OpenRouter Batch API: half-price inference by bundling requests | Hacker News - But Better

OpenRouter Batch API: half-price inference by bundling requests openrouter.ai

Send thousands of requests in one call, collect the results within 24 hours, and typically pay half the standard per-token price across more than 70 models. Median turnaround across 230k+ beta batches was 7 minutes.

2 points•porridgeraisin•8 days ago•0 comments•

#requests #half #price #batch #openrouter #bundling #api #inference

0 comments

No comments yet.

Related stories

Launch HN: Magnitude (YC S25) – Self-optimizing inference engine for agentsgithub.com
Hacker News · 120 points · about 8 hours ago
Outages across API, Grok.com, and Grok Build – API (us-east-1.api.x.ai) Statusstatus.x.ai
Hacker News · 2 points · 9 days ago
Razer’s low-latency wireless gaming keyboard is almost half offtheverge.com
The Verge · 0 points · 1 day ago
Decision API – compare and call decision models through one APIdecisionapi.org
Hacker News · 4 points · about 19 hours ago
DeepSeek API vs. OpenRouter latency, measured dailylatencyradar.com
Hacker News · 1 points · about 20 hours ago
Show HN: An API that tells you what people love about a productbb-product-api-docs.web.app
Hacker News · 1 points · 8 days ago