NovitaAI serves 50 of the models we track. We do not support bring-your-own-key for this provider yet.
| Model | Made by | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|
| Llama 3.1 8B Instruct | NVIDIA | $0.02 | $0.05 | 16K |
| Llama 3.2 3B Instruct | NVIDIA | $0.03 | $0.05 | 33K |
| Qwen3 8B | Alibaba | $0.035 | $0.138 | 128K |
| Mistral Nemo | Mistral | $0.04 | $0.17 | 60K |
| Gemma 3 12B | $0.05 | $0.1 | 131K | |
| Qwen3-Coder 30B-A3B Instruct | Alibaba | $0.07 | $0.27 | 160K |
| GLM-4.7-Flash | Zhipu AI | $0.07 | $0.4 | 200K |
| Qwen2.5 7B Instruct | Alibaba | $0.07 | $0.07 | 32K |
| Qwen3 235B-A22B Instruct 2507 | Amazon Bedrock | $0.09 | $0.58 | 131K |
| Gemma 3 27B | $0.119 | $0.2 | 98K | |
| GLM-4.5-Air | Zhipu AI | $0.13 | $0.85 | 131K |
| Llama 3.3 70b Instruct | NVIDIA | $0.135 | $0.4 | 131K |
| DeepSeek V4 Flash | DeepSeek | $0.14 | $0.28 | 1.0M |
| Qwen3-Next 80B-A3B Instruct | Alibaba | $0.15 | $1.5 | 131K |
| Qwen3 Coder Next | Amazon Bedrock | $0.2 | $1.5 | 262K |
| Qwen3 235B-A22B | Alibaba | $0.2 | $0.8 | 41K |
| Qwen-MT Plus | Alibaba | $0.25 | $0.75 | 16K |
| Qwen3.5 35B-A3B | Alibaba | $0.25 | $2 | 262K |
| DeepSeek V3.1 | DeepSeek | $0.27 | $1 | 131K |
| DeepSeek V3.2 | DeepSeek | $0.27 | $0.41 | 164K |
| MiniMax-M2.7 | MiniMax | $0.3 | $1.2 | 205K |
| MiniMax M2.5 | MiniMax | $0.3 | $1.2 | 205K |
| Qwen3.5 27B | Alibaba | $0.3 | $2.4 | 262K |
| GLM-4.6V | Zhipu AI | $0.3 | $0.9 | 131K |
| MiniMax-M2 | MiniMax | $0.3 | $1.2 | 205K |
| Qwen3 VL 235B A22B Instruct | Amazon Bedrock | $0.3 | $1.5 | 131K |
| MiniMax-M2.1 | MiniMax | $0.3 | $1.2 | 205K |
| Qwen3-Coder 480B-A35B Instruct | Alibaba | $0.38 | $1.55 | 262K |
| Qwen3.5 122B-A10B | Alibaba | $0.4 | $3.2 | 262K |
| GLM-4.6 | Zhipu AI | $0.55 | $2.2 | 205K |
| GLM-4.5V | Zhipu AI | $0.6 | $1.8 | 66K |
| Kimi K2 0905 | NVIDIA | $0.6 | $2.5 | 262K |
| GLM-4.7 | Zhipu AI | $0.6 | $2.2 | 205K |
| MiniMax-M2.7-highspeed | MiniMax | $0.6 | $2.4 | 205K |
| MiniMax-M2.5-highspeed | MiniMax | $0.6 | $2.4 | 205K |
| Kimi K2 Thinking | Vertex | $0.6 | $2.5 | 262K |
| Kimi K2.5 | Moonshot AI | $0.6 | $3 | 262K |
| Qwen3.5 397B-A17B | Alibaba | $0.6 | $3.6 | 262K |
| GLM-4.5 | Zhipu AI | $0.6 | $2.2 | 131K |
| DeepSeek R1 0528 | DeepSeek | $0.7 | $2.5 | 164K |
| DeepSeek R1 | DeepSeek | $0.7 | $2.5 | 64K |
| Kimi K2.6 | Moonshot AI | $0.8 | $3.4 | 262K |
| Qwen2.5-VL 72B Instruct | Alibaba | $0.8 | $0.8 | 33K |
| Kimi K2.7 Code | Moonshot AI | $0.95 | $4 | 262K |
| GLM-5 | Zhipu AI | $1 | $3.2 | 203K |
| Qwen3.7 Max | Alibaba | $1.25 | $3.75 | 1.0M |
| GLM-5.1 | Zhipu AI | $1.38 | $4.4 | 205K |
| GLM-5.2 | Mistral | $1.4 | $4.4 | 1.0M |
| DeepSeek V4 Pro | DeepSeek | $1.6 | $3.2 | 1.0M |
| Kimi K3 | Moonshot AI | $3 | $15 | 1.0M |
NovitaAI serves 50 of the models we track, across 1 model type.
Llama 3.1 8B Instruct at $0.02 per million input tokens.
Not yet — NovitaAI is not currently one of the providers Serenities supports for bring-your-own-key.
