What is Infermatic
Infermatic provides a hosted interface and OpenAI-compatible API for open language models, with flat monthly subscriptions rather than token-based overage billing.
Plans
As of August 5, 2026, Free costs US$0 and provides interface-only access to one free model, up to 300 interface requests daily and 60 output tokens per request; it does not include API access.
Essential costs US$9 per month and includes a curated selection of models up to 72 billion parameters, one parallel API request, 12 requests per minute, up to 86,400 interface requests daily and 2,048 output tokens. Standard costs US$16 per month and expands access to every supported model up to 72 billion parameters with one parallel API request and 15 requests per minute.
Plus costs US$20 per month and unlocks the full catalogue, including mixture-of-experts, beta and models above 72 billion parameters, with two parallel API requests, 18 requests per minute and early access to updates. Enterprise uses custom pricing for higher parallelism and rate limits. Paid plans are flat-rate, encrypt traffic and state that prompts and responses are not logged.
Official source: Infermatic pricing.