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

# Monitor OpenAI using OpenTelemetry (Go)

OpenLIT uses OpenTelemetry instrumentation to help you monitor Go applications built with OpenAI models. This includes tracking performance, token usage, costs, and how users interact with the application.

The Go SDK wraps your OpenAI client with an `InstrumentedClient` that automatically emits traces and metrics for every API call — with zero changes to your application logic.

The integration supports:

* Chat completions (standard and streaming)
* Embeddings
* Image generation (`dall-e-2`, `dall-e-3`)

## Get started

<Steps>
  <Step title="Install the Go SDK">
    Open your terminal and run:

    <Tabs>
      <Tab title="Latest Version">
        ```shell theme={null}
        go get github.com/openlit/openlit/sdk/go
        ```
      </Tab>

      <Tab title="Specific Version">
        ```shell theme={null}
        go get github.com/openlit/openlit/sdk/go@v1.2.3
        ```

        Replace `v1.2.3` with the version you want to install.
      </Tab>
    </Tabs>
  </Step>

  <Step title="Initialize OpenLIT">
    Add this once at the start of your application (e.g. in `main()`):

    <Tabs>
      <Tab title="Via Config Struct">
        ```go theme={null}
        import (
            "context"
            openlit "github.com/openlit/openlit/sdk/go"
        )

        if err := openlit.Init(openlit.Config{
            OtlpEndpoint:    "YOUR_OTEL_ENDPOINT",
            ApplicationName: "my-ai-app",
            Environment:     "production",
        }); err != nil {
            log.Fatal(err)
        }
        defer openlit.Shutdown(context.Background())
        ```
      </Tab>

      <Tab title="Via Environment Variable">
        ```go theme={null}
        import (
            "context"
            openlit "github.com/openlit/openlit/sdk/go"
        )

        if err := openlit.Init(openlit.Config{
            ApplicationName: "my-ai-app",
        }); err != nil {
            log.Fatal(err)
        }
        defer openlit.Shutdown(context.Background())
        ```

        Then set your OTLP endpoint via environment variable:

        ```shell theme={null}
        export OTEL_EXPORTER_OTLP_ENDPOINT=YOUR_OTEL_ENDPOINT
        ```
      </Tab>
    </Tabs>

    **Replace** `YOUR_OTEL_ENDPOINT` with the URL of your OpenTelemetry backend, such as `http://127.0.0.1:4318` for a local OpenLIT deployment.
  </Step>

  <Step title="Create an instrumented client">
    Replace your existing OpenAI client creation with the OpenLIT instrumented client:

    ```go theme={null}
    import "github.com/openlit/openlit/sdk/go/instrumentation/openai"

    client := openai.NewClient("your-openai-api-key")
    ```

    Optional configuration:

    ```go theme={null}
    // Custom base URL (e.g. for Azure OpenAI or local models)
    client := openai.NewClient("your-api-key",
        openai.WithBaseURL("https://your-custom-endpoint/v1"),
    )
    ```
  </Step>

  <Step title="Use the client">
    Use the instrumented client exactly as you would a normal OpenAI client:

    **Chat completion:**

    ```go theme={null}
    resp, err := client.CreateChatCompletion(ctx, openai.ChatCompletionRequest{
        Model: "gpt-4o",
        Messages: []openai.Message{
            {Role: "system", Content: "You are a helpful assistant."},
            {Role: "user", Content: "What is OpenTelemetry?"},
        },
        MaxTokens:   256,
        Temperature: 0.7,
    })
    if err != nil {
        return err
    }
    fmt.Println(resp.Choices[0].Message.Content)
    ```

    **Streaming:**

    ```go theme={null}
    stream, err := client.CreateChatCompletionStream(ctx, openai.ChatCompletionRequest{
        Model: "gpt-4o",
        Messages: []openai.Message{
            {Role: "user", Content: "Tell me a story."},
        },
    })
    if err != nil {
        return err
    }
    defer stream.Close()

    for {
        chunk, err := stream.Recv()
        if err == io.EOF {
            break
        }
        if err != nil {
            return err
        }
        if len(chunk.Choices) > 0 {
            fmt.Print(chunk.Choices[0].Delta.Content)
        }
    }
    ```

    **Embeddings:**

    ```go theme={null}
    resp, err := client.CreateEmbedding(ctx, openai.EmbeddingRequest{
        Model: "text-embedding-3-small",
        Input: "The quick brown fox",
    })
    ```

    **Image generation:**

    ```go theme={null}
    resp, err := client.CreateImage(ctx, openai.ImageRequest{
        Model:  "dall-e-3",
        Prompt: "A futuristic city skyline at sunset",
        N:      1,
        Size:   "1024x1024",
    })
    ```
  </Step>
</Steps>

## What gets collected

Every call to the instrumented client automatically records:

| Data                  | Attribute                                         |
| --------------------- | ------------------------------------------------- |
| Operation name        | `gen_ai.operation.name`                           |
| Model requested       | `gen_ai.request.model`                            |
| Model used            | `gen_ai.response.model`                           |
| Input tokens          | `gen_ai.usage.input_tokens`                       |
| Output tokens         | `gen_ai.usage.output_tokens`                      |
| Estimated cost        | `gen_ai.usage.cost`                               |
| Finish reason         | `gen_ai.response.finish_reasons`                  |
| Tool calls            | `gen_ai.tool.name`, `gen_ai.tool.call.id`         |
| Time to first token   | `gen_ai.server.time_to_first_token` (streaming)   |
| Time per output token | `gen_ai.server.time_per_output_token` (streaming) |

Metrics emitted:

* `gen_ai.client.token.usage` — token usage histogram (input/output)
* `gen_ai.client.operation.duration` — total operation duration
* `gen_ai.server.time_to_first_token` — TTFT for streaming
* `gen_ai.client.operation.time_to_first_chunk` — client-side TTFT
* `gen_ai.client.operation.time_per_output_chunk` — per-chunk latency
* `gen_ai.server.request.duration` — estimated server processing time

***

<CardGroup cols={3}>
  <Card title="Go SDK Overview" href="/latest/sdk/go-overview" icon="golang">
    Full configuration reference and setup guide
  </Card>

  <Card title="Configuration" href="/latest/sdk/configuration" icon="bolt">
    Configure the OpenLIT SDK according to your requirements
  </Card>

  <Card title="Destinations" href="/latest/sdk/destinations/overview" icon="link">
    Send telemetry to Datadog, Grafana, New Relic, and other observability stacks
  </Card>
</CardGroup>