Novita AI models — pricing & benchmarks

Official siteDocsPricingAPI

Novita AI provides 200+ Model APIs, custom deployment, GPU Instances, and Serverless GPUs. Scale AI, optimize performance, and innovate with ease and efficiency. Inference platform · OpenAI-compatible API · Fine Tuning · Lora · Low Cost · Open Source · Serverless

Intelligence vs Price

Best value among Novita models on this chart: Kimi K3 · GLM-5.3 · Kimi K2 (and 6 more on the dashed frontier). Prices use each model's lowest available Novita price across regions. Hover any dot for full pricing, or click a creator in the legend to isolate.

Novita models

134 models in Global, 134 with pricing

All Model Types

All Creators

US Dollar ($)

Per 1M tokens

Model	Creator	Input Price, $	Output Price, $	Context	Max Output	Intelligence	Coding
Kimi K3	Moonshot AI (Kimi)	3.00	15.00	1.0M	944K	#1	#1
GLM-5.3	Zhipu AI	1.40	4.40	1.3M	131K	#2	#2
Qwen3.8 Max	Alibaba	2.00	6.00	1.0M	131K	#3	#3
Kimi K2	Moonshot AI (Kimi)	0.6	2.50	262K	100K	#4	#19
DeepSeek V4 Pro	DeepSeek	1.60	3.20	1.0M	393K	#5	#5
GLM-5.2	Zhipu AI	1.40	4.40	1.0M	262K	#6	#6
DeepSeek V4 Flash	DeepSeek	0.14	0.28	1.3M	1.0M	#7	#4
Qwen3.7 Max	Alibaba	1.25	3.75	1.0M	131K	#8	#7
MiniMax M3	MiniMax	0.3	1.20	1.0M	512K	#9	#12
Kimi K2.6	Moonshot AI (Kimi)	0.8	3.40	262K	236K	#10	#8
Kimi K2.7 Code	Moonshot AI (Kimi)	0.95	4.00	262K	236K	#11	#9
MiMo V2.5 Pro	Xiaomi	0.522	1.04	1.1M	131K	#12	#10
Hy 3	Tencent	0.14	0.58	262K	128K	#13	#11
GLM-5.1	Zhipu AI	1.38	4.40	205K	203K	#14	#13
GLM-5	Zhipu AI	1.00	3.20	205K	131K	#15	N/A
GLM-5 Turbo	Zhipu AI	1.20	4.00	203K	131K	#16	N/A
MiniMax M2.7	MiniMax	0.3	1.20	1.0M	131K	#17	#15
InclusionAI Ling 3 Flash	Inclusionai	0.06	0.18	262K	33K	#18	#16
Qwen3.6 27B	Alibaba	0.6	3.60	262K	236K	#19	#14
Kimi K2.5	Moonshot AI (Kimi)	0.6	3.00	262K	236K	#20	#20
GLM-5V Turbo	Zhipu AI	1.20	4.00	205K	131K	#21	N/A
Qwen3.5 27B	Alibaba	0.3	2.40	262K	66K	#22	N/A
MiniMax M2.5	MiniMax	0.3	1.20	1.0M	131K	#23	N/A
GLM-4.7	Zhipu AI	0.6	2.20	205K	131K	#24	#23
Qwen3.5 397B A17B	Alibaba	0.6	3.60	262K	66K	#25	#18
Kimi K2 Thinking	Moonshot AI (Kimi)	0.6	2.50	262K	100K	#26	N/A
Qwen3.5 122B A10B	Alibaba	0.4	3.20	262K	236K	#27	#22
DeepSeek V3.2	DeepSeek	0.269	0.4	164K	147K	#28	#24
Qwen3.6 35B A3B	Alibaba	0.248	1.49	262K	236K	#29	#26
MiniMax M2.1	MiniMax	0.3	1.20	1.0M	131K	#30	N/A
MiMo V2 Flash	Xiaomi	0.11	0.33	262K	32K	#31	#17
DeepSeek V3.1 Terminus	DeepSeek	0.27	1.00	164K	66K	#32	#25
Step 3.7 Flash	StepFun	0.2	1.15	262K	256K	#33	#27
Qwen3.5 35B A3B	Alibaba	0.25	2.00	262K	236K	#34	#28
GLM-4.6	Zhipu AI	0.55	2.20	205K	131K	#35	#21
MiniMax M2	MiniMax	0.3	1.20	205K	131K	#36	N/A
Qwen3 Max	Alibaba	2.11	8.45	262K	66K	#37	N/A
