About — Quanteta LLM API Price Index
Public data infrastructure tracking LLM API token list prices for 327 models from 51 providers. Free to use, source-attributed, timestamped.
Data as of:
LLM API list prices change frequently (new models and price cuts are common) and vary by tier, region, batch / cache usage and time. These are list prices captured at the time shown; always verify the current price with the provider before relying on it.
Data Sources
- OpenRouter
- OpenRouter Models API — public aggregated per-model prompt/completion prices, context length and modalities.
- LiteLLM
- LiteLLM model prices dataset — public dataset of token prices, context windows and capability flags; used to cross-check input prices.
- Capability score
- Open LLM Leaderboard (Hugging Face) (Apache-2.0, as of 2026-05-25) — a third party's published per-model scores shown as-is (not a Quanteta score). Open-weight models only, so unlisted models show "—".
Where a model can be matched across both sources, we surface whether the OpenRouter and LiteLLM input prices agree — a factual cross-check, not a score.
How we treat the data
- Prices and specs are shown exactly as the official aggregated sources report them, with attribution. We make no subjective recommendations or predictions — facts only.
- The only computed numbers are factual arithmetic (blended = 0.75×input + 0.25×output, in+out, per-use-case cost) with published formulas and assumptions.
- No fabrication: specs the source does not provide (an unmatched model's capability flags, a missing max-output) show "—" rather than a guess.
- To avoid drifting into opinion, we do not publish benchmark-derived composite scores (e.g. quality-per-price); the public surface is facts only.
Data Access
- Browse and filter all data on this site
- By Provider · By Use Case
- Download the full dataset as CSV
- Schema.org Dataset / Product markup for machine consumption
Data under CC BY 4.0. Prices are the property of the respective model providers.