Model provider
Novita AI
Explore models served by Novita AI.
87models
| Model | Organization | Context | Providers | Input / 1M | Weights | Reasoning |
|---|---|---|---|---|---|---|
| MiniMax-M2.7minimax/MiniMax-M2.7 | minimax | 204,800 | 38 | from $0.21 | Open | — |
| MiniMax-M2.7-highspeedminimax/MiniMax-M2.7-highspeed | minimax | 204,800 | 15 | — | Open | — |
| Qwen3.5 122B-A10Balibaba/qwen3.5-122b-a10b | alibaba | 262,144 | 21 | from $0.26 | Open | — |
| Qwen3.5 27Balibaba/qwen3.5-27b | alibaba | 262,144 | 18 | from $0.195 | Open | — |
| Qwen3.5 35B-A3Balibaba/qwen3.5-35b-a3b | alibaba | 262,144 | 20 | from $0.08 | Open | — |
| Qwen3.5 397B-A17Balibaba/qwen3.5-397b-a17b | alibaba | 262,144 | 33 | from $0.39 | Open | — |
| MiniMax-M2.5minimax/MiniMax-M2.5 | minimax | 204,800 | 37 | from $0.27 | Open | — |
| GLM-5zhipuai/glm-5 | zhipuai | 204,800 | 42 | from $0.60 | Open | — |
| DeepSeek OCR 2deepseek/deepseek-ocr-2 | deepseek | 8,192 | 3 | — | Open | — |
| Kimi K2.5moonshotai/kimi-k2.5 | moonshotai | 262,144 | 37 | from $0.49 | Open | — |
| GLM-4.7-Flashzhipuai/glm-4.7-flash | zhipuai | 200,000 | 26 | from $0.06 | Open | — |
| GLM-4.7zhipuai/glm-4.7 | zhipuai | 204,800 | 33 | from $0.40 | Open | — |
| Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | nvidia | 262,144 | 16 | from $0.05 | Open | — |
| AutoGLM Phone 9B Multilingualzhipuai/autoglm-phone-9b-multilingual | zhipuai | 65,536 | 2 | — | Open | — |
| GLM-4.6Vzhipuai/glm-4.6v | zhipuai | 128,000 | 16 | from $0.30 | Open | — |
| Kimi K2 Thinkingmoonshotai/kimi-k2-thinking | moonshotai | 262,144 | 16 | from $0.60 | Open | — |
| PaddleOCR VLpaddlepaddle/paddleocr-vl | paddlepaddle | 131,072 | 1 | — | Open | — |
| Qwen3 VL 30B A3B Instructalibaba/qwen3-vl-30b-a3b-instruct | alibaba | 262,144 | 13 | from $0.15 | Open | — |
| GLM-4.6zhipuai/glm-4.6 | zhipuai | 204,800 | 29 | from $0.43 | Open | — |
| Qwen3 Omni 30B A3B Thinkingalibaba/qwen3-omni-30b-a3b-thinking | alibaba | 65,536 | 1 | — | Open | — |
| Kimi K2 Instruct 0905moonshotai/kimi-k2-0905 | moonshotai | 262,144 | 13 | from $0.60 | Open | — |
| Baichuan M2 32Bbaichuan/baichuan-m2-32b | baichuan | 131,072 | 1 | — | Open | — |
| GLM-4.5Vzhipuai/glm-4.5v | zhipuai | 64,000 | 16 | from $0.60 | Open | — |
| GPT OSS 120Bopenai/gpt-oss-120b | openai | 131,072 | 67 | from $0.03 | Open | — |
| GLM-4.5-Airzhipuai/glm-4.5-air | zhipuai | 131,072 | 19 | from $0.13 | Open | — |
| Qwen MT Plusalibaba/qwen-mt-plus | alibaba | 16,384 | 2 | — | Closed | — |
| Kimi K2 Instructmoonshotai/kimi-k2-instruct | moonshotai | 131,072 | 5 | — | Open | — |
| ERNIE 4.5 21B A3Bbaidu/ernie-4.5-21b-a3b | baidu | 131,072 | 1 | — | Open | — |
| MiniMax M1 80Kminimax/minimax-m1-80k | minimax | 1,000,000 | 5 | — | Open | — |
| Qwen3 Embedding 8Balibaba/qwen3-embedding-8b | alibaba | 32,768 | 9 | — | Open | — |
| Qwen3 Reranker 8Balibaba/qwen3-reranker-8b | alibaba | 32,768 | 2 | — | Open | — |
| DeepSeek R1 0528 Qwen3 8Bdeepseek/deepseek-r1-0528-qwen3-8b | deepseek | 131,072 | 1 | — | Open | — |
| DeepSeek R1 0528deepseek/deepseek-r1-0528 | deepseek | 163,840 | 16 | from $0.50 | Open | — |
| Llama 4 Maverick 17B Instructmeta/llama-4-maverick-17b-instruct | meta | 1,000,000 | 16 | — | Open | — |
| Llama 4 Scout 17B Instructmeta/llama-4-scout-17b-instruct | meta | 10,000,000 | 13 | — | Open | — |
| Gemma 3 12B ITgoogle/gemma-3-12b-it | 131,072 | 13 | from $0.05 | Open | — | |
| Gemma 3 27B ITgoogle/gemma-3-27b-it | 131,072 | 17 | from $0.08 | Open | — | |
| DeepSeek-R1deepseek/deepseek-r1 | deepseek | 128,000 | 13 | — | Open | — |
| DeepSeek-V3deepseek/deepseek-v3 | deepseek | 131,072 | 8 | — | Open | — |
| Llama-3.3-70B-Instructmeta/llama-3.3-70b-instruct | meta | 128,000 | 40 | from $0.10 | Open | — |
41–80 of 87