Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 1 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. And the score can be mapped to a float value in [0,1] by sigmoid function.