Zhipu AI Launches GLM-5.1 High-Speed API: 400 Tokens/s Sets New Global Benchmark

New Products

Summary

Zhipu AI launched the GLM-5.1 High-Speed API, claiming a throughput of 400 tokens per second and positioning the release as a new global benchmark for LLM inference. The announcement targets developers and enterprises that need low-latency, high-throughput language model integrations for real-time applications. Zhipu emphasizes speed and scalability to compete with other AI platform vendors. The move signals intensified competition in the AI platform market around performance and developer-facing APIs.

Classifications

industries
No industries detected
applications
AI & Machine learning

AskAI Classifications

Labels
AI/ML Platforms Developer Tools SaaS

Linked Companies

Z.ai
$50M to $100M