About TokenFeeds

TokenFeeds is a real-time price and performance hub for compute and LLM tokens. It aggregates pricing, latency (time-to-first-token), and throughput across providers and venues so you can compare the true cost of running a model.

The problem

The compute-token market is fragmented — the same model is billed differently across aggregators (like OpenRouter), direct providers, and cloud marketplaces. TokenFeeds normalizes this by separating three roles: the data source (where a price was scraped), the venue (the entity that actually bills you), and the underlying provider (the inference server running the model) — so comparisons are apples-to-apples.

What we track

• Hundreds of models across 130+ providers.
• Prices refreshed every minute.
• Per-token-type pricing (input / output / cache) and route eligibility.
• Third-party speed metrics (time-to-first-token and throughput).

TokenFeeds is informational only — not financial advice. Always verify a price with the provider before relying on it. Questions? support@tokenfeeds.com.