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
142
提示缓存
✓
批量折扣
—
Tool Calling
✓
模型142
| 模型 | 输入价格 | 输出价格 | 缓存输入 | 上下文 | 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 | ¥0.237 | ¥0.9343 | — | 64K | text |
| BaiChuan M2 32B | ¥0.4739 | ¥0.4739 | — | 128K | text |
| Bunny | Free | Free | — | 256K | text |
| CoBuddy | ¥1.9 | ¥7.65 | ¥0.4739 | 128K | text |
| DeepSeek-OCRDeepSeek | ¥0.2031 | ¥0.2031 | — | 8K | text |
| DeepSeek-OCR 2DeepSeek | ¥0.2031 | ¥0.2031 | — | 8K | text |
| Deepseek Prover V2 671BDeepSeek | ¥4.74 | ¥16.93 | — | 160K | text |
| DeepSeek R1DeepSeek | ¥27.08 | ¥27.08 | — | 64K | text |
| DeepSeek R1DeepSeek | ¥27.08 | ¥27.08 | — | 64K | text |
| DeepSeek R1 0528DeepSeek | ¥4.74 | ¥16.93 | ¥2.37 | 160K | text |
| DeepSeek R1 0528 Qwen3 8BQwen | ¥0.4062 | ¥0.6093 | — | 128K | text |
| DeepSeek R1 Distill LLama 70BLlama | ¥5.42 | ¥5.42 | — | 8K | text |
| DeepSeek R1 Distill Qwen 14BQwen | ¥1.02 | ¥1.02 | — | 32K | text |
| DeepSeek R1 Distill Qwen 32BQwen | ¥2.03 | ¥2.03 | — | 64K | text |
| DeepSeek R1 (Turbo) DeepSeek | ¥4.74 | ¥16.93 | — | 64K | text |
| DeepSeek V3DeepSeek | ¥6.03 | ¥6.03 | — | 64K | text |
| DeepSeek V3DeepSeek | ¥6.03 | ¥6.03 | — | 64K | text |
| DeepSeek V3 0324DeepSeek | ¥1.83 | ¥7.58 | ¥0.914 | 160K | text |
| DeepSeek V3.1DeepSeek | ¥1.83 | ¥6.77 | ¥0.914 | 128K | text |
| Deepseek V3.1 TerminusDeepSeek | ¥1.83 | ¥6.77 | ¥0.914 | 128K | text |
| Deepseek V3.2DeepSeek | ¥1.82 | ¥2.71 | ¥0.9106 | 160K | text |
| Deepseek V3.2 ExpDeepSeek | ¥1.83 | ¥2.78 | — | 160K | text |
| DeepSeek V3 (Turbo) DeepSeek | ¥2.71 | ¥8.8 | — | 64K | text |
| Deepseek V4 FlashDeepSeek | ¥0.9478 | ¥1.9 | ¥0.1896 | 1M | text |
| Deepseek V4 ProDeepSeek | ¥10.83 | ¥21.66 | ¥0.914 | 1M | text |
| dev/glm46GLM | Free | Free | — | 256K | text |
| ERNIE 4.5 21B A3B | ¥0.4739 | ¥1.9 | — | 120K | text |
| ERNIE-4.5-21B-A3B-Thinking | ¥0.4739 | ¥1.9 | — | 128K | text |
| ERNIE 4.5 300B A47B | ¥1.9 | ¥7.45 | — | 123K | text |
| ERNIE 4.5 VL 28B A3B | ¥0.9478 | ¥3.79 | — | 30K | textimage |
| ERNIE-4.5-VL-28B-A3B-Thinking | ¥2.64 | ¥2.64 | — | 128K | textimage |
| ERNIE 4.5 VL 424B A47B | ¥2.84 | ¥8.46 | — | 123K | textimage |
