[AI Model Aggregation Platform OpenRouter Launches Batch API, Most Model Token Prices Halved] According to a post by OpenRouter on the X platform, its Batch API has officially launched, targeting tasks that do not require immediate results. The per-token price for most models has been halved, and all results will be returned within 24 hours. The 50% discount applies to both input and output tokens, with support for over 70 models currently available. OpenRouter stated that during the two-week testing period, more than 230,000 batch tasks were completed, with a median completion time of 7 minutes and 90% completed within 1 hour.