LLM Prices & Context Windows
Compare per-million-token prices and context sizes across providers, then tick up to four models to compare them side by side.
| Compare | Provider | Model | Input $/1M | Output $/1M | Context (K) |
|---|
What It Is For
Compare what each model charges per million tokens and how much context it can hold, then filter down to the ones that fit your budget and your documents. Click a column header to sort. Tick up to four models, from any provider, to compare them side by side for your own usage.
How to Compare Models
Search for a model, tick its box, then search for another and tick that too. Your ticks stay while you change the search or filters. Set typical token sizes and monthly requests to see what each model would cost, and copy the compare link to share the exact selection.
Questions
Where do the prices come from?
From the open-source LiteLLM catalog, refreshed daily by an automated job that checks for suspicious changes. They are not verified against provider billing, so confirm on the provider page before relying on a number.
Why are some models missing?
The list covers the main providers and chat models. Cloud-reseller duplicates, embeddings, fine-tunes and deprecated models are left out.
What does a price per million tokens mean?
Providers bill input and output tokens separately, per million. A typical English word is about 1.3 tokens.
Can I reuse this data?
The prices come from an open-source catalog, so you can get them there directly. Please credit the source if you republish them.