llm-rates

Named llm-rates (not llm-prices, its name until 2026-08-21) because PyPI's similarity check rejected llm-prices as too close to the existing llmprices project — collapsed-separator collision, not an exact-name clash. llm-rates was verified free in every form (llm-rates, llmrates, llm_rates, singular llm-rate/llmrate) before adopting it; don't re-litigate the name.

One vendored model-price catalog + one internal overlay + a shared Python lookup/cost-math module, replacing four independently hand-maintained price tables that were drifting apart. Full origin story and decisions: this repo's sibling checkout plugin/docs/plans/model-catalog-consolidation.md (cross-repo — plugin is a separate git repository from libs, so this is a path reference, not a clickable link).

Why this exists

Four tables held the same vendor facts (plugin/scripts/prices/anthropic.json, plugin/skills/tokenator/scripts/pricing.json, sessions/src/sessmon/pricing.py, factory-bench/runs/model-bench/model-bench-runner.py). One of them silently returned $0.00 for any model it didn't recognise — a lookup bug, not a data bug — and under-reported real spend by over $800 in one 30-day window. This package fixes the lookup logic (never $0 for an unknown model) and gives the data one home.

Files

• catalog.json — vendored snapshot of litellm's model_prices_and_context_window.json, filtered to the providers/models the portfolio actually uses. Vendor list price, per-single-token USD (litellm's native unit). Never hand-edit — regenerate prices via refresh.py --apply; for Anthropic-provider rows, the capability fields (max_input_tokens/max_output_tokens) are instead kept in sync with Anthropic's own live Models API via refresh_context.py --apply (litellm's snapshot is a third-party guess for those fields, not authoritative).
• overlay.json — everything no public catalog can know: actual-billing overrides (e.g. Groq OSS models are free-tier here, not their list price), family-rate fallbacks (claude-opus → tier rate, so an unrecognised new model prices at its family's rate instead of $0), model-ID aliases (dated suffixes → canonical key), retirement/deprecation history (a retired model's row is kept, never deleted, so historical transcripts still reprice correctly), context_overrides for the rare model whose real default-served context genuinely differs from its published maximum (empty as of 2026-08-21 — see "Context-window data" below), and per-consumer portfolio pins.
• llm_rates/ — lookup(model_id) -> PriceRecord + cost math (in __init__.py); catalog.json and overlay.json ship inside this directory as package data so an installed wheel carries them alongside the code. Shared by every Python consumer; the sole PowerShell consumer (tokenator.ps1) can't import Python, so it reads a generated JSON table instead — see generate_tokenator_table.py below and the plan doc's "Known constraint".
• refresh.py — re-pulls the live litellm catalog, re-filters it to the same model set, diffs against the vendored catalog.json, and prints a report. Never applies silently — pass --apply to write. Price source only; does not touch capability fields for Anthropic-provider rows.
• refresh_context.py — re-pulls max_input_tokens/max_tokens for every Anthropic-provider catalog.json row from Anthropic's own live Models API (client.models.retrieve()), diffs against the vendored values, and prints a report. Never applies silently — pass --apply to write. Requires the anthropic package (pip install "llm-rates[refresh]") and a resolvable Anthropic credential (ANTHROPIC_API_KEY, ANTHROPIC_AUTH_TOKEN, or an ant auth login profile) — never falls back to a guessed value if no credential resolves. Run manually; not wired into any scheduled job. lookup()/cost() never import this module or touch the network — see "Context-window data" below.
• generate_tokenator_table.py — emits a plain JSON price table shaped for tokenator.ps1 (a models map of {input, output, context} per model id, plus flat cache_read_multiplier/cache_write_multiplier and a default row) from catalog.json + overlay.json, so that repo can hold a generated copy instead of a hand-maintained one. Deterministic — the same inputs always produce byte-identical output.

Usage

from llm_rates import lookup, cost, UnknownModelError

record = lookup("claude-sonnet-5")
record.input          # 2.0   ($/MTok)
record.output          # 10.0  ($/MTok)
record.source           # "catalog"
record.context           # 1000000 (context-window token limit, or None)

# A client-side "[1m]" resolvedModel signal (not a vendor id — see
# overlay.json's aliases) resolves to the same price and, as of 2026-08-21,
# the same context — the base id already reports the model's real
# 1,000,000-token window:
lookup("claude-sonnet-5[1m]").context   # 1000000

# One-shot cost for a turn:
usd = cost(
    "claude-opus-4-8",
    input_tokens=12_000,
    output_tokens=800,
    cache_read_tokens=50_000,
)

# An unrecognised model still resolves at its family rate:
lookup("claude-opus-4-9").source   # "overlay-family-fallback"

# A genuinely unknown vendor/model raises instead of returning $0:
try:
    lookup("some-new-vendor/mystery-model")
except UnknownModelError as e:
    ...

lookup() and cost() both accept optional catalog=/overlay= kwargs (already-loaded dicts) — useful for tests, or for a caller that wants to load once and reuse across many lookups instead of re-reading the JSON files each call.

