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: GLM-4.7 · Kimi K2 Thinking · MiniMax M2.1 (and 6 more on the dashed frontier). Hover any dot for full pricing, or click a creator in the legend to isolate.

Novita models

85 models, 85 with pricing

All Model Types

All Creators

US Dollar ($)

Per 1M tokens

Model	Creator	Input Price, $	Output Price, $	Context	Max Output	Inference Providers	Intelligence	Coding
GLM-4.7	Zhipu AI	0.4	1.75	205K	131K	compare (13)	33.7#1	45.3#3
Kimi K2 Thinking	Moonshot AI (Kimi)	0.47	1.20	262K	100K	compare (13)	32.7#2	N/A
MiniMax M2.1	MiniMax	0.3	1.20	1.0M	131K	compare (8)	31.4#3	N/A
MiniMax M2	MiniMax	0.255	1.02	205K	131K	compare (9)	28.3#4	N/A
MiMo V2 Flash	Xiaomi	0.1	0.3	262K	32K	compare (3)	24.7#6	49.8#1
DeepSeek V3.2	DeepSeek	0.229	0.343	164K	66K	compare (13)	24.7#5	N/A
Qwen3 Max	Alibaba	0.78	3.90	262K	66K	compare (4)	24.0#7	N/A
GPT OSS 120B	OpenAI	0.03	0.15	131K	131K	compare (23)	23.8#8	30.4#4
GLM-4.6	Zhipu AI	0.43	1.74	205K	131K	compare (10)	23.0#9	N/A
DeepSeek V3.1 Terminus	DeepSeek	0.27	0.95	164K	66K	compare (6)	21.4#10	N/A
DeepSeek V3.1	DeepSeek	0.27	1.00	164K	33K	compare (14)	21.0#11	N/A
GLM-4.5	Zhipu AI	0.4	1.60	131K	98K	compare (7)	19.5#12	N/A
Kimi K2	Moonshot AI (Kimi)	0.57	2.30	262K	100K	compare (4)	19.4#13	47.1#2
Qwen3 Coder 480B A35B Instruct	Alibaba	0.22	1.30	262K	66K	compare (8)	18.0#14	N/A
MiniMax M1 80k	MiniMax	0.1	0.1	1.0M	40K	compare (3)	17.7#15	N/A
GLM-4.5 Air	Zhipu AI	0.125	0.45	131K	98K	compare (7)	16.5#16	N/A
DeepSeek V3 324	DeepSeek	0.2	0.4	164K	16K	compare (13)	15.4#17	21.2#5
GPT OSS 20B	OpenAI	0.0145	0.07	131K	131K	compare (18)	14.9#18	20.7#6
Qwen3 VL 235B A22B Instruct	Alibaba	0.2	0.88	262K	129K	compare (7)	14.3#19	N/A
Qwen3 Next 80B A3B Instruct	Alibaba	0.09	0.9	262K	66K	compare (10)	13.7#20	N/A
Qwen3 Coder 30B A3B Instruct	Alibaba	0.07	0.27	262K	33K	compare (5)	13.6#21	N/A
GLM-4.6V	Zhipu AI	0.3	0.9	131K	33K	compare (4)	11.0#23	N/A
DeepSeek R1 Distill Qwen 32B	DeepSeek	0.15	0.15	131K	32K	compare (6)	11.0#22	N/A
Qwen3 235B A22B Instruct	Alibaba	0.09	0.58	262K	16K	compare (11)	10.9#24	N/A
Qwen3 VL 30B A3B Instruct	Alibaba	0.13	0.52	262K	33K	compare (5)	10.0#25	N/A
DeepSeek R1 Distill Llama 70B	DeepSeek	0.2	0.375	131K	8K	compare (11)	9.9#26	N/A
DeepSeek R1 Distill Qwen 14B	DeepSeek	0.07	0.07	131K	16K	compare (5)	9.8#27	N/A
Qwen2.5 72B Instruct	Alibaba	0.12	0.3	131K	16K	compare (7)	9.6#28	N/A
Qwen3 30B A3B	Alibaba	0.051	0.2	131K	20K	compare (8)	9.1#29	N/A
Llama 3.3 70B Instruct	Meta	0.1	0.2	131K	120K	compare (21)	8.6#30	11.9#7
