Skip to main content
Dear Developer, We are writing to inform you of upcoming changes to our Serverless Endpoints. As part of our regular product lifecycle management to ensure high performance and resource optimization, we will be deprecating a list of specific models on January 8, 2026 (UTC). You have 14 days from today to update your integration before these models are removed from the Serverless Endpoints.
Please refer to the table below to see if your application is using any of the impacted models and find their recommended alternatives:
Deprecated modelRecommended alternatives
baichuan/baichuan-m2-32bqwen/qwen3-32b-fp8
paddlepaddle/paddleocr-vlqwen/qwen3-vl-8b-instruct
qwen/qwen3-reranker-8bbaai/bge-reranker-v2-m3
deepseek/deepseek-ocrqwen/qwen3-vl-235b-a22b-instruct
thudm/glm-4.1v-9b-thinkingzai-org/glm-4.6v
deepseek/deepseek-r1-distill-qwen-14bdeepseek/deepseek-r1-0528
meta-llama/llama-3.2-3b-instructmeta-llama/llama-3.3-70b-instruct
google/gemma-3-12b-itgoogle/gemma-3-27b-it
gryphe/mythomax-l2-13bdeepseek/deepseek-v3-0324
deepseek/deepseek-r1-0528-qwen3-8bdeepseek/deepseek-r1-0528
deepseek/deepseek-r1-distill-qwen-32bdeepseek/deepseek-r1-0528
qwen/qwen3-8b-fp8qwen/qwen3-next-80b-a3b-instruct

What actions should you take?

To avoid service interruption, please choose one of the following options before the deadline: Update your API code to point to the Recommended Alternative listed above. These newer models offer improved reasoning capabilities, faster inference speeds, and better cost-efficiency.

Option 2: Continue Using Legacy Models (via Dedicated Endpoints)

If your workflow strictly requires a specific version from the deprecated list (e.g., for reproducibility or specific fine-tuning), you can deploy it on your own private GPU resources using our Dedicated Endpoints.

Timeline

  • Announcement Date: December 25, 2025
  • End of Life (EOL): January 8, 2026 (UTC)
Note: After the EOL date, API requests to any models in the Deprecated list via Serverless Endpoints will result in an error. If you have any questions or need assistance with the migration, please reach out to us via our Discord community or submit a support ticket. Best regards, The Novita AI Team