Methodology & data sources

Pricing data

Model prices are aggregated from live provider data via OpenRouter, which normalizes rates across the major API providers. We include current models from providers such as OpenAI, Anthropic, Google, xAI, DeepSeek, Mistral, Moonshot and Qwen. The roster isn’t hand-picked — models are pulled automatically and filtered by provider, a real published price, and text output, so the list grows as providers ship.

• Normalization. Every rate is converted to a single unit — USD per 1,000,000 tokens — for input, output, and cached input, so models are directly comparable.
• Cached input. We store each model’s own cached-input rate where a provider publishes one, rather than applying a flat discount. Where none is published we fall back to a conservative estimate.
• Tiers. The Budget / Standard / Premium tag is our own rough classification to help you filter by price class; it isn’t a provider designation.

Benchmark data

Benchmark scores come directly from each benchmark’s published data. We don’t run models ourselves or invent scores — we ingest, normalize model names, and join to pricing.

• LiveBench — category scores and measured cost-per-task from the LiveBench project’s published results.
• SWE-bench Verified and Aider Polyglot — sourced from Epoch AI’s benchmarking dataset (CC BY), which aggregates published results with API-identifier keys we can join on.

To draw cost vs quality, we match each benchmarked model to our pricing by a normalized model key. Coverage is partial by design: benchmarks include older or niche models we don’t price, and those still appear on the leaderboard with their score but are omitted from the cost chart. For LiveBench the cost axis is its measured cost-per-task; for SWE-bench and Aider it’s the model’s output price per 1M tokens, used as a proxy.

How often it updates

Pricing and benchmark data refresh on an automated daily schedule. When new data lands it’s committed and the site is rebuilt, so the static pages you read always reflect the latest refresh. The “updated” dates shown on the pricing and benchmark pages mark the most recent run.

Accuracy and corrections

We aim to be a reliable planning reference, but this is aggregated third-party data and providers change prices without notice. Always confirm the current rate on the provider’s own pricing page before committing spend, and verify a specific benchmark number on that benchmark’s own site before relying on it. Spotted something off? Send a correction via our contact page and we’ll check it against the source.

Independence

TokenCost is an independent reference and is not affiliated with, sponsored by, or endorsed by any model provider or benchmark. We don’t accept payment for placement or ranking. The tool is free; the site is supported by advertising. All estimates are for planning only and are not billing, financial, or professional advice.