Choose a model. Know its tradeoffs.
Compare language models across the providers that serve them, then browse image, speech, reranking and decision models from the same catalog. Everything loads from the public AIVAX catalogs when you visit this page.
- Language models
- —
- Model families
- —
- Serving providers
- —
- Loaded
- —
Integrated models use the AIVAX balance. BYOK keeps the provider contract and model bill with you.
Available models.
Choose a kind of model, then search, filter and compare. Rates and availability come from the public catalog when the page loads.
Chat, reasoning and tool-calling models. Open a model's providers to compare the rates, limits and data policy of each serving route.
Create or edit images from a text prompt. Prices are fixed estimates per output image; models that accept reference images add a rate for each one.
Transcribe recorded audio into text. Billing follows the length of the audio.
Turn written text into spoken audio. Billing follows the number of characters.
Reorder candidate documents by their relevance to a query. Start with the default reranker unless you have a measured reason to choose another.
Answer yes-or-no, choice and score questions about a text in one billed call instead of a chat completion.
Available AIVAX language models in the selected order, with capabilities, context, token pricing and serving providers
No models match this combination of search and filters.
Could not load the model catalog. Please try again.
Prices are USD per million tokens. The rates beside each model are an estimate; open its providers for the rates and limits of each serving route. Context shows the largest published window among enabled providers, not a shared guarantee. Speed and intelligence are catalog ratings, not measured benchmarks.
Previews are illustrative. Results depend on the prompt, the parameters and any reference images you send.