LLMPrice
Updated daily
Data standards

Where every number comes from

The catalog separates verified direct pricing from synchronized endpoint pricing instead of blending them into one unexplained number.

1. Direct-provider pricing

30 listings are refreshed daily from the official pricing documentation published by OpenAI, Anthropic, Google, xAI, DeepSeek, and Mistral. These rows are labeled Direct, link to the first-party page, and were last validated 2026-08-26 20:50:00 UTC.

2. OpenRouter endpoint pricing

411 listings are synchronized daily from OpenRouter's public models API. OpenRouter reports dollars per token; LLMPrice multiplies those values by 1,000,000 for display. Invalid or negative router records are excluded. The current snapshot was captured 2026-08-26 20:50:00 UTC.

3. Workload calculation

monthly cost = requests × ((uncached input × input rate) + (cached input × cache-read rate) + (cache writes × write rate) + (output × output rate)) ÷ 1,000,000

When an endpoint does not publish a cache-read or cache-write rate, the calculator uses the normal input rate for that portion. This avoids inventing a discount.

4. Model-specific billing rules

The first-party catalog includes published batch discounts, long-context thresholds, cache-write rates, and DeepSeek peak/off-peak prices where applicable. OpenRouter records use the model-level rates supplied by its API and do not inherit first-party batch rules.

5. Capabilities and limits

OpenRouter context limits, modalities, and supported parameters come from the same API snapshot. A capability means the endpoint advertises the related input modality or parameter; it is not an independent quality score.

6. What is not included

Estimates exclude taxes, rate limits, minimum commitments, tool calls, web-search charges, media-token conversion, cache storage, regional premiums, retries, and negotiated discounts unless a model record explicitly includes them. Tokenizers also differ, so identical text can produce different token counts across models.

7. Why there are no copied benchmark scores

LLMPrice does not copy another site's proprietary rankings. Quality benchmarks need their own licensed or first-party source, model-version matching, and evaluation date. Price and capability comparison are kept separate until that data can be published responsibly.

8. Automatic update safety

Both source groups run every day. A run publishes only after all tracked direct rows, router records, billing relationships, generated pages, links, and calculator tests pass. Missing rows, malformed prices, suspicious large changes, or a changed source-page layout stop the run, leaving the last known-good catalog live.