v1/openai/"
  )

  headers = {
      "adaline-api-key": "your-adaline-api-key",
      "adaline-project-id": "your-project-id",
      "adaline-prompt-id": "your-prompt-id"
  }

  response = client.embeddings.create(
      model="text-embedding-3-small",
      input="The quick brown fox jumps over the lazy dog",
      extra_headers=headers
  )

  embedding = response.data[0].embedding
  print(f"Embedding dimension: {len(embedding)}")
  ```

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

  const client = new OpenAI({
    apiKey: "your-openai-api-key",
    baseURL: "https://gateway.adaline.ai/v1/openai/",
  });

  const response = await client.embeddings.create(
    {
      model: "text-embedding-3-small",
      input: "The quick brown fox jumps over the lazy dog",
    },
    {
      headers: {
        "adaline-api-key": "your-adaline-api-key",
        "adaline-project-id": "your-project-id",
        "adaline-prompt-id": "your-prompt-id",
      },
    }
  );

  console.log(`Embedding dimension: ${response.data[0].embedding.length}`);
  ```
</CodeGroup>

## Optional Headers

Customize tracing behavior with optional headers:

```python theme={null}
headers = {
    # Required
    "adaline-api-key": "your-adaline-api-key",
    "adaline-project-id": "your-project-id",
    "adaline-prompt-id": "your-prompt-id",
    # Optional
    "adaline-trace-name": "openai-chat-completion",
    "adaline-trace-session-id": "user-session-123",
    "adaline-span-name": "gpt-4o-call",
    "adaline-trace-tags": '["production", "chat"]',
    "adaline-trace-attributes": '{"create": {"userId": "user-123"}}',
}
```

See the full [Headers Reference](/docs/reference/proxy/headers) for all available options.

## Next Steps

* [Multi-Step Workflows](/docs/integrations/examples/multi-step-workflows) — RAG pipelines, multi-step generation, and conversational agents
* [Headers Reference](/docs/reference/proxy/headers) — Complete header documentation

***

<Card title="Back to Integrations" icon="arrow-left" href="/docs/integrations/introduction">
  Browse all integrations
</Card>