genai_pricing

Core package badges:

PYPI

Quality and tooling:

Project/community:

Docs:

Estimate GenAI prompt costs from a unified, auto-updated pricing table. This repo provides a small usage-based cost estimator plus parsers for LiteLLM JSON and markdown pricing tables.

• Parses the pricing table at genai_pricing.PRICING_URL or a local file
• Computes costs from a usage dictionary with prompt_tokens and completion_tokens
• Includes internal helpers for OpenAI/Gemini-style usage extraction and fallback token counting

Installation

• Python 3.8+
• Packages:
  • tiktoken

pip install tiktoken

Quick start

The included example shows how to estimate cost from a model name and token usage dictionary using genai_pricing.estimate_costs. See example.py.

# Minimal example
from genai_pricing import estimate_costs

model = "gpt-4.1"
usage = {"prompt_tokens": 21_549, "completion_tokens": 7_091}
estimate = estimate_costs(model, usage)

print("Cost (USD):", estimate["total_cost"])
print("Details:", estimate)

Run the example:

python example.py

How cost is computed

Prices are looked up by model name in the pricing table, then applied to token counts:

$$ C = \frac{t_\text{in}}{10^6}. p_\text{in} + \frac{t_\text{out}}{10^6}. p_\text{out} $$

• $t_\text{in}$: prompt tokens
• $t_\text{out}$: completion tokens
• $p_\text{in}$: USD per 1M input tokens
• $p_\text{out}$: USD per 1M output tokens

Provide token counts from your model provider when available. Internal helpers can extract OpenAI- and Gemini-style usage metadata and fall back to tiktoken or a lightweight heuristic when needed.

Pricing table

By default, prices are read from genai_pricing.PRICING_URL, the remote LiteLLM JSON source.

To pin a specific table, pass pricing_source as a raw URL or local file path. For a local LiteLLM snapshot, use a path ending in model_prices_and_context_window_backup.json.

Testing

The project uses Python’s built-in unittest.

• Run all tests (discovery):

python -m unittest discover -s test -p "*_test.py" -v

API surface

• genai_pricing.estimate_costs
  • Computes a dict with prompt/completion costs and total_cost from a model name, a usage dictionary, and an optional pricing_source
• genai_pricing.clear_pricing_cache
  • Clears cached pricing data so the configured source is fetched or read again

Key constant:

• genai_pricing.PRICING_URL — remote table to fetch by default

License

MIT © 2025 Roberto Rossi

Acknowledgements

Pricing data sourced from the AgentOps tokencost table and mirrored (22 Oct 2025) locally at data/pricing_table.md for testing purposes.