
Novita AI
Model AggregatorNovita 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.
Models
142
Prompt Caching
✓
Batch Discount
—
Tool Calling
✓
Model142
| Model | Input Price | Output Price | Cached Input | Context | Modality |
|---|---|---|---|---|---|
| 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 | $0.035 | $0.138 | — | 64K | text |
| BaiChuan M2 32B | $0.07 | $0.07 | — | 128K | text |
| Bunny | Free | Free | — | 256K | text |
| CoBuddy | $0.28 | $1.13 | $0.07 | 128K | text |
| DeepSeek-OCRDeepSeek | $0.03 | $0.03 | — | 8K | text |
| DeepSeek-OCR 2DeepSeek | $0.03 | $0.03 | — | 8K | text |
| Deepseek Prover V2 671BDeepSeek | $0.7 | $2.5 | — | 160K | text |
| DeepSeek R1DeepSeek | $4 | $4 | — | 64K | text |
| DeepSeek R1DeepSeek | $4 | $4 | — | 64K | text |
| DeepSeek R1 0528DeepSeek | $0.7 | $2.5 | $0.35 | 160K | text |
| DeepSeek R1 0528 Qwen3 8BQwen | $0.06 | $0.09 | — | 128K | text |
| DeepSeek R1 Distill LLama 70BLlama | $0.8 | $0.8 | — | 8K | text |
| DeepSeek R1 Distill Qwen 14BQwen | $0.15 | $0.15 | — | 32K | text |
| DeepSeek R1 Distill Qwen 32BQwen | $0.3 | $0.3 | — | 64K | text |
| DeepSeek R1 (Turbo) DeepSeek | $0.7 | $2.5 | — | 64K | text |
| DeepSeek V3DeepSeek | $0.89 | $0.89 | — | 64K | text |
| DeepSeek V3DeepSeek | $0.89 | $0.89 | — | 64K | text |
| DeepSeek V3 0324DeepSeek | $0.27 | $1.12 | $0.135 | 160K | text |
| DeepSeek V3.1DeepSeek | $0.27 | $1 | $0.135 | 128K | text |
| Deepseek V3.1 TerminusDeepSeek | $0.27 | $1 | $0.135 | 128K | text |
| Deepseek V3.2DeepSeek | $0.269 | $0.4 | $0.1345 | 160K | text |
| Deepseek V3.2 ExpDeepSeek | $0.27 | $0.41 | — | 160K | text |
| DeepSeek V3 (Turbo) DeepSeek | $0.4 | $1.3 | — | 64K | text |
| Deepseek V4 FlashDeepSeek | $0.14 | $0.28 | $0.028 | 1M | text |
| Deepseek V4 ProDeepSeek | $1.6 | $3.2 | $0.135 | 1M | text |
| dev/glm46GLM | Free | Free | — | 256K | text |
| ERNIE 4.5 21B A3B | $0.07 | $0.28 | — | 120K | text |
| ERNIE-4.5-21B-A3B-Thinking | $0.07 | $0.28 | — | 128K | text |
| ERNIE 4.5 300B A47B | $0.28 | $1.1 | — | 123K | text |
| ERNIE 4.5 VL 28B A3B | $0.14 | $0.56 | — | 30K | textimage |
| ERNIE-4.5-VL-28B-A3B-Thinking | $0.39 | $0.39 | — | 128K | textimage |
| ERNIE 4.5 VL 424B A47B | $0.42 | $1.25 | — | 123K | textimage |
| Gemma3 12BGemma | $0.05 | $0.1 | — | 128K | text |
| Gemma 3 27BGemma | $0.119 | $0.2 | — | 96K | text |
| Gemma 4 26B A4BGemma | $0.13 | $0.4 | — | 256K | text |
| Gemma 4 31BGemma | $0.14 | $0.4 | — | 256K | text |
| GLM-4-32B-0414GLM | $0.55 | $1.66 | — | 32K | text |
| GLM-4.5GLM | $0.6 | $2.2 | $0.11 | 128K | text |
| GLM 4.5VGLM | $0.6 | $1.8 | $0.11 | 64K | text |
| GLM 4.6GLM | $0.55 | $2.2 | $0.11 | 200K | text |
| GLM 4.6VGLM | $0.3 | $0.9 | $0.055 | 128K | text |
| GLM-4.7GLM | $0.6 | $2.2 | $0.11 | 200K | text |
| GLM-4.7GLM | $0.6 | $2.2 | $0.11 | 200K | text |
