Novita AI
模型集成商Novita AI is an open-model inference aggregator with an OpenAI-compatible API, hosting DeepSeek, Llama, Qwen, GLM, Kimi and MiniMax models with per-token pricing and prompt caching.
模型
161
提示缓存
✓
批量折扣
—
Tool Calling
✓
模型161
| 模态 | |||||
|---|---|---|---|---|---|
| ai_infer_test_1 | Free | Free | — | 200K | text |
| ai_infer_test_2 | Free | Free | — | 200K | text |
| ai_infer_test_3 | Free | Free | — | 200K | text |
| AutoGLM Phone 9B MultilingualGLM | ¥0.2348 | ¥0.9257 | — | 64K | text |
| Baichuan M2 32B | ¥0.4695 | ¥0.4695 | — | 128K | text |
| Bunny | Free | Free | — | 256K | text |
| CoBuddy | ¥1.88 | ¥7.58 | ¥0.4695 | 128K | text |
| DeepSeek OCRDeepSeek | ¥0.2012 | ¥0.2012 | — | 8K | text |
| DeepSeek OCR 2DeepSeek | ¥0.2012 | ¥0.2012 | — | 8K | text |
| Deepseek Prover V2 671BDeepSeek | ¥4.7 | ¥16.77 | — | 160K | text |
| DeepSeek R1DeepSeek | ¥26.83 | ¥26.83 | — | 64K | text |
| DeepSeek R1DeepSeek | ¥26.83 | ¥26.83 | — | 64K | text |
| DeepSeek R1 0528DeepSeek | ¥4.7 | ¥16.77 | ¥2.35 | 160K | text |
| DeepSeek R1 Distill Llama 70BLlama | ¥5.37 | ¥5.37 | — | 8K | text |
| DeepSeek R1 Distill Qwen 14BQwen | ¥1.01 | ¥1.01 | — | 32K | text |
| DeepSeek R1 Distill Qwen 32BQwen | ¥2.01 | ¥2.01 | — | 64K | text |
| DeepSeek R1 Distill Qwen3 8B 0528Qwen | ¥0.4025 | ¥0.6037 | — | 128K | text |
| DeepSeek R1 TurboDeepSeek | ¥4.7 | ¥16.77 | — | 64K | text |
| DeepSeek V3DeepSeek | ¥5.97 | ¥5.97 | — | 64K | text |
| DeepSeek V3DeepSeek | ¥5.97 | ¥5.97 | — | 64K | text |
| DeepSeek V3 0324DeepSeek | ¥1.81 | ¥7.51 | ¥0.9056 | 160K | text |
| DeepSeek V3 TurboDeepSeek | ¥2.68 | ¥8.72 | — | 64K | text |
| DeepSeek V3.1DeepSeek | ¥1.81 | ¥6.71 | ¥0.9056 | 128K | text |
| DeepSeek V3.1 TerminusDeepSeek | ¥1.81 | ¥6.71 | ¥0.9056 | 128K | text |
| DeepSeek V3.2DeepSeek | ¥1.8 | ¥2.68 | ¥0.9022 | 160K | text |
| DeepSeek V3.2 ExpDeepSeek | ¥1.81 | ¥2.75 | — | 160K | text |
| DeepSeek V4 FlashDeepSeek | ¥0.9391 | ¥1.88 | ¥0.1878 | 1M | text |
| DeepSeek V4 Flash 0731DeepSeek | ¥2.95 | ¥8.85 | ¥0.1878 | 1M | text |
| DeepSeek V4 Flash Vision ExpDeepSeek | ¥2.95 | ¥8.85 | ¥0.1878 | 1M | text |
| DeepSeek V4 ProDeepSeek | ¥10.73 | ¥21.46 | ¥0.9056 | 1M | text |
| DeepSeek V4 Pro 0813DeepSeek | ¥8.85 | ¥26.56 | ¥0.8854 | 1M | text |
| DeepSeek V4.1 FlashDeepSeek | ¥2.01 | ¥8.05 | ¥0.0402 | 1M | text |
| DeepSeek V4.1 Flash Expires ExpDeepSeek | Free | Free | — | 1M | text |
| dev/glm46GLM | Free | Free | — | 256K | text |
| ERNIE 4.5 21B A3B | ¥0.4695 | ¥1.88 | — | 120K | text |
| ERNIE 4.5 300B A47B | ¥1.88 | ¥7.38 | — | 123K | text |