GPT OSS 120B	OpenAI	0.05	0.25	131K	131K	#38	#30
GLM-4.7 Flash	Zhipu AI	0.07	0.4	203K	131K	#39	N/A
DeepSeek V3.1	DeepSeek	0.27	1.00	164K	128K	#40	N/A
Qwen3 Coder Next	Alibaba	0.2	1.50	262K	236K	#41	#29
DeepSeek R1	DeepSeek	4.00	4.00	164K	66K	#42	#31
Qwen3 235B A22B	Alibaba	0.2	0.8	262K	236K	#43	#33
GLM-4.5	Zhipu AI	0.6	2.20	131K	98K	#44	N/A
Qwen3 235B A22B Instruct	Alibaba	0.09	0.58	262K	16K	#45	N/A
Qwen3 Coder 480B A35B Instruct	Alibaba	0.38	1.55	262K	66K	#46	N/A
MiniMax M1 80k	MiniMax	0.55	2.20	1.0M	40K	#47	N/A
GLM-4.6V	Zhipu AI	0.3	0.9	131K	33K	#48	N/A
GLM-4.5 Air	Zhipu AI	0.13	0.85	131K	98K	#49	N/A
GPT OSS 20B	OpenAI	0.04	0.15	131K	131K	#51	#35
DeepSeek V3 324	DeepSeek	0.27	1.12	164K	66K	#50	#34
Qwen3 30B A3B	Alibaba	0.09	0.45	131K	20K	#52	#38
Nemotron Nano 3 30B A3B	NVIDIA	0.05	0.2	262K	236K	#53	#37
Qwen3 VL 235B A22B Instruct	Alibaba	0.3	1.50	262K	129K	#54	N/A
DeepSeek V3	DeepSeek	0.89	0.89	164K	82K	#55	#32
Qwen3 Next 80B A3B Instruct	Alibaba	0.15	1.50	262K	236K	#56	N/A
Qwen3 Coder 30B A3B Instruct	Alibaba	0.07	0.27	262K	236K	#57	N/A
Qwen3 32B	Alibaba	0.1	0.45	131K	41K	#58	#36
DeepSeek R1 Distill Qwen 32B	DeepSeek	0.3	0.3	131K	32K	#59	N/A
Qwen3 VL 30B A3B Instruct	Alibaba	0.2	0.7	262K	33K	#60	N/A
DeepSeek R1 Distill Llama 70B	DeepSeek	0.8	0.8	131K	8K	#61	N/A
DeepSeek R1 Distill Qwen 14B	DeepSeek	0.15	0.15	131K	16K	#62	N/A
Qwen2.5 72B Instruct	Alibaba	0.38	0.4	131K	16K	#63	N/A
Llama 3.3 70B Instruct	Meta	0.135	0.4	131K	120K	#64	#39
GLM-4.5V	Zhipu AI	0.6	1.80	131K	32K	#65	N/A
Qwen3 8B	Alibaba	0.035	0.138	131K	20K	#66	#40
Qwen3 VL 8B Instruct	Alibaba	0.08	0.5	262K	33K	#67	N/A
Llama 3.1 8B Instruct	Meta	0.02	0.05	200K	128K	#68	#41
Qwen3 Omni 30B A3B Instruct	Alibaba	0.25	0.97	66K	16K	#69	N/A
Llama 3.2 3B Instruct	Meta	0.03	0.05	131K	118K	#70	N/A
Llama 3 70B Instruct	Meta	0.51	0.74	131K	8K	#71	N/A
Llama 3.2 1B Instruct	Meta	0.02	0.02	131K	54K	#72	N/A
Llama 3 8B Instruct	Meta	0.04	0.04	32K	8K	#73	N/A
AutoGLM Phone 9B Multilingual	Zhipu AI	0.035	0.138	66K	N/A	N/A	N/A
BaiChuan M2 32B	Baichuan	0.07	0.07	131K	N/A	N/A	N/A
BGE Reranker M3 2	Baai	0.01	0.01	8K	8K	N/A	N/A
BGE-M3	Baai	0.01	0.01	60K	N/A	N/A	N/A
CoBuddy	Baidu	0.28	1.13	131K	66K	N/A	N/A
DeepSeek Prover V2 671B	DeepSeek	0.7	2.50	160K	N/A	N/A	N/A
DeepSeek R1 528	DeepSeek	0.7	2.50	164K	33K	N/A	N/A
DeepSeek R1 528B Qwen3 8B	DeepSeek	0.06	0.09	128K	32K	N/A	N/A
DeepSeek R1 Turbo	DeepSeek	0.7	2.50	64K	16K	N/A	N/A
DeepSeek V3 Community	DeepSeek	0.89	0.89	64K	8K	N/A	N/A
DeepSeek V3 Turbo	DeepSeek	0.4	1.30	64K	16K	N/A	N/A
DeepSeek V3.2 Exp	DeepSeek	0.27	0.41	164K	66K	N/A	N/A
DeepSeek V4 731 Flash	DeepSeek	0.44	1.32	1.3M	944K	N/A	N/A
DeepSeek V4 Flash Vision Exp	DeepSeek	0.44	1.32	1.0M	393K	N/A	N/A