| GLM-4.7-FlashGLM | $0.07 | $0.4 | $0.01 | 200K | text |
| GLM-5GLM | $1 | $3.2 | $0.2 | 202.8K | text |
| GLM-5.1GLM | $1.38 | $4.4 | $0.26 | 200K | text |
| GLM 5.2GLM | $1.4 | $4.4 | $0.26 | 1M | text |
| GLM-5-TurboGLM | $1.2 | $4 | $0.24 | 202.8K | text |
| GLM-5V-TurboGLM | $1.2 | $4 | $0.24 | 200K | text |
| gt-4p | Free | Free | — | — | text |
| Hermes 2 Pro Llama 3 8BLlama | $0.14 | $0.14 | — | 8K | text |
| Hy3 | $0.14 | $0.58 | $0.035 | 256K | text |
| Kat Coder Pro | $0.3 | $1.2 | $0.06 | 256K | text |
| Kimi K2 0905Kimi | $0.6 | $2.5 | — | 256K | text |
| Kimi K2.5Kimi | $0.6 | $3 | $0.1 | 256K | text |
| Kimi K2.6Kimi | $0.8 | $3.4 | $0.16 | 256K | text |
| Kimi K2.7 CodeKimi | $0.95 | $4 | $0.19 | 256K | text |
| Kimi K2 InstructKimi | $0.57 | $2.3 | — | 128K | text |
| Kimi K2 ThinkingKimi | $0.6 | $2.5 | $0.15 | 256K | text |
| Kimi K3Kimi | $3 | $15 | $0.3 | 1M | text |
| L31 70B Euryale V2.2 | $1.48 | $1.48 | — | 8K | text |
| L3 70B Euryale V2.1 | $1.48 | $1.48 | — | 8K | text |
| L3 8B Stheno V3.2 | $0.05 | $0.05 | — | 8K | text |
| Ling-2.6-1T | $0.3 | $2.5 | $0.06 | 256K | text |
| Ling-2.6-flash | $0.1 | $0.3 | $0.02 | 256K | text |
| Ling-2.6-flash | $0.1 | $0.3 | $0.02 | 256K | text |
| Ling-3.0-flash | Free | Free | — | 256K | text |
| Llama 3.1 8B InstructLlama | $0.02 | $0.05 | — | 16K | text |
| Llama 3.2 1B Instruct Llama | $0.02 | $0.02 | — | 131K | text |
| Llama 3.2 3B InstructLlama | $0.03 | $0.05 | — | 32K | text |
| Llama 3.3 70B InstructLlama | $0.135 | $0.4 | — | 6K | text |
| Llama3 70B InstructLlama | $0.51 | $0.74 | — | 8K | text |
| Llama 3 8B InstructLlama | $0.04 | $0.04 | — | 8K | text |
| Llama 4 Maverick InstructLlama | $0.27 | $0.85 | — | 1M | text |
| Llama 4 Scout InstructLlama | $0.18 | $0.59 | — | 128K | text |
| M2-herMiniMax | Free | Free | — | 32K | text |
| Macaron V1 Venti | Free | Free | — | 1M | text |
| MiniMax M1MiniMax | $0.55 | $2.2 | — | 1M | text |
| MiniMax-M2MiniMax | $0.3 | $1.2 | $0.03 | 200K | text |
| Minimax M2.1MiniMax | $0.3 | $1.2 | $0.03 | 200K | text |
| MiniMax M2.5MiniMax | $0.3 | $1.2 | $0.03 | 200K | text |
| MiniMax M2.5-highspeedMiniMax | $0.6 | $2.4 | $0.03 | 200K | text |
| MiniMax M2.7MiniMax | $0.3 | $1.2 | $0.06 | 200K | text |
| MiniMax M2.7-highspeedMiniMax | $0.6 | $2.4 | $0.06 | 200K | text |
| MiniMax M3MiniMax | $0.3 | $1.2 | $0.06 | 1M | text |
| Mistral NemoMistral | $0.04 | $0.17 | — | 60.3K | text |
| Mythomax L2 13B | $0.09 | $0.09 | — | 4K | text |
| Nemotron 3 Nano 30B A3B | $0.05 | $0.2 | — | 256K | text |
| Nex-N2-Pro | Free | Free | — | 256K | text |
| Nous Hermes Llama2 13BLlama | $0.17 | $0.17 | — | 4K | text |
| OpenAI GPT OSS 120BGPT-OSS | $0.05 | $0.25 | — | 128K | text |
| OpenAI: GPT OSS 20BGPT-OSS | $0.04 | $0.15 | — | 128K | text |
| OpenChat 7B | $0.06 | $0.06 | — | 4K | text |
