Usage Accounting

The OpenRouter API provides built-in Usage Accounting that allows you to track AI model usage without making additional API calls. This feature provides detailed information about token counts, costs, and caching status directly in your API responses.

Usage Information

The API returns detailed usage information including:

1. Prompt and completion token counts using the model’s native tokenizer
2. Cost in credits
3. Reasoning token counts (if applicable)
4. Cached token counts (if available)

This information is included in the last SSE message for streaming responses, or in the complete response for non-streaming requests.

Response Format

The response includes a usage object with detailed token information:

1
{
2
  "object": "chat.completion.chunk",
3
  "usage": {
4
    "completion_tokens": 2,
5
    "completion_tokens_details": {
6
      "reasoning_tokens": 0
7
    },
8
    "cost": 0.95,
9
    "cost_details": {
10
      "upstream_inference_cost": 19
11
    },
12
    "prompt_tokens": 194,
13
    "prompt_tokens_details": {
14
      "cached_tokens": 0,
15
      "audio_tokens": 0
16
    },
17
    "total_tokens": 196
18
  }
19
}

cached_tokens is the number of tokens that were read from the cache. At this point in time, we do not support retrieving the number of tokens that were written to the cache.

Cost Breakdown

The usage response includes detailed cost information:

• cost: The total amount charged to your account
• cost_details.upstream_inference_cost: The actual cost charged by the upstream AI provider

Note: The upstream_inference_cost field only applies to BYOK (Bring Your Own Key) requests.

Benefits

1. Efficiency: Get usage information without making separate API calls
2. Accuracy: Token counts are calculated using the model’s native tokenizer
3. Transparency: Track costs and cached token usage in real-time
4. Detailed Breakdown: Separate counts for prompt, completion, reasoning, and cached tokens

Best Practices

1. Use the usage information to monitor token consumption and costs
2. Consider tracking usage in development to optimize token usage before production
3. Use the cached token information to optimize your application’s performance

Alternative: Getting Usage via Generation ID

You can also retrieve usage information asynchronously by using the generation ID returned from your API calls. This is particularly useful when you want to fetch usage statistics after the completion has finished or when you need to audit historical usage.

To use this method:

1. Make your chat completion request as normal
2. Note the id field in the response
3. Use that ID to fetch usage information via the /generation endpoint

For more details on this approach, see the Get a Generation documentation.

Examples

Basic Usage with Token Tracking

1
import { OpenRouter } from '@openrouter/sdk';
2
3
const openRouter = new OpenRouter({
4
  apiKey: '{{API_KEY_REF}}',
5
});
6
7
const response = await openRouter.chat.send({
8
  model: '{{MODEL}}',
9
  messages: [
10
    {
11
      role: 'user',
12
      content: 'What is the capital of France?',
13
    },
14
  ],
15
});
16
17
console.log('Response:', response.choices[0].message.content);
18
console.log('Usage Stats:', response.usage);

Streaming with Usage Information

This example shows how to handle usage information in streaming mode:

1
from openai import OpenAI
2
3
client = OpenAI(
4
    base_url="https://openrouter.ai/api/v1",
5
    api_key="{{API_KEY_REF}}",
6
)
7
8
def chat_completion_with_usage(messages):
9
    response = client.chat.completions.create(
10
        model="{{MODEL}}",
11
        messages=messages,
12
        stream=True
13
    )
14
    return response
15
16
for chunk in chat_completion_with_usage([
17
    {"role": "user", "content": "Write a haiku about Paris."}
18
]):
19
    if hasattr(chunk, 'usage'):
20
        if hasattr(chunk.usage, 'total_tokens'):
21
            print(f"\nUsage Statistics:")
22
            print(f"Total Tokens: {chunk.usage.total_tokens}")
23
            print(f"Prompt Tokens: {chunk.usage.prompt_tokens}")
24
            print(f"Completion Tokens: {chunk.usage.completion_tokens}")
25
            print(f"Cost: {chunk.usage.cost} credits")
26
    elif chunk.choices[0].delta.content:
27
        print(chunk.choices[0].delta.content, end="")