DeepSeek V4 Pro	DeepSeek	1.32	3.96	1.0M	944K	N/A	N/A
DeepSeek-OCR	DeepSeek	0.03	0.03	8K	8K	N/A	N/A
DeepSeek-OCR 2	DeepSeek	0.03	0.03	8K	8K	N/A	N/A
ERNIE 4.5 21B A3B	Baidu	0.07	0.28	120K	8K	N/A	N/A
ERNIE 4.5 21B A3B Thinking	Baidu	0.07	0.28	131K	66K	N/A	N/A
ERNIE 4.5 300B A47B Paddle	Baidu	0.28	1.10	123K	12K	N/A	N/A
ERNIE 4.5 VL 28B A3B	Baidu	0.14	0.56	30K	8K	N/A	N/A
ERNIE 4.5 VL 28B A3B Thinking	Baidu	0.39	0.39	131K	66K	N/A	N/A
ERNIE 4.5 VL 424B A47B	Baidu	0.42	1.25	123K	16K	N/A	N/A
Gemma 3 12B Instruct	Google	0.05	0.1	131K	16K	N/A	N/A
Gemma 3 27B Instruct	Google	0.119	0.2	262K	131K	N/A	N/A
Gemma 4 26B A4B IT	Google	0.13	0.4	262K	131K	N/A	N/A
Gemma 4 31B IT	Google	0.14	0.4	262K	131K	N/A	N/A
GLM-4 32B	Zhipu AI	0.55	1.66	128K	32K	N/A	N/A
GLM-4.7 H	Zhipu AI	0.6	2.20	205K	131K	N/A	N/A
Hermes 2 Pro Llama 3 8B	Nous Research	0.14	0.14	8K	8K	N/A	N/A
InclusionAI Ling 3 Flash Fast	Inclusionai	0.06	0.18	262K	33K	N/A	N/A
Kimi K2 Instruct	Moonshot AI (Kimi)	0.57	2.30	262K	100K	N/A	N/A
KwaiPilot KAT Pro Coder	KwaiPilot	0.3	1.20	256K	128K	N/A	N/A
L3 70B Euryale V2.1	Sao10K	1.48	1.48	8K	8K	N/A	N/A
L3 Lunaris 8B	Sao10K	0.05	0.05	8K	8K	N/A	N/A
L3 Stheno 3.2 8B	Sao10K	0.05	0.05	8K	N/A	N/A	N/A
L3.1 70B Euryale V2.2	Sao10K	1.48	1.48	131K	8K	N/A	N/A
Llama 4 17B Maverick Instruct	Meta	0.27	0.85	1.0M	16K	N/A	N/A
Llama 4 17B Scout Instruct	Meta	0.18	0.59	10.0M	16K	N/A	N/A
Macaron V1 Tall	Mindai	0.45	2.60	262K	33K	N/A	N/A
Macaron V1 Venti	Mindai	1.50	4.50	1.0M	131K	N/A	N/A
MiMo V2.5	Xiaomi	0.168	0.336	1.1M	131K	N/A	N/A
MiniMax M2.5 Highspeed	MiniMax	0.6	2.40	205K	131K	N/A	N/A
MiniMax M2.7 Highspeed	MiniMax	0.6	2.40	205K	131K	N/A	N/A
MT Plus	Alibaba	0.25	0.75	16K	8K	N/A	N/A
MythoMax L2 13B	Gryphe	0.09	0.09	8K	7K	N/A	N/A
Nemo	Mistral AI	0.04	0.17	131K	16K	N/A	N/A
PaddleOCR VL	PaddlePaddle (Baidu)	0.02	0.02	16K	16K	N/A	N/A
Qwen2.5 7B Instruct	Alibaba	0.07	0.07	33K	33K	N/A	N/A
Qwen2.5 VL 72B Instruct	Alibaba	0.8	0.8	131K	128K	N/A	N/A
Qwen3 235B A22B Thinking	Alibaba	0.3	3.00	262K	118K	N/A	N/A
Qwen3 4B	Alibaba	0.03	0.03	128K	20K	N/A	N/A
Qwen3 Embedding 0.6B	Alibaba	0.07	N/A	33K	N/A	N/A	N/A
Qwen3 Embedding 8B	Alibaba	0.07	N/A	41K	4K	N/A	N/A
Qwen3 Next 80B A3B Thinking	Alibaba	0.15	1.50	262K	66K	N/A	N/A
Qwen3 Omni 30B A3B Thinking	Alibaba	0.25	0.97	66K	16K	N/A	N/A
Qwen3 Reranker 8B	Alibaba	0.05	0.05	41K	4K	N/A	N/A
Qwen3 VL 235B A22B Thinking	Alibaba	0.98	3.95	262K	33K	N/A	N/A
Qwen3 VL 30B A3B Thinking	Alibaba	0.2	1.00	262K	33K	N/A	N/A
Skywork R1 4 Lite	Skywork	0.2	0.6	262K	66K	N/A	N/A
WizardLM 2 8x22B	Microsoft	0.62	0.62	66K	8K	N/A	N/A

Novita

Intelligence vs Price

Novita modelsAPIGET/api/v1/providers/novita/models

Novita models