AI model catalog: 785+ models, one API
The FastInfra AI model catalog lists every model available through the OpenAI-compatible API, each with its live input and output price per million tokens, the number of upstream routes behind it, and a copy-paste request. Search by publisher or model name, filter to free-tier models, and open any model page for its FAQs, comparison links and routing details. New models appear automatically when a provider adds them.
Every model below is available through FastInfra's API at
https://api.fastinfra.ai/v1. Search by model id for Base URL, endpoints, and examples.
Open a model page for integration details (Base URL, endpoints, copy-paste code).
No models match that id.
Frequently asked questions
How many models does FastInfra offer?
Hundreds, across chat, vision, embeddings, video and speech. The exact count is shown at the top of the catalog and updates automatically as upstream providers add or retire models.
How do I call a specific model?
Copy the model ID from its catalog page and pass it as the model field in POST /v1/chat/completions (or the matching endpoint for video and speech). No per-provider keys are needed.
What does the route count on a model page mean?
It is the number of healthy upstream routes FastInfra can send that model's requests to. Requests use the lowest-cost route by default and fail over automatically if a route is unavailable.
Are model prices on the catalog live?
Yes. Prices are synced from providers and shown in USD per 1 million tokens for input and output. Free-tier models show $0.
Can I compare two models side by side?
Yes. Each model page links to comparison pages at /compare/{model-a}-vs-{model-b} with prices, context and routing shown side by side.
Last reviewed October 15, 2026 by FastInfra. Prices and counts on this page come from the live catalog.