| Openhermes2.5 Mistral 7BMistral | $0.17 | $0.17 | — | 4K | text |
| PaddleOCR-VL | $0.02 | $0.02 | — | 16K | textimage |
| Qwen 2.5 72B InstructQwen | $0.38 | $0.4 | — | 32K | text |
| Qwen2.5 7B InstructQwen | $0.07 | $0.07 | — | 32K | text |
| Qwen2.5 VL 72B InstructQwen | $0.8 | $0.8 | — | 32K | textimage |
| Qwen 2 7B InstructQwen | $0.054 | $0.054 | — | 32K | text |
| Qwen 2 VL 72B InstructQwen | $0.45 | $0.45 | — | 32K | textimage |
| Qwen3 235B A22BQwen | $0.2 | $0.8 | — | 40K | text |
| Qwen3 235B A22B Instruct 2507Qwen | $0.09 | $0.58 | — | 128K | text |
| Qwen3 235B A22b Thinking 2507Qwen | $0.3 | $3 | — | 128K | text |
| Qwen3 30B A3BQwen | $0.09 | $0.45 | — | 40K | text |
| Qwen3 32BQwen | $0.1 | $0.45 | — | 40K | text |
| Qwen3 4BQwen | $0.03 | $0.03 | — | 128K | text |
| Qwen3.5-122B-A10BQwen | $0.4 | $3.2 | — | 256K | text |
| Qwen3.5-27BQwen | $0.3 | $2.4 | — | 256K | text |
| Qwen3.5-35B-A3BQwen | $0.25 | $2 | — | 256K | text |
| Qwen3.5-397B-A17BQwen | $0.6 | $3.6 | — | 256K | text |
| Qwen3.5-PlusQwen | Free | Free | — | 1M | text |
| Qwen3.6-27BQwen | $0.6 | $3.6 | — | 256K | text |
| Qwen3.6-35B-A3BQwen | $0.248 | $1.49 | — | 256K | text |
| Qwen3.6-PlusQwen | Free | Free | — | 1M | text |
| Qwen3.7-MaxQwen | $1.25 | $3.75 | $0.25 | 1M | text |
| Qwen3 8BQwen | $0.035 | $0.138 | — | 128K | text |
| Qwen3 Coder 30b A3B InstructQwen | $0.07 | $0.27 | — | 160K | text |
| Qwen3 Coder 480B A35B InstructQwen | $0.38 | $1.55 | — | 256K | text |
| Qwen3 Coder NextQwen | $0.2 | $1.5 | — | 256K | text |
| Qwen3 MaxQwen | $2.11 | $8.45 | — | 256K | text |
| Qwen3 Next 80B A3B InstructQwen | $0.15 | $1.5 | — | 128K | text |
| Qwen3 Next 80B A3B ThinkingQwen | $0.15 | $1.5 | — | 128K | text |
| Qwen3 Omni 30B A3B InstructQwen | $0.25 | $0.97 | — | 64K | text |
| Qwen3 Omni 30B A3B ThinkingQwen | $0.25 | $0.97 | — | 64K | text |
| Qwen3 VL 235B A22B InstructQwen | $0.3 | $1.5 | — | 128K | textimage |
| Qwen3 VL 235B A22B ThinkingQwen | $0.98 | $3.95 | — | 128K | textimage |
| Qwen MT PlusQwen | $0.25 | $0.75 | — | 16K | text |
| qwen/qwen3-vl-30b-a3b-instructQwen | $0.2 | $0.7 | — | 128K | textimage |
| qwen/qwen3-vl-30b-a3b-thinkingQwen | $0.2 | $1 | — | 128K | textimage |
| qwen/qwen3-vl-8b-instructQwen | $0.08 | $0.5 | — | 128K | textimage |
| Ring-2.6-1T | $0.3 | $2.5 | $0.06 | 256K | text |
| Sao10k L3 8B Lunaris | $0.05 | $0.05 | — | 8K | text |
| Step 3.7 Flash | $0.2 | $1.15 | $0.04 | 256K | text |
| Wizardlm 2 8x22B | $0.62 | $0.62 | — | 65.5K | text |
| XiaomiMiMo/MiMo-V2.5 | $0.168 | $0.336 | $0.0034 | 1M | text |
| XiaomiMiMo/MiMo-V2.5-Pro | $0.522 | $1.04 | $0.0043 | 1M | text |
| XiaomiMiMo/MiMo-V2-Flash | $0.11 | $0.33 | $0.024 | 256K | text |
| XiaomiMiMo/MiMo-V2-Pro | $2 | $6 | $0.4 | 1M | text |
| zai-org/glm-4.5-airGLM | $0.13 | $0.85 | $0.025 | 128K | text |
