Same agent Smaller bill. The tools and infrastructure to get more work from your AI. Fewer tokens. Less compute. Lower cost.
TypeScript agent-harnessagent-harness-engineeringai-engineeringai-observabilityamd-gpuclaude-codeclickhousecodexcoding-agentcoding-agentscursorgenaigpu-monitoringllm-observabilityllmopsnvidia-smiobservabilityopen-sourceopenaiopentelemetry
---
title: 'Monitor OpenAI using OpenTelemetry'
description: 'Monitor OpenAI LLM applications with OpenTelemetry auto-instrumentation, giving AI observability into performance, token usage, and cost tracking.'
sidebarTitle: 'OpenAI'
---
import IntegrationMethods from '/snippets/integration-methods.mdx';
OpenLIT uses OpenTelemetry instrumentation to help you monitor LLM applications built using OpenAI models. This includes tracking performance, token usage, costs, and how users interact with the application.
The integration is compatible with:
- OpenAI Python SDK client `>=1.92.0`
- OpenAI Typescript SDK client `>=1.13.0`
- OpenAI Go SDK, via OpenLIT's `InstrumentedClient` wrapper
## Get started
<Tabs>
<Tab title="Python / TypeScript">
Auto-instrumentation means you don't have to set up monitoring manually for different LLMs, frameworks, or databases. By simply adding OpenLIT in your application, all the necessary monitoring configurations are automatically set up.
<Steps>
<Step title="Install OpenLIT">
Open your command line or terminal and run:
<Tabs>
<Tab title="Python">
```shell
pip install openlit
```
</Tab>
<Tab title="Typescript">
```shell
npm install openlit
```
</Tab>
</Tabs>
</Step>
<IntegrationMethods />
</Steps>
</Tab>
<Tab title="Go">
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`)
<Steps>
<Step title="Install the Go SDK">
Open your terminal and run:
<Tabs>
<Tab title="Latest Version">
```shell
go get github.com/openlit/openlit/sdk/go
```
</Tab>
<Tab title="Specific Version">
```shell
go get github.com/openlit/openlit/sdk/[email protected]
```
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
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
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
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
import "github.com/openlit/openlit/sdk/go/instrumentation/openai"
client := openai.NewClient("your-openai-api-key")
```
Optional configuration:
```go
// 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
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
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
resp, err := client.CreateEmbedding(ctx, openai.EmbeddingRequest{
Model: "text-embedding-3-small",
Input: "The quick brown fox",
})
```
**Image generation:**
```go
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
</Tab>
</Tabs>
---
<CardGroup cols={3}>
<Card title="Quickstart: LLM Observability" href="/latest/sdk/quickstart-ai-observability" icon='bolt'>
Production-ready AI monitoring setup in 2 simple steps with zero code changes
</Card>
<Card title="Configuration" href="/latest/sdk/configuration" icon='bolt'>
Configure the OpenLIT SDK according to you 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>