See what each run costs, and stop it at a budget.

How it works

See it run

The code is a checked example from the docs; the output is an example of what it prints.

from shipit_agent import Agent
from shipit_agent.costs import CostTracker, Budget

tracker = CostTracker(budget=Budget(max_dollars=5.00))
agent = Agent.with_builtins(llm=llm, hooks=tracker.as_hooks())

result = agent.run("Analyze this codebase")

print(f"Total cost: ${tracker.total_cost:.4f}")
tokens = tracker.total_tokens
print(f"Tokens: {tokens['input_tokens']} in, {tokens['output_tokens']} out")

Go deeper

6 more ways to use it

Each example is from the docs and checked against the library.

from shipit_agent.costs import Budget, BudgetExceededError

budget = Budget(
    max_dollars=5.00,   # hard limit
    warn_at=0.80,       # warn at 80% ($4.00)
)

tracker = CostTracker(budget=budget)

What you get

• Pricing built in

  Input, output and prompt-cache prices for the models shipit knows.

• Budgets

  Warn at a threshold, stop at the limit.

• Attribution

  A breakdown by model and by call.

• Custom prices

  Add or override a model's prices.

Agent parameters