Batch Mode in the Gemini API: Process more for less- Google Developers Blog
Jul 7, 2025Lucia Loher, Vishal Dharmadhikari

Summary
Introduces Batch Mode for the Gemini API, an asynchronous endpoint for high-throughput, non-latency-critical workloads. This feature offers a 50% cost discount compared to synchronous APIs, higher rate limits, and simplified job management by allowing developers to submit requests in a single file and retrieve results within 24 hours. Demonstrates usage with Python SDK for bulk content generation and model evaluations.
More from the Google Developer Platform trail
- Autonomous LLM post-training with Tunix on TPUs- Google Developers Blog
- HeyGen x Google Cloud: Bringing Avatar IV to TPUs- Google Developers Blog
- Run Ray on TPU, Part 2: Ray AI libraries- Google Developers Blog
- Scaling Agentic RL: High-Throughput Agentic Training with Tunix- Google Developers Blog
- Run Ray on TPU, Part 1: The foundations- Google Developers Blog