Master Your AI Spend: A Guide to Infron Usage Accounting

Usage Accounting

The Infron 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

When enabled, the API will return 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.

Enabling Usage Accounting

You can enable usage accounting in your requests by including the usage parameter:

{
  "model": "your-model",
  "usage": {
    "include": true
  }
}

Response Format

When usage accounting is enabled, the response will include a usage object with detailed token information and a cost item and a cost_details object with detailed costs:

{
  "id": "c4942c8a-39d8-d39e-7eb0-395c4e4dbf68",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "content": "**Paris** is the capital of France. It's the largest city in the country, serving as the political, cultural, and economic center, with a population of about 2.1 million in the city proper and over 12 million in the greater metropolitan area. This has been the case since the 10th century, when Hugh Capet established it as the seat of the Capetian dynasty.",
        "refusal": null,
        "role": "assistant",
        "annotations": null,
        "audio": null,
        "function_call": null,
        "tool_calls": null
      }
    }
  ],
  "created": 1763949831,
  "model": "grok-4-1-fast-non-reasoning",
  "object": "chat.completion",
  "service_tier": null,
  "system_fingerprint": "fp_80e0751284",
  "usage": {
    "completion_tokens": 80,
    "prompt_tokens": 175,
    "total_tokens": 255,
    "completion_tokens_details": {
      "accepted_prediction_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 0,
      "rejected_prediction_tokens": 0
    },
    "prompt_tokens_details": {
      "audio_tokens": 0,
      "cached_tokens": 161,
      "image_tokens": 0,
      "text_tokens": 175
    },
    "num_sources_used": 0
  },
  "cost": 0.000051,
  "cost_details": {
    "audio_cost": 0,
    "cache_prompt_cost": 8.05e-6,
    "cache_write_cost": 0,
    "generation_cost": 0,
    "image_cost": 0,
    "input_prompt_cost": 2.8e-6,
    "output_prompt_cost": 0.00004,
    "tools_cost": 0,
    "video_cost": 0
  },
  "request_id": "e7d2ff652d84410f903aef33d7f6471e"
}

cost is the total amount charged to your account.

cost_details is the breakdown of the total cost.

Enabling usage accounting will add a few hundred milliseconds to the last response as the API calculates token counts and costs. This only affects the final message and does not impact overall streaming performance.

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. Enable usage tracking when you need to monitor token consumption or costs

2. Account for the slight delay in the final response when usage accounting is enabled

3. Consider implementing usage tracking in development to optimize token usage before production

4. Use the cached token information to optimize your application's performance

Examples

Basic Usage with Token Tracking

from openai import OpenAI

client = OpenAI(
    base_url="https://llm.onerouter.pro/v1",
    api_key="{{API_KEY_REF}}",
)

response = client.chat.completions.create(
    model="{{MODEL}}",
    messages=[
        {"role": "user", "content": "What is the capital of France?"}
    ],
    extra_body={
        "usage": {
            "include": True
        }
    }
)

print("Response:", response.choices[0].message.content)
print("Usage Stats:", getattr(response, "usage", None))

Streaming with Token Tracking

According to the OpenAI specification, to request token usage information in a streaming response, you would include the following parameters in your request:

{
    "model": "gemini-2.5-flash",
    "messages": [
        {
            "role": "user",
            "content": "hi"
        }
    ],
    "stream": true,
    "stream_options": {
        "include_usage": true
    }
}

This configuration tells the API to:

1. ⁠Use the Gemini 2.5 Flash model

2. ⁠Stream the response incrementally

3. Include token usage statistics in the stream response

The ⁠ stream_options.include_usage ⁠ parameter specifically requests that token usage information be returned as part of the streaming response.

Dive Deeper

Now that you've mastered the implementation of Usage Accounting, take a step back to understand the strategic value and engineering capability behind this feature. We recommend these deep-dive articles:

The Future of AI API Cost Management: Discover how usage transparency drives better business decisions.

Real-Time Cost Tracking: The Technical Foundation: A look at the infrastructure powering Infron AI's accounting engine.