Novita AI logo

Novita AI

Model Aggregator

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.

Models
142
Prompt Caching
Batch Discount
Tool Calling
Model142
ModelInput PriceOutput Price
ai_infer_test_1FreeFree
ai_infer_test_2FreeFree
ai_infer_test_3FreeFree
AutoGLM-Phone-9B-MultilingualGLM$0.035$0.138
BaiChuan M2 32B$0.07$0.07
BunnyFreeFree
CoBuddy$0.28$1.13
DeepSeek-OCRDeepSeek$0.03$0.03
DeepSeek-OCR 2DeepSeek$0.03$0.03
Deepseek Prover V2 671BDeepSeek$0.7$2.5
DeepSeek R1DeepSeek$4$4
DeepSeek R1DeepSeek$4$4
DeepSeek R1 0528DeepSeek$0.7$2.5
DeepSeek R1 0528 Qwen3 8BQwen$0.06$0.09
DeepSeek R1 Distill LLama 70BLlama$0.8$0.8
DeepSeek R1 Distill Qwen 14BQwen$0.15$0.15
DeepSeek R1 Distill Qwen 32BQwen$0.3$0.3
DeepSeek R1 (Turbo) DeepSeek$0.7$2.5
DeepSeek V3DeepSeek$0.89$0.89
DeepSeek V3DeepSeek$0.89$0.89
DeepSeek V3 0324DeepSeek$0.27$1.12
DeepSeek V3.1DeepSeek$0.27$1
Deepseek V3.1 TerminusDeepSeek$0.27$1
Deepseek V3.2DeepSeek$0.269$0.4
Deepseek V3.2 ExpDeepSeek$0.27$0.41
DeepSeek V3 (Turbo) DeepSeek$0.4$1.3
Deepseek V4 FlashDeepSeek$0.14$0.28
Deepseek V4 ProDeepSeek$1.6$3.2
dev/glm46GLMFreeFree
ERNIE 4.5 21B A3B$0.07$0.28
ERNIE-4.5-21B-A3B-Thinking$0.07$0.28
ERNIE 4.5 300B A47B$0.28$1.1
ERNIE 4.5 VL 28B A3B$0.14$0.56
ERNIE-4.5-VL-28B-A3B-Thinking$0.39$0.39
ERNIE 4.5 VL 424B A47B$0.42$1.25
Gemma3 12BGemma$0.05$0.1
Gemma 3 27BGemma$0.119$0.2
Gemma 4 26B A4BGemma$0.13$0.4
Gemma 4 31BGemma$0.14$0.4
GLM-4-32B-0414GLM$0.55$1.66
GLM-4.5GLM$0.6$2.2
GLM 4.5VGLM$0.6$1.8
GLM 4.6GLM$0.55$2.2
GLM 4.6VGLM$0.3$0.9
GLM-4.7GLM$0.6$2.2
GLM-4.7GLM$0.6$2.2
GLM-4.7-FlashGLM$0.07$0.4
GLM-5GLM$1$3.2
GLM-5.1GLM$1.38$4.4
GLM 5.2GLM$1.4$4.4
GLM-5-TurboGLM$1.2$4
GLM-5V-TurboGLM$1.2$4
gt-4pFreeFree
Hermes 2 Pro Llama 3 8BLlama$0.14$0.14
Hy3$0.14$0.58
Kat Coder Pro$0.3$1.2
Kimi K2 0905Kimi$0.6$2.5
Kimi K2.5Kimi$0.6$3
Kimi K2.6Kimi$0.8$3.4
Kimi K2.7 CodeKimi$0.95$4
Kimi K2 InstructKimi$0.57$2.3
Kimi K2 ThinkingKimi$0.6$2.5
Kimi K3Kimi$3$15
L31 70B Euryale V2.2$1.48$1.48
L3 70B Euryale V2.1 $1.48$1.48
L3 8B Stheno V3.2$0.05$0.05
Ling-2.6-1T$0.3$2.5
Ling-2.6-flash$0.1$0.3
Ling-2.6-flash$0.1$0.3
Ling-3.0-flashFreeFree
Llama 3.1 8B InstructLlama$0.02$0.05
Llama 3.2 1B Instruct Llama$0.02$0.02
Llama 3.2 3B InstructLlama$0.03$0.05
