LLM API aggregation
LLM API aggregation platform
Stop integrating each model vendor’s API and account separately. Tokenjoy brings many models behind one OpenAI-compatible endpoint. One API key calls them all, and usage and cost are recorded in one place.
One key, many models
- OpenAI- and Anthropic-compatible; change base_url and the API key to connect
- Chat, image, audio, video, embedding and rerank models, managed in one model catalog
- Switch models by changing only the model parameter
Visible prices, pay as you go
Selected models carry a platform discount, and prices are listed in the Pricing section of the website, with the best channel chosen when a model has several. Billing can be per token, per request or tiered, so you pay for what you use. Negotiated company prices and prices of your own channels follow the console and your actual bill.
Managing shared use
- Budgets flow from company to department, project, member and API key, and calls are blocked when quota runs out
- Allowed models per department and per API key
- Filter the call log by department, member, model or channel, and export CSV
FAQ
What is an LLM API aggregation platform?
It gathers the APIs of several model vendors behind one endpoint, so one API key can call them all with unified billing and usage records.
Where can I see prices?
The Pricing section on the home page shows the base price and the default platform discount for each model. Negotiated company prices and prices of your own channels follow the console and your actual bill.