5 Services from api.cheapestinference.com

Run chat completions against 200+ open-source AI models via an OpenAI-compatible API at a flat per-call rate

Generate text completions using 200+ open-source AI models via a flat-rate, OpenAI-compatible completions endpoint

Generates vector embeddings for text input using 200+ open-source AI models via an OpenAI-compatible API with flat-rate pricing

Send messages to Anthropic-compatible AI models via a flat-rate OpenAI-compatible API endpoint, paying per call rather than per token

Returns the full list of 200+ open-source AI models available through the CheapestInference flat-rate API