Llama 3.3 70B InstructLlama$0.135$0.4
Llama3 70B InstructLlama$0.51$0.74
Llama 3 8B InstructLlama$0.04$0.04
Llama 4 Maverick InstructLlama$0.27$0.85
Llama 4 Scout InstructLlama$0.18$0.59
M2-herMiniMaxFreeFree
Macaron V1 VentiFreeFree
MiniMax M1MiniMax$0.55$2.2
MiniMax-M2MiniMax$0.3$1.2
Minimax M2.1MiniMax$0.3$1.2
MiniMax M2.5MiniMax$0.3$1.2
MiniMax M2.5-highspeedMiniMax$0.6$2.4
MiniMax M2.7MiniMax$0.3$1.2
MiniMax M2.7-highspeedMiniMax$0.6$2.4
MiniMax M3MiniMax$0.3$1.2
Mistral NemoMistral$0.04$0.17
Mythomax L2 13B$0.09$0.09
Nemotron 3 Nano 30B A3B$0.05$0.2
Nex-N2-ProFreeFree
Nous Hermes Llama2 13BLlama$0.17$0.17
OpenAI GPT OSS 120BGPT-OSS$0.05$0.25
OpenAI: GPT OSS 20BGPT-OSS$0.04$0.15
OpenChat 7B$0.06$0.06
Openhermes2.5 Mistral 7BMistral$0.17$0.17
PaddleOCR-VL$0.02$0.02
Qwen 2.5 72B InstructQwen$0.38$0.4
Qwen2.5 7B InstructQwen$0.07$0.07
Qwen2.5 VL 72B InstructQwen$0.8$0.8
Qwen 2 7B InstructQwen$0.054$0.054
Qwen 2 VL 72B InstructQwen$0.45$0.45
Qwen3 235B A22BQwen$0.2$0.8
Qwen3 235B A22B Instruct 2507Qwen$0.09$0.58
Qwen3 235B A22b Thinking 2507Qwen$0.3$3
Qwen3 30B A3BQwen$0.09$0.45
Qwen3 32BQwen$0.1$0.45
Qwen3 4BQwen$0.03$0.03
Qwen3.5-122B-A10BQwen$0.4$3.2
Qwen3.5-27BQwen$0.3$2.4
Qwen3.5-35B-A3BQwen$0.25$2
Qwen3.5-397B-A17BQwen$0.6$3.6
Qwen3.5-PlusQwenFreeFree
Qwen3.6-27BQwen$0.6$3.6
Qwen3.6-35B-A3BQwen$0.248$1.49
Qwen3.6-PlusQwenFreeFree
Qwen3.7-MaxQwen$1.25$3.75
Qwen3 8BQwen$0.035$0.138
Qwen3 Coder 30b A3B InstructQwen$0.07$0.27
Qwen3 Coder 480B A35B InstructQwen$0.38$1.55
Qwen3 Coder NextQwen$0.2$1.5
Qwen3 MaxQwen$2.11$8.45
Qwen3 Next 80B A3B InstructQwen$0.15$1.5
Qwen3 Next 80B A3B ThinkingQwen$0.15$1.5
Qwen3 Omni 30B A3B InstructQwen$0.25$0.97
Qwen3 Omni 30B A3B ThinkingQwen$0.25$0.97
Qwen3 VL 235B A22B InstructQwen$0.3$1.5
Qwen3 VL 235B A22B ThinkingQwen$0.98$3.95
Qwen MT PlusQwen$0.25$0.75
qwen/qwen3-vl-30b-a3b-instructQwen$0.2$0.7
qwen/qwen3-vl-30b-a3b-thinkingQwen$0.2$1
qwen/qwen3-vl-8b-instructQwen$0.08$0.5
Ring-2.6-1T$0.3$2.5
Sao10k L3 8B Lunaris $0.05$0.05
Step 3.7 Flash$0.2$1.15
Wizardlm 2 8x22B$0.62$0.62
XiaomiMiMo/MiMo-V2.5$0.168$0.336
XiaomiMiMo/MiMo-V2.5-Pro$0.522$1.04
XiaomiMiMo/MiMo-V2-Flash$0.11$0.33
XiaomiMiMo/MiMo-V2-Pro$2$6
zai-org/glm-4.5-airGLM$0.13$0.85