Skip to content
Back to feed

July 17, 2025 · Together AI

DeepSeek-R1-0528 serverless inference faster on NVIDIA Blackwell, same pricing

Record-breaking serverless inference speed for DeepSeek-R1-0528 using NVIDIA's Blackwell architecture. Read more.

  • Dramatically improved throughput and lower latency.
  • Same API endpoints and pricing.
  • Model ID: deepseek-ai/DeepSeek-R1.

Latest Together AI platform changes

All Together AI platform changes