Refreshing the catalog

python refresh.py            # pull live litellm catalog, diff, print report
python refresh.py --apply    # also overwrite catalog.json with the diff

refresh.py always pulls the live GitHub-hosted catalog URL, never the litellm pip package's bundled snapshot — that bundled copy is stale (it was missing Haiku 4.5, Opus 5, Opus 4.8, Fable 5, and Sonnet 5 entirely as of 2026-07-28; see the plan doc's "Two traps found").

Refreshing context-window data

python refresh_context.py            # pull the live Models API, diff, print report
python refresh_context.py --apply    # also overwrite catalog.json with the diff

Context-window limits (max_input_tokens) and output caps (max_output_tokens) for Anthropic-provider rows come from Anthropic's own Models API (client.models.retrieve(model_id)), not litellm's snapshot — litellm is a third-party-maintained guess for these fields, and it was wrong at least once (see "Pricing notes worth knowing" below). lookup() itself never calls this API: it's a refresh-time-only script, exactly like refresh.py, that writes into the vendored catalog.json, so lookup()/cost() stay pure and offline (they price historical transcripts and run behind a PowerShell overlay with no network access). Requires pip install "llm-rates[refresh]" (the anthropic SDK) and a credential the SDK's own resolution chain can find (ANTHROPIC_API_KEY/ANTHROPIC_AUTH_TOKEN/ant auth login) — with none resolvable, the script fails with an actionable message and writes nothing, never a guessed value.

Generating tokenator's pricing table

python generate_tokenator_table.py            # print to stdout
python generate_tokenator_table.py --out FILE  # write to FILE

This is a read-only export — it never touches plugin's checkout. The consumer migration that adopts the generated bytes as tokenator/pricing.json is tracked separately. Before emitting anything, the generator proves (via verify_cache_multipliers()) that its flat cache multipliers (0.1x read, 2.0x write of input — tuned to Claude Code's 1h-TTL cache behaviour) match this package's real per-model cache rates for every model tokenator prices; a divergence raises instead of silently drifting.

Pricing notes worth knowing

• claude-sonnet-5 is $2.00/$10.00 per MTok, permanently — not a time-limited introductory rate. It was announced as an introductory price through 2026-08-31, but the vendor cancelled the scheduled 2026-09-01 rise to $3.00/$15.00 (~2026-08-17). See overlay.json's notes.
• Groq OSS models list at $0.075–$0.29/MTok but bill $0.00 on the portfolio's free-tier key — the vendor list price lives in catalog.json, the actual billed rate lives in overlay.json's actual_billing_overrides. Both are correct; they answer different questions.
• A retired/de-listed model keeps its row. claude-opus-4-1 (retired 2026-08-05) and the Groq-delisted llama-4-scout/qwen3-32b entries stay priced at their historical rate so old transcripts still reprice correctly — deleting a row would silently re-price past usage at whatever family-fallback rate happens to apply now.
• claude-fable-5, claude-opus-5, and claude-sonnet-5 all serve 1,000,000 tokens of context, natively — confirmed by Anthropic's own Models API. A prior overlay.json context_overrides block forced all three to 200,000 (on the mistaken theory that catalog.json's max_input_tokens=1000000 was an extended-context-beta-only ceiling); that override has been removed (corrected 2026-08-21, C8). Only claude-haiku-4-5 among current Claude models genuinely has a 200,000-token window.

Setup for consumers

pip install -e C:/data/projects/libs/llm-rates

Same convention as libs/plan-doc and libs/triad-base — see plugin/CLAUDE.md.

Status

Rollout step 1 of model-catalog-consolidation.md — the library itself, built and tested. Consumer migrations (activity_cost.py, sessmon, model-bench-runner.py, tokenator.ps1) are steps 2–5, tracked separately in the plan doc and out of scope for this package's initial PR.

Testing

pytest llm-rates/tests/ -v