| ERNIE 4.5 VL 28B A3B | ¥0.9391 | ¥3.76 | — | 30K | textimage |
| ERNIE 4.5 VL 424B A47B | ¥2.82 | ¥8.38 | — | 123K | imagetext |
| ERNIE-4.5-21B-A3B-Thinking | ¥0.4695 | ¥1.88 | — | 128K | text |
| ERNIE-4.5-VL-28B-A3B-Thinking | ¥2.62 | ¥2.62 | — | 128K | textimage |
| Gemma 3 12BGemma | ¥0.3354 | ¥0.6708 | — | 128K | text |
| Gemma 3 27BGemma | ¥0.7982 | ¥1.34 | — | 96K | text |
| Gemma 4 26B A4BGemma | ¥0.872 | ¥2.68 | — | 256K | text |
| Gemma 4 31BGemma | ¥0.9391 | ¥2.68 | — | 256K | text |
| GLM 4.5 AirGLM | ¥0.872 | ¥5.7 | ¥0.1677 | 128K | text |
| GLM 4.5VGLM | ¥4.02 | ¥12.07 | ¥0.7379 | 64K | text |
| GLM 4.6GLM | ¥3.69 | ¥14.76 | ¥0.7379 | 200K | text |
| GLM 4.6VGLM | ¥2.01 | ¥6.04 | ¥0.3689 | 128K | text |
| GLM 4.7GLM | ¥4.02 | ¥14.76 | ¥0.7379 | 200K | text |
| GLM 4.7GLM | ¥4.02 | ¥14.76 | ¥0.7379 | 200K | text |
| GLM 4.7 FlashGLM | ¥0.4695 | ¥2.68 | ¥0.0671 | 200K | text |
| GLM 5GLM | ¥6.71 | ¥21.46 | ¥1.34 | 202.8K | text |
| GLM 5.1GLM | ¥9.26 | ¥29.51 | ¥1.74 | 200K | text |
| GLM 5.2GLM | ¥9.39 | ¥29.51 | ¥1.74 | 1M | text |
| GLM 5.3GLM | ¥9.39 | ¥29.51 | ¥1.74 | 1M | text |
| GLM 5.3 FlashGLM | ¥1.01 | ¥3.35 | ¥0.2012 | 1M | text |
| GLM-4-32B-0414GLM | ¥3.69 | ¥11.13 | — | 32K | text |
| GLM-4.5GLM | ¥4.02 | ¥14.76 | ¥0.7379 | 128K | text |
| GLM-5-TurboGLM | ¥8.05 | ¥26.83 | ¥1.61 | 202.8K | text |
| GLM-5V-TurboGLM | ¥8.05 | ¥26.83 | ¥1.61 | 200K | text |
| gt-4p | Free | Free | — | — | text |
| Hermes 2 Pro Llama 3 8BLlama | ¥0.9391 | ¥0.9391 | — | 8K | text |
| hermes/mercury-oss-120b | ¥0.3354 | ¥1.68 | — | 128K | text |
| hermes/mercury-oss-20b | ¥0.2683 | ¥1.01 | — | 128K | text |
| Hy3 | ¥0.9391 | ¥3.89 | ¥0.2348 | 256K | text |
| KAT Coder Pro | ¥2.01 | ¥8.05 | ¥0.4025 | 256K | text |
| Kimi K2 InstructKimi | ¥3.82 | ¥15.43 | — | 128K | text |
| Kimi K2 Instruct 0905Kimi | ¥4.02 | ¥16.77 | — | 256K | text |
| Kimi K2 ThinkingKimi | ¥4.02 | ¥16.77 | ¥1.01 | 256K | text |
| Kimi K2.5Kimi | ¥4.02 | ¥20.12 | ¥0.6708 | 256K | text |
| Kimi K2.6Kimi | ¥5.37 | ¥22.81 | ¥1.07 | 256K | text |
| Kimi K2.7 CodeKimi | ¥6.37 | ¥26.83 | ¥1.27 | 256K | text |
| Kimi K3Kimi | ¥20.12 | ¥100.62 | ¥2.01 | 1M | text |
| Ling 2.6 1T | ¥2.01 | ¥16.77 | ¥0.4025 | 256K | text |
| Ling 2.6 Flash | ¥0.6708 | ¥2.01 | ¥0.1342 | 256K | text |
| Ling 2.6 Flash | ¥0.6708 | ¥2.01 | ¥0.1342 | 256K | text |
| Ling 3.0 Flash | ¥0.4025 | ¥1.21 | ¥0.0805 | 256K | text |
| Ling 3.0 Flash Fast | ¥0.4025 | ¥1.21 | ¥0.0805 | 256K | text |
| Ling 3.0 Flash Fin | Free | Free | — | 256K | text |