| Gemma3 12BGemma | ¥0.3385 | ¥0.677 | — | 128K | text |
| Gemma 3 27BGemma | ¥0.8057 | ¥1.35 | — | 96K | text |
| Gemma 4 26B A4BGemma | ¥0.8801 | ¥2.71 | — | 256K | text |
| Gemma 4 31BGemma | ¥0.9478 | ¥2.71 | — | 256K | text |
| GLM-4-32B-0414GLM | ¥3.72 | ¥11.24 | — | 32K | text |
| GLM-4.5GLM | ¥4.06 | ¥14.89 | ¥0.7447 | 128K | text |
| GLM 4.5VGLM | ¥4.06 | ¥12.19 | ¥0.7447 | 64K | text |
| GLM 4.6GLM | ¥3.72 | ¥14.89 | ¥0.7447 | 200K | text |
| GLM 4.6VGLM | ¥2.03 | ¥6.09 | ¥0.3724 | 128K | text |
| GLM-4.7GLM | ¥4.06 | ¥14.89 | ¥0.7447 | 200K | text |
| GLM-4.7GLM | ¥4.06 | ¥14.89 | ¥0.7447 | 200K | text |
| GLM-4.7-FlashGLM | ¥0.4739 | ¥2.71 | ¥0.0677 | 200K | text |
| GLM-5GLM | ¥6.77 | ¥21.66 | ¥1.35 | 202.8K | text |
| GLM-5.1GLM | ¥9.34 | ¥29.79 | ¥1.76 | 200K | text |
| GLM 5.2GLM | ¥9.48 | ¥29.79 | ¥1.76 | 1M | text |
| GLM-5-TurboGLM | ¥8.12 | ¥27.08 | ¥1.62 | 202.8K | text |
| GLM-5V-TurboGLM | ¥8.12 | ¥27.08 | ¥1.62 | 200K | text |
| gt-4p | Free | Free | — | — | text |
| Hermes 2 Pro Llama 3 8BLlama | ¥0.9478 | ¥0.9478 | — | 8K | text |
| Hy3 | ¥0.9478 | ¥3.93 | ¥0.237 | 256K | text |
| Kat Coder Pro | ¥2.03 | ¥8.12 | ¥0.4062 | 256K | text |
| Kimi K2 0905Kimi | ¥4.06 | ¥16.93 | — | 256K | text |
| Kimi K2.5Kimi | ¥4.06 | ¥20.31 | ¥0.677 | 256K | text |
| Kimi K2.6Kimi | ¥5.42 | ¥23.02 | ¥1.08 | 256K | text |
| Kimi K2.7 CodeKimi | ¥6.43 | ¥27.08 | ¥1.29 | 256K | text |
| Kimi K2 InstructKimi | ¥3.86 | ¥15.57 | — | 128K | text |
| Kimi K2 ThinkingKimi | ¥4.06 | ¥16.93 | ¥1.02 | 256K | text |
| Kimi K3Kimi | ¥20.31 | ¥101.55 | ¥2.03 | 1M | text |
| L31 70B Euryale V2.2 | ¥10.02 | ¥10.02 | — | 8K | text |
| L3 70B Euryale V2.1 | ¥10.02 | ¥10.02 | — | 8K | text |
| L3 8B Stheno V3.2 | ¥0.3385 | ¥0.3385 | — | 8K | text |
| Ling-2.6-1T | ¥2.03 | ¥16.93 | ¥0.4062 | 256K | text |
| Ling-2.6-flash | ¥0.677 | ¥2.03 | ¥0.1354 | 256K | text |
| Ling-2.6-flash | ¥0.677 | ¥2.03 | ¥0.1354 | 256K | text |
| Ling-3.0-flash | Free | Free | — | 256K | text |
| Llama 3.1 8B InstructLlama | ¥0.1354 | ¥0.3385 | — | 16K | text |
| Llama 3.2 1B Instruct Llama | ¥0.1354 | ¥0.1354 | — | 131K | text |
| Llama 3.2 3B InstructLlama | ¥0.2031 | ¥0.3385 | — | 32K | text |
