Skip to main content

llm-prices

Dated, source-cited LLM API prices for Python: the same table as the Rust crate llm-prices, generated from prices.json. Pure Python, no dependencies, no network access. Prices are USD per 1M tokens, and every row carries the provider's pricing page and the date it was checked.

import llm_prices
from llm_prices import Usage

p = llm_prices.lookup("claude-sonnet-4-6")          # also dated, Bedrock, Vertex, prefixed ids
groq = llm_prices.lookup_provider("groq", "openai/gpt-oss-120b")

usage = Usage(input=2_048, cache_read=45_000, cache_write_5m=3_500, output=1_024)
p.cost_usage(usage).total                 # 0.048129 (float)
p.cost_usage(usage, exact=True).total     # Decimal('0.048129')

cost_usage prices prompt-cache reads, cache writes by lifetime, batch discounts and the long-context switch. Source and docs: https://github.com/Mattbusel/llm-prices

Metadata

Release files for llm-prices 1.2.0

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

Source distribution (sdist)

Source distribution for llm-prices 1.2.0
File Size Uploaded Provenance Actions
llm_prices-1.2.0.tar.gz 25.0 kB With provenance Details for llm_prices-1.2.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for llm-prices 1.2.0
File Interpreter ABI Platform Actions
llm_prices-1.2.0-py3-none-any.whl Python 3 none any Details for llm_prices-1.2.0-py3-none-any.whl

Total release size: 44.2 kB

Release files / llm_prices-1.2.0.tar.gz

Download URL llm_prices-1.2.0.tar.gz
Size 25.0 kB
Tags Source
SHA-256 checksum
How to use checksums
a86aafe2bcfbdcf653e7e4b9fb63bfc4de3630fbd3f827b6adfa22c6023ef931
BLAKE2b-256 checksum
How to use checksums
d852054d17ca60249694a8faa5fd586fd4ddbd959d44430b6077983fd4ad9bb5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 15, 2026.

Transparency log

Release files / llm_prices-1.2.0-py3-none-any.whl

Download URL llm_prices-1.2.0-py3-none-any.whl
Size 19.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
06d9f067dd07ce6925582381c65e16849787a2365e57fb86053afe5cc48f992c
BLAKE2b-256 checksum
How to use checksums
fb8ba8e0bb805bc8b01af71db39a00418965bf5b90c463a5eff0798468b0faff
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 15, 2026.

Transparency log

Security for llm-prices 1.2.0

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.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for llm_prices-1.2.0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 15, 2026.

Transparency log

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.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

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