As open-source models quickly evolve, we are focused on providing the most cutting-edge options to our users.
The DeepSeek V3.1 and Llama 3.3 70B serverless Model APIs are scheduled to be retired at 5pm PT on May 15, at which time these models will be disabled and any requests made to them will return HTTP error code 400.
As a replacement, we suggest using DeepSeek V4 Pro, which delivers strong performance in agentic coding and tool use. Before the cutoff, update your integration to use lightning-ai/deepseek-v4-pro. If you still need access to DeepSeek V3.1 and/or Llama 3.3 70B, please reach out to discuss setting up a dedicated deployment.