What is Novita AI
Novita AI combines serverless APIs for language, image, audio and video models with on-demand GPU infrastructure and isolated agent sandboxes.
Serverless model pricing
As of October 13, 2026, serverless APIs are pay as you go with no monthly commitment. Current language-model rates per million tokens include DeepSeek V4.1 Flash at US$0.30 input, US$0.006 cached input and US$1.20 output; DeepSeek V4 Pro 0813 at US$1.32, US$0.044 and US$3.96; GLM 5.3 Flash at US$0.15, US$0.03 and US$0.50; and GLM 5.3 at US$1.40, US$0.26 and US$4.40.
The official pricing catalogue also publishes current chat, vision, OCR, embedding and reranking endpoints with per-million-token rates. Batch inference is available at an introductory 50% discount on input and output tokens for supported models.
GPU and agent infrastructure
GPU Instances provide dedicated machines with predictable resources, while Serverless GPU allocates compute for individual jobs and scales to zero when idle. Agent Sandbox is billed per second by requested vCPU and memory. Enterprise buyers can request dedicated clusters, higher-volume arrangements and support.
Official sources: Novita AI pricing, Novita platform and current model rates, Novita GLM 5.1 pricing and API guide.