# Counting Tokens — Agent Loops, Stop Conditions and Token Budgets

Source: https://www.geekswithgeeks.com/en/agent-loops/budget-counting

> Read usage from responses and estimate size before you send.

## Measure, do not guess

Every Claude API response includes a `usage` object with `input_tokens` and `output_tokens`; with prompt caching it also reports cache creation and cache read tokens. Add these up each turn to feed your Budget. To check a prompt before sending, use the provider's token-counting endpoint; as a rough guide English text is about 4 characters per token, and Hindi or code often uses more tokens per character.

## Where the budget goes

A context window is shared by the system prompt, tools, history and the reply. Reserve space for each.

![Three shares: fixed prompt, growing history, reply reserve.](assets/figures/agent-loops/section-3-map.svg) — Figure 3.1 — Fixed prompt, growing history and reply reserve.

## Charging the budget from usage

`response` is the API reply. Input and output tokens are billed at different prices, so keep them separate.

```python
u = response.usage
in_tokens, out_tokens = u.input_tokens, u.output_tokens
budget.charge(in_tokens + out_tokens)
metrics["input"] += in_tokens
metrics["output"] += out_tokens
```

## A rough size estimate

A quick estimate of 4 characters per token is fine for guard rails but not for billing. 1,200 characters gives about 300 tokens.

```python
def rough_tokens(text: str) -> int:
    return len(text) // 4

print(rough_tokens("hello world " * 100))
```

Output:

```
300
```

**Quiz:** Where do you find the exact tokens a call used?

- [x] The usage object in the response
- [ ] The length of the prompt in characters
- [ ] The model name
- [ ] The HTTP status code

*Answer:* The usage object in the response. The API reports exact input and output token counts for each response.