| Llama 3.3 70B InstructLlama | ¥0.914 | ¥2.71 | — | 6K | text |
| Llama3 70B InstructLlama | ¥3.45 | ¥5.01 | — | 8K | text |
| Llama 3 8B InstructLlama | ¥0.2708 | ¥0.2708 | — | 8K | text |
| Llama 4 Maverick InstructLlama | ¥1.83 | ¥5.75 | — | 1M | text |
| Llama 4 Scout InstructLlama | ¥1.22 | ¥3.99 | — | 128K | text |
| M2-herMiniMax | Free | Free | — | 32K | text |
| Macaron V1 Venti | Free | Free | — | 1M | text |
| MiniMax M1MiniMax | ¥3.72 | ¥14.89 | — | 1M | text |
| MiniMax-M2MiniMax | ¥2.03 | ¥8.12 | ¥0.2031 | 200K | text |
| Minimax M2.1MiniMax | ¥2.03 | ¥8.12 | ¥0.2031 | 200K | text |
| MiniMax M2.5MiniMax | ¥2.03 | ¥8.12 | ¥0.2031 | 200K | text |
| MiniMax M2.5-highspeedMiniMax | ¥4.06 | ¥16.25 | ¥0.2031 | 200K | text |
| MiniMax M2.7MiniMax | ¥2.03 | ¥8.12 | ¥0.4062 | 200K | text |
| MiniMax M2.7-highspeedMiniMax | ¥4.06 | ¥16.25 | ¥0.4062 | 200K | text |
| MiniMax M3MiniMax | ¥2.03 | ¥8.12 | ¥0.4062 | 1M | text |
| Mistral NemoMistral | ¥0.2708 | ¥1.15 | — | 60.3K | text |
| Mythomax L2 13B | ¥0.6093 | ¥0.6093 | — | 4K | text |
| Nemotron 3 Nano 30B A3B | ¥0.3385 | ¥1.35 | — | 256K | text |
| Nex-N2-Pro | Free | Free | — | 256K | text |
| Nous Hermes Llama2 13BLlama | ¥1.15 | ¥1.15 | — | 4K | text |
| OpenAI GPT OSS 120BGPT-OSS | ¥0.3385 | ¥1.69 | — | 128K | text |
| OpenAI: GPT OSS 20BGPT-OSS | ¥0.2708 | ¥1.02 | — | 128K | text |
| OpenChat 7B | ¥0.4062 | ¥0.4062 | — | 4K | text |
| Openhermes2.5 Mistral 7BMistral | ¥1.15 | ¥1.15 | — | 4K | text |
| PaddleOCR-VL | ¥0.1354 | ¥0.1354 | — | 16K | textimage |
| Qwen 2.5 72B InstructQwen | ¥2.57 | ¥2.71 | — | 32K | text |
| Qwen2.5 7B InstructQwen | ¥0.4739 | ¥0.4739 | — | 32K | text |
| Qwen2.5 VL 72B InstructQwen | ¥5.42 | ¥5.42 | — | 32K | textimage |
| Qwen 2 7B InstructQwen | ¥0.3656 | ¥0.3656 | — | 32K | text |
| Qwen 2 VL 72B InstructQwen | ¥3.05 | ¥3.05 | — | 32K | textimage |
| Qwen3 235B A22BQwen | ¥1.35 | ¥5.42 | — | 40K | text |
| Qwen3 235B A22B Instruct 2507Qwen | ¥0.6093 | ¥3.93 | — | 128K | text |
| Qwen3 235B A22b Thinking 2507Qwen | ¥2.03 | ¥20.31 | — | 128K | text |
| Qwen3 30B A3BQwen | ¥0.6093 | ¥3.05 | — | 40K | text |
| Qwen3 32BQwen | ¥0.677 | ¥3.05 | — | 40K | text |
