Together AI· Inference platformPartnership

Learn how Cursor partnered with Together AI to deliver real-time, low-latency inference at scale

Cursor and Together AI partner to deliver real-time, low-latency inference for Cursor's AI coding platform using NVIDIA Blackwell GPUs, custom kernels, and a quantization pipeline to enable fast model iteration.

From the source

Cursor partnered with Together AI, the AI Native Cloud, to build infrastructure for this loop — using the NVIDIA Blackwell architecture and tuning the inference stack to meet strict latency targets.

together.ai

Announced

13 Jan 2026 00:00 UTC

Detected

03 Aug 2026 21:12 UTC (+202d after)