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

# OpenRouter (TypeScript)

> Trace OpenRouter API calls using the Fallom SDK

[OpenRouter](https://openrouter.ai) provides access to 200+ LLM models through a single API. Use the Fallom SDK for full tracing with Model A/B Testing and Prompt Management.

<Info>
  For SDK-free observability, see [OpenRouter
  Broadcast](/integrations/openrouter-broadcast).
</Info>

## Installation

```bash theme={null}
npm install @fallom/trace openai
```

## Quick Start

OpenRouter uses the OpenAI-compatible API:

```typescript theme={null}
import fallom from "@fallom/trace";
import OpenAI from "openai";

// Initialize Fallom once at app startup
await fallom.init({ apiKey: process.env.FALLOM_API_KEY });

// Create a session for this conversation/request
const session = fallom.session({
  configKey: "my-app",
  sessionId: "session-123",
  customerId: "user-456",
});

// Wrap OpenAI client with OpenRouter base URL
const openrouter = session.wrapOpenAI(
  new OpenAI({
    baseURL: "https://openrouter.ai/api/v1",
    apiKey: process.env.OPENROUTER_API_KEY,
  })
);

// Use any OpenRouter model
const response = await openrouter.chat.completions.create({
  model: "openai/gpt-4o-mini",
  messages: [{ role: "user", content: "Hello!" }],
});

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

## Available Models

OpenRouter supports 200+ models:

```typescript theme={null}
// OpenAI
model: "openai/gpt-4o";
model: "openai/gpt-4o-mini";

// Anthropic
model: "anthropic/claude-sonnet-4-20250514";
model: "anthropic/claude-3-opus";

// Google
model: "google/gemini-1.5-pro";
model: "google/gemini-1.5-flash";

// Meta
model: "meta-llama/llama-3.1-70b-instruct";

// And many more...
```

## With Vercel AI SDK

```typescript theme={null}
import fallom from "@fallom/trace";
import * as ai from "ai";
import { createOpenAI } from "@ai-sdk/openai";

await fallom.init({ apiKey: "your-fallom-api-key" });

const session = fallom.session({
  configKey: "my-agent",
  sessionId: "session-123",
});

const { generateText, streamText } = session.wrapAISDK(ai);

const openrouter = createOpenAI({
  baseURL: "https://openrouter.ai/api/v1",
  apiKey: process.env.OPENROUTER_API_KEY,
});

const { text } = await generateText({
  model: openrouter("openai/gpt-4o-mini"),
  prompt: "Hello!",
});
```

## Model A/B Testing

Test different models from different providers:

```typescript theme={null}
import fallom from "@fallom/trace";
import OpenAI from "openai";

await fallom.init({ apiKey: "your-fallom-api-key" });

const session = fallom.session({
  configKey: "my-experiment",
  sessionId: "session-123",
});

const openrouter = session.wrapOpenAI(
  new OpenAI({
    baseURL: "https://openrouter.ai/api/v1",
    apiKey: process.env.OPENROUTER_API_KEY,
  })
);

// Get assigned model - could be GPT-4o, Claude, Gemini, etc.
const modelId = await session.getModel({ fallback: "openai/gpt-4o-mini" });

const response = await openrouter.chat.completions.create({
  model: modelId,
  messages: [{ role: "user", content: "Hello!" }],
});
```

## Streaming

```typescript theme={null}
const stream = await openrouter.chat.completions.create({
  model: "openai/gpt-4o-mini",
  messages: [{ role: "user", content: "Write a poem." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}
```

## What Gets Traced

| Field       | Description                             |
| ----------- | --------------------------------------- |
| Model       | Full model path (e.g., `openai/gpt-4o`) |
| Duration    | Total request time (ms)                 |
| Tokens      | Prompt, completion tokens               |
| Cost        | Calculated from token usage             |
| Prompts     | All input messages                      |
| Completions | Model response                          |
| Session     | Your config key + session ID            |

## SDK vs Broadcast

| Feature           | SDK (this page) | Broadcast |
| ----------------- | --------------- | --------- |
| Tracing           | ✅               | ✅         |
| Token tracking    | ✅               | ✅         |
| Cost tracking     | ✅               | ✅         |
| Session grouping  | ✅               | ✅         |
| Model A/B Testing | ✅               | ❌         |
| Prompt Management | ✅               | ❌         |

## Next Steps

<CardGroup cols={2}>
  <Card title="OpenRouter Broadcast" icon="broadcast-tower" href="/integrations/openrouter-broadcast">
    SDK-free tracing via OpenRouter.
  </Card>

  <Card title="Model A/B Testing" icon="flask" href="/model-testing">
    Test models across providers.
  </Card>
</CardGroup>