| Qwen3 4BQwen | ¥0.2031 | ¥0.2031 | — | 128K | text |
| Qwen3.5-122B-A10BQwen | ¥2.71 | ¥21.66 | — | 256K | text |
| Qwen3.5-27BQwen | ¥2.03 | ¥16.25 | — | 256K | text |
| Qwen3.5-35B-A3BQwen | ¥1.69 | ¥13.54 | — | 256K | text |
| Qwen3.5-397B-A17BQwen | ¥4.06 | ¥24.37 | — | 256K | text |
| Qwen3.5-PlusQwen | Free | Free | — | 1M | text |
| Qwen3.6-27BQwen | ¥4.06 | ¥24.37 | — | 256K | text |
| Qwen3.6-35B-A3BQwen | ¥1.68 | ¥10.05 | — | 256K | text |
| Qwen3.6-PlusQwen | Free | Free | — | 1M | text |
| Qwen3.7-MaxQwen | ¥8.46 | ¥25.39 | ¥1.69 | 1M | text |
| Qwen3 8BQwen | ¥0.237 | ¥0.9343 | — | 128K | text |
| Qwen3 Coder 30b A3B InstructQwen | ¥0.4739 | ¥1.83 | — | 160K | text |
| Qwen3 Coder 480B A35B InstructQwen | ¥2.57 | ¥10.49 | — | 256K | text |
| Qwen3 Coder NextQwen | ¥1.35 | ¥10.16 | — | 256K | text |
| Qwen3 MaxQwen | ¥14.29 | ¥57.21 | — | 256K | text |
| Qwen3 Next 80B A3B InstructQwen | ¥1.02 | ¥10.16 | — | 128K | text |
| Qwen3 Next 80B A3B ThinkingQwen | ¥1.02 | ¥10.16 | — | 128K | text |
| Qwen3 Omni 30B A3B InstructQwen | ¥1.69 | ¥6.57 | — | 64K | text |
| Qwen3 Omni 30B A3B ThinkingQwen | ¥1.69 | ¥6.57 | — | 64K | text |
| Qwen3 VL 235B A22B InstructQwen | ¥2.03 | ¥10.16 | — | 128K | textimage |
| Qwen3 VL 235B A22B ThinkingQwen | ¥6.63 | ¥26.74 | — | 128K | textimage |
| Qwen MT PlusQwen | ¥1.69 | ¥5.08 | — | 16K | text |
| qwen/qwen3-vl-30b-a3b-instructQwen | ¥1.35 | ¥4.74 | — | 128K | textimage |
| qwen/qwen3-vl-30b-a3b-thinkingQwen | ¥1.35 | ¥6.77 | — | 128K | textimage |
| qwen/qwen3-vl-8b-instructQwen | ¥0.5416 | ¥3.39 | — | 128K | textimage |
| Ring-2.6-1T | ¥2.03 | ¥16.93 | ¥0.4062 | 256K | text |
| Sao10k L3 8B Lunaris | ¥0.3385 | ¥0.3385 | — | 8K | text |
| Step 3.7 Flash | ¥1.35 | ¥7.79 | ¥0.2708 | 256K | text |
| Wizardlm 2 8x22B | ¥4.2 | ¥4.2 | — | 65.5K | text |
| XiaomiMiMo/MiMo-V2.5 | ¥1.14 | ¥2.27 | ¥0.023 | 1M | text |
| XiaomiMiMo/MiMo-V2.5-Pro | ¥3.53 | ¥7.07 | ¥0.0291 | 1M | text |
| XiaomiMiMo/MiMo-V2-Flash | ¥0.7447 | ¥2.23 | ¥0.1625 | 256K | text |
| XiaomiMiMo/MiMo-V2-Pro | ¥13.54 | ¥40.62 | ¥2.71 | 1M | text |
| zai-org/glm-4.5-airGLM | ¥0.8801 | ¥5.75 | ¥0.1693 | 128K | text |