OpenRouter Launches Batch API, Offering 50% Off Batch Inference
Batch API: half-price inference by bundling requests
AI BriefingOpenRouter released Batch API, through which providers complete asynchronous batch requests within a 24-hour window. Requests are typically charged at 50% or less of standard per-token prices, and more than 70 models are currently supported.
Also reported by 1 other source
- OpenRouter Batch API launches, with token prices cut in half for most modelsOpenRouter · September 23
Source: OpenRouter: Announcements · openrouter.ai
Event follow-up1
View all event coverage- OpenRouter Launches Batch API, Offering 50% Off Batch InferenceOpenRouter: Announcements · September 22