Skip to main content

pricetoken

Real-time LLM pricing data — typed client, cost calculator, and static pricing.

PyPI Python License: MIT

Python SDK for PriceToken. Zero runtime dependencies.

Install

pip install pricetoken
# or
uv add pricetoken

Quick Start

Calculate cost offline (no API call)

from pricetoken import calculate_model_cost

cost = calculate_model_cost("claude-sonnet-4-6", 1_000_000, 100_000)
print(cost.total_cost)  # $4.50

Fetch live pricing

from pricetoken import PriceTokenClient

client = PriceTokenClient()
pricing = client.get_pricing()

for model in pricing:
    print(f"{model.display_name}: ${model.input_per_m_tok}/MTok in, ${model.output_per_m_tok}/MTok out")

With API key (higher rate limits)

client = PriceTokenClient(api_key="pt_your_key_here")

Cost Calculation

from pricetoken import calculate_cost, calculate_model_cost

# By model ID (uses bundled static pricing)
cost = calculate_model_cost("gpt-4.1", 500_000, 100_000)
print(cost.input_cost)   # $1.00
print(cost.output_cost)  # $0.80
print(cost.total_cost)   # $1.80

# With explicit rates
cost = calculate_cost("custom-model", 5.0, 15.0, 1_000_000, 500_000)
print(cost.total_cost)   # $12.50

Static Pricing Data

21 models from Anthropic, OpenAI, Google, and DeepSeek are bundled for offline use:

from pricetoken import STATIC_PRICING

for model in STATIC_PRICING:
    print(f"{model.model_id}: ${model.input_per_m_tok}/MTok")

Note: Static data reflects prices at the time the package was published and does not auto-update. For the latest prices, use PriceTokenClient to fetch live data from the API.

API Reference

Method API Path
get_pricing(provider=, currency=) GET /api/v1/text
get_model(model_id, currency=) GET /api/v1/text/{model_id}
get_history(days=, model_id=, provider=) GET /api/v1/text/history
get_providers() GET /api/v1/text/providers
compare(model_ids, currency=) GET /api/v1/text/compare
get_cheapest(provider=, currency=) GET /api/v1/text/cheapest

Types

All types are dataclass(slots=True) for performance and type safety:

  • ModelPricing — model pricing data
  • CostEstimate — cost calculation result
  • PriceHistoryPoint — historical price data point
  • ModelHistory — price history for a model
  • ProviderSummary — provider overview with stats
  • PriceTokenError — API error (extends Exception)

Type aliases: ModelStatus, DataConfidence, Source (all Literal types).

Requirements

  • Python >= 3.10
  • Zero runtime dependencies

License

MIT

Metadata

Release files for pricetoken 0.13.10

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for pricetoken 0.13.10
File Size Uploaded Provenance
pricetoken-0.13.10.tar.gz 46.4 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for pricetoken 0.13.10
File Interpreter ABI Platform
pricetoken-0.13.10-py3-none-any.whl Python 3 none any Details

Total release size: 73.7 kB

Release files / pricetoken-0.13.10.tar.gz

Download URL pricetoken-0.13.10.tar.gz
Size 46.4 kB
Tags Source
SHA-256 checksum
How to use checksums
de1b95a38149690cd43d796f8be17ed9dea67e1551b91bf90b8e541bf9c8c098
BLAKE2b-256 checksum
How to use checksums
e73e3b1e890e426626ada282daa0de8b67cd379892e7b8b8cdb33928d222aa99
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.10.12 {"installer":{"name":"uv","version":"0.10.12","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / pricetoken-0.13.10-py3-none-any.whl

Download URL pricetoken-0.13.10-py3-none-any.whl
Size 27.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
13afdd24c285f39c8f329b99256b9b02089ed2ac6201729121ad6b9912c3530d
BLAKE2b-256 checksum
How to use checksums
2eff9354fafa9002143b7bc12dda03a90a0d8890a2893d8335a1e6ab7df5d7c3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.10.12 {"installer":{"name":"uv","version":"0.10.12","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Security for pricetoken 0.13.10

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page