| Ling 3.0 Flash Sante | Free | Free | — | 256K | text |
| Ling 3.0 Flash VL | Free | Free | — | 256K | textimage |
| Ling 3.0 Tiny | Free | Free | — | 256K | text |
| Llama 3 70B Euryale V2.1 | ¥9.93 | ¥9.93 | — | 8K | text |
| Llama 3 8B InstructLlama | ¥0.2683 | ¥0.2683 | — | 8K | text |
| Llama 3 8B Lunaris | ¥0.3354 | ¥0.3354 | — | 8K | text |
| Llama 3 8B Stheno V3.2 | ¥0.3354 | ¥0.3354 | — | 8K | text |
| Llama 3.1 70B Euryale V2.2 | ¥9.93 | ¥9.93 | — | 8K | text |
| Llama 3.1 8B InstructLlama | ¥0.1342 | ¥0.3354 | — | 16K | text |
| Llama 3.2 1B Instruct Llama | ¥0.1342 | ¥0.1342 | — | 131K | text |
| Llama 3.2 3B InstructLlama | ¥0.2012 | ¥0.3354 | — | 32K | text |
| Llama 3.3 70B InstructLlama | ¥0.9056 | ¥2.68 | — | 12K | text |
| Llama 4 Maverick InstructLlama | ¥1.81 | ¥5.7 | — | 1M | text |
| Llama 4 Scout InstructLlama | ¥1.21 | ¥3.96 | — | 128K | text |
| Llama3 70B InstructLlama | ¥3.42 | ¥4.96 | — | 8K | text |
| M2-herMiniMax | Free | Free | — | 32K | text |
| Macaron V1 Tall | ¥1.66 | ¥9.59 | ¥0.2951 | 256K | text |
| Macaron V1 Venti | ¥5.53 | ¥16.6 | ¥1.11 | 1M | text |
| MiniMax M1MiniMax | ¥3.69 | ¥14.76 | — | 1M | text |
| MiniMax M2MiniMax | ¥2.01 | ¥8.05 | ¥0.2012 | 200K | text |
| MiniMax M2.1MiniMax | ¥2.01 | ¥8.05 | ¥0.2012 | 200K | text |
| MiniMax M2.5MiniMax | ¥2.01 | ¥8.05 | ¥0.2012 | 200K | text |
| MiniMax M2.5 HighspeedMiniMax | ¥4.02 | ¥16.1 | ¥0.2012 | 200K | text |
| MiniMax M2.7MiniMax | ¥2.01 | ¥8.05 | ¥0.4025 | 200K | text |
| MiniMax M2.7-highspeedMiniMax | ¥4.02 | ¥16.1 | ¥0.4025 | 200K | text |
| MiniMax M3MiniMax | ¥2.01 | ¥8.05 | ¥0.4025 | 1M | text |
| Mistral NemoMistral | ¥0.2683 | ¥1.14 | — | 60.3K | text |
| MythoMax L2 13B | ¥0.6037 | ¥0.6037 | — | 4K | text |
| Nex-N2-Pro | Free | Free | — | 256K | text |
| Nous Hermes Llama2 13BLlama | ¥1.14 | ¥1.14 | — | 4K | text |
| NVIDIA Nemotron 3 Nano 30B A3B | ¥0.3354 | ¥1.34 | — | 256K | text |
| OpenAI GPT OSS 120BGPT-OSS | ¥0.3354 | ¥1.68 | — | 128K | text |
| OpenAI GPT OSS 20BGPT-OSS | ¥0.2683 | ¥1.01 | — | 128K | text |
| OpenChat 7B | ¥0.4025 | ¥0.4025 | — | 4K | text |
| Openhermes2.5 Mistral 7BMistral | ¥1.14 | ¥1.14 | — | 4K | text |
| PaddleOCR VL | ¥0.1342 | ¥0.1342 | — | 16K | textimage |
| Qwen 2 7B InstructQwen | ¥0.3622 | ¥0.3622 | — | 32K | text |
| Qwen 2 VL 72B InstructQwen | ¥3.02 | ¥3.02 | — | 32K | imagetext |
| Qwen MT PlusQwen | ¥1.68 | ¥5.03 | — | 16K | text |
| qwen/qwen3-vl-30b-a3b-thinkingQwen | ¥1.34 | ¥6.71 | — | 128K | textimage |
| qwen/qwen3-vl-8b-instructQwen | ¥0.5366 | ¥3.35 | — | 128K | textimage |
