OpenAI cost calculation ignores cached input tokens (over-costs cache hits)

Summary

calculateOpenAICost in core/llm/utils/calculateRequestCost.ts bills the full promptTokens at the standard input rate and never accounts for cached input tokens, so requests that hit OpenAI's prompt cache are over-costed. The Anthropic branch in the same file already handles cache tokens; the OpenAI branch does not.

Detail

OpenAI reports cached input as usage.prompt_tokens_details.cached_tokens, and prompt_tokens includes those cached tokens. Cached input is billed at a discount (for example gpt-4o cached input is half the standard input rate). The cost function charges every prompt token at full rate:

const inputCost = (usage.promptTokens / 1_000_000) * modelPricing.input;
// no use of usage.promptTokensDetails.cachedTokens

Compare calculateAnthropicCost, which reads usage.promptTokensDetails and prices cachedTokens / cacheWriteTokens at their own rates.

Effect

For an OpenAI request with cached input (common with long, stable system prompts), the reported cost is higher than the actual OpenAI charge — the cached portion is billed at full price instead of the cache-read discount.

Suggested direction

Give the OpenAI pricing table a cachedInput rate and subtract the cached tokens from the full-rate input, pricing them separately, the way the Anthropic branch does:

const cachedTokens = usage.promptTokensDetails?.cachedTokens ?? 0;
const uncachedInput = Math.max(0, usage.promptTokens - cachedTokens);
const inputCost = (uncachedInput / 1_000_000) * modelPricing.input
                + (cachedTokens / 1_000_000) * modelPricing.cachedInput;

Happy to open a PR with the cached-input rates for the models already listed if that direction sounds right.

Start in core/llm/utils/calculateRequestCost.ts at calculateOpenAICost and compare it with the Anthropic branch's cache-token handling. Review the OpenAI pricing entries and promptTokensDetails usage fields, then verify that cached and uncached input are priced separately and the reported total matches the provider's charge.