Novita AI
Novita AI (novita, Inference host, headquartered in SG) serves 20 models through the Autonomous Relay Agents API. Prices are the provider's list prices, per million tokens.
| Model | Model id | Context | Input | Output |
|---|---|---|---|---|
| Llama 3 8B Stheno V3.2 | Sao10K/L3-8B-Stheno-v3.2 | 8,192 | $0.05 per M | $0.05 per M |
| Baichuan M2 32B | baichuan/baichuan-m2-32b | 131,072 | $0.07 per M | $0.07 per M |
| CoBuddy | baidu/cobuddy | 131,072 | $0.28 per M | $1.13 per M |
| ERNIE 4.5 21B A3B | baidu/ernie-4.5-21B-a3b | 120,000 | $0.07 per M | $0.28 per M |
| DeepSeek OCR 2 | deepseek/deepseek-ocr-2 | 8,192 | $0.03 per M | $0.03 per M |
| DeepSeek R1 Distill Qwen3 8B 0528 | deepseek/deepseek-r1-0528-qwen3-8b | 128,000 | $0.06 per M | $0.09 per M |
| DeepSeek R1 Turbo | deepseek/deepseek-r1-turbo | 64,000 | $0.70 per M | $2.50 per M |
| Ling 3.0 Flash Sante | inclusionai/ling-3.0-flash-sante | 262,144 | $0.075 per M | $0.22 per M |
| Ling 3.0 Flash VL | inclusionai/ling-3.0-flash-vl | 262,144 | $0.075 per M | $0.22 per M |
| Macaron V1 Tall | mindai/macaron-v1-tall | 262,144 | $0.2475 per M | $1.43 per M |
| Macaron V1 Venti | mindai/macaron-v1-venti | 1,048,576 | $0.825 per M | $2.475 per M |
| MiniMax M2.7-highspeed | minimax/minimax-m2.7-highspeed | 204,800 | $0.60 per M | $2.40 per M |
| Kimi K2 Instruct | moonshotai/kimi-k2-instruct | 131,072 | $0.57 per M | $2.30 per M |
| Hermes 2 Pro Llama 3 8B | nousresearch/hermes-2-pro-llama-3-8b | 8,192 | $0.14 per M | $0.14 per M |
| Bunny | novita/bunny | 262,144 | $0.00 per M | $0.00 per M |
| PaddleOCR VL | paddlepaddle/paddleocr-vl | 16,384 | $0.02 per M | $0.02 per M |
| Qwen MT Plus | qwen/qwen-mt-plus | 16,384 | $0.25 per M | $0.75 per M |
| Qwen3 Omni 30B A3B Thinking | qwen/qwen3-omni-30b-a3b-thinking | 65,536 | $0.25 per M | $0.97 per M |
| Llama 3 70B Euryale V2.1 | sao10k/l3-70b-euryale-v2.1 | 8,192 | $1.48 per M | $1.48 per M |
| AutoGLM Phone 9B Multilingual | zai-org/autoglm-phone-9b-multilingual | 65,536 | $0.035 per M | $0.138 per M |