| Qwen2.5 72B InstructQwen | ¥2.55 | ¥2.68 | — | 32K | text |
| Qwen2.5 7B InstructQwen | ¥0.4695 | ¥0.4695 | — | 32K | text |
| Qwen2.5 VL 72B InstructQwen | ¥5.37 | ¥5.37 | — | 32K | textimage |
| Qwen3 235B A22BQwen | ¥1.34 | ¥5.37 | — | 40K | text |
| Qwen3 235B A22B Instruct 2507Qwen | ¥0.6037 | ¥3.89 | — | 128K | text |
| Qwen3 235B A22B Thinking 2507Qwen | ¥2.01 | ¥20.12 | — | 128K | text |
| Qwen3 30B A3BQwen | ¥0.6037 | ¥3.02 | — | 40K | text |
| Qwen3 32BQwen | ¥0.6708 | ¥3.02 | — | 40K | text |
| Qwen3 4BQwen | ¥0.2012 | ¥0.2012 | — | 128K | text |
| Qwen3 8BQwen | ¥0.2348 | ¥0.9257 | — | 128K | text |
| Qwen3 Coder 30B A3B InstructQwen | ¥0.4695 | ¥1.81 | — | 160K | text |
| Qwen3 Coder 480B A35B InstructQwen | ¥2.55 | ¥10.4 | — | 256K | text |
| Qwen3 Coder NextQwen | ¥1.34 | ¥10.06 | — | 256K | text |
| Qwen3 MaxQwen | ¥14.15 | ¥56.68 | — | 256K | text |
| Qwen3 Next 80B A3B InstructQwen | ¥1.01 | ¥10.06 | — | 128K | text |
| Qwen3 Next 80B A3B ThinkingQwen | ¥1.01 | ¥10.06 | — | 128K | text |
| Qwen3 Omni 30B A3B InstructQwen | ¥1.68 | ¥6.51 | — | 64K | text |
| Qwen3 Omni 30B A3B ThinkingQwen | ¥1.68 | ¥6.51 | — | 64K | text |
| Qwen3 VL 235B A22B InstructQwen | ¥2.01 | ¥10.06 | — | 128K | imagetext |
| Qwen3 VL 235B A22B ThinkingQwen | ¥6.57 | ¥26.5 | — | 128K | textimage |
| Qwen3 VL 30B A3B InstructQwen | ¥1.34 | ¥4.7 | — | 128K | textimage |
| Qwen3.5 122B A10BQwen | ¥2.68 | ¥21.46 | — | 256K | text |
| Qwen3.5 27BQwen | ¥2.01 | ¥16.1 | — | 256K | text |
| Qwen3.5 35B A3BQwen | ¥1.68 | ¥13.42 | — | 256K | text |
| Qwen3.5 397B A17BQwen | ¥4.02 | ¥24.15 | — | 256K | text |
| Qwen3.5-PlusQwen | Free | Free | — | 1M | text |
| Qwen3.6 27BQwen | ¥4.02 | ¥24.15 | — | 256K | text |
| Qwen3.6 35B A3BQwen | ¥1.66 | ¥9.96 | — | 256K | text |
| Qwen3.6-PlusQwen | Free | Free | — | 1M | text |
| Qwen3.7 MaxQwen | ¥8.38 | ¥25.15 | ¥1.68 | 1M | text |
| Qwen3.8 2.4T A95BQwen | ¥13.42 | ¥40.25 | ¥1.68 | 1M | text |
| Qwen3.8 27BQwen | ¥2.82 | ¥20.12 | ¥0.5702 | 1M | text |
| Qwen3.8 FlashQwen | ¥1.01 | ¥3.15 | ¥0.1073 | 1M | text |
| Qwen3.8 MaxQwen | ¥13.42 | ¥40.25 | ¥1.68 | 1M | text |
| Ring 2.6 1T | ¥2.01 | ¥16.77 | ¥0.4025 | 256K | text |
| Step 3.7 Flash | ¥1.34 | ¥7.71 | ¥0.2683 | 256K | text |
| WizardLM 2 8x22B | ¥4.16 | ¥4.16 | — | 65.5K | text |
| Xiaomi MiMo V2.5 | ¥1.13 | ¥2.25 | ¥0.0228 | 1M | text |
| Xiaomi MiMo V2.5 Pro | ¥3.5 | ¥7 | ¥0.0288 | 1M | text |
| XiaomiMiMo/MiMo-V2-Flash | ¥0.7379 | ¥2.21 | ¥0.161 | 256K | text |
| XiaomiMiMo/MiMo-V2-Pro | ¥13.42 | ¥40.25 | ¥2.68 | 1M | text |