Qwen3 VL 8B Instruct	Alibaba	0.08	0.2	256K	33K	compare (4)	8.4#31	N/A
Llama 3.1 8B Instruct	Meta	0.02	0.03	200K	128K	compare (21)	7.6#32	5.4#8
GLM-4.5V	Zhipu AI	0.6	1.20	131K	32K	compare (6)	7.0#33	N/A
Qwen3 Omni 30B A3B Instruct	Alibaba	0.25	0.97	66K	16K	compare (1)	5.1#34	N/A
Llama 3.2 3B Instruct	Meta	0.015	0.02	131K	80K	compare (10)	4.2#35	N/A
Llama 3 70B Instruct	Meta	0.12	0.3	131K	8K	compare (8)	3.5#36	N/A
Llama 3 8B Instruct	Meta	0.03	0.04	32K	8K	compare (9)	1.2#37	N/A
AutoGLM Phone 9B Multilingual	Zhipu AI	0.035	0.138	66K	N/A	compare (2)	N/A	N/A
BaiChuan M2 32B	Baichuan	0.07	0.07	131K	N/A	compare (1)	N/A	N/A
BGE Reranker M3 2	Baai	0.01	0.01	8K	8K	compare (1)	N/A	N/A
BGE-M3	Baai	0.01	0.01	60K	N/A	compare (3)	N/A	N/A
DeepSeek Prover V2 671B	DeepSeek	0.7	2.50	160K	N/A	compare (1)	N/A	N/A
DeepSeek R1 528	DeepSeek	0.2	0.25	164K	33K	compare (13)	N/A	N/A
DeepSeek R1 528B Qwen3 8B	DeepSeek	0.06	0.09	128K	32K	compare (1)	N/A	N/A
DeepSeek R1 Turbo	DeepSeek	0.7	2.50	64K	16K	compare (3)	N/A	N/A
DeepSeek V3 Turbo	DeepSeek	0.4	1.30	64K	16K	compare (2)	N/A	N/A
DeepSeek V3.2 Exp	DeepSeek	0.27	0.41	164K	66K	compare (4)	N/A	N/A
DeepSeek-OCR	DeepSeek	0.03	0.03	8K	8K	compare (4)	N/A	N/A
ERNIE 4.5 21B A3B	Baidu	0.07	0.28	120K	8K	compare (1)	N/A	N/A
ERNIE 4.5 21B A3B Thinking	Baidu	0.07	0.28	131K	66K	compare (1)	N/A	N/A
ERNIE 4.5 300B A47B Paddle	Baidu	0.28	1.10	123K	12K	compare (1)	N/A	N/A
ERNIE 4.5 VL 28B A3B	Baidu	0.14	0.56	30K	8K	compare (1)	N/A	N/A
ERNIE 4.5 VL 28B A3B Thinking	Baidu	0.39	0.39	131K	66K	compare (1)	N/A	N/A
ERNIE 4.5 VL 424B A47B	Baidu	0.42	1.25	131K	16K	compare (3)	N/A	N/A
Gemma 3 12B Instruct	Google	0.05	0.1	131K	16K	compare (6)	N/A	N/A
Gemma 3 27B Instruct	Google	0.06	0.16	131K	16K	compare (7)	N/A	N/A
Hermes 2 Pro Llama 3 8B	Nous Research	0.14	0.14	8K	8K	compare (1)	N/A	N/A
Kimi K2 Instruct	Moonshot AI (Kimi)	0.5	2.00	262K	33K	compare (9)	N/A	N/A
KwaiPilot KAT Pro Coder	KwaiPilot	0.3	1.20	256K	128K	compare (1)	N/A	N/A
L3 70B Euryale V2.1	Sao10K	1.48	1.48	8K	8K	compare (1)	N/A	N/A
L3 Lunaris 8B	Sao10K	0.04	0.05	8K	8K	compare (3)	N/A	N/A
L3 Stheno 3.2 8B	Sao10K	0.05	0.05	8K	N/A	compare (2)	N/A	N/A
L3.1 70B Euryale V2.2	Sao10K	0.65	0.75	131K	8K	compare (2)	N/A	N/A
Llama 4 17B Maverick Instruct	Meta	0.05	0.1	1.0M	16K	compare (9)	N/A	N/A
Llama 4 17B Scout Instruct	Meta	0.05	0.1	10.0M	16K	compare (12)	N/A	N/A
MT Plus	Alibaba	0.25	0.75	16K	8K	compare (2)	N/A	N/A
MythoMax L2 13B	Gryphe	0.06	0.06	4K	4K	compare (4)	N/A	N/A
Nemo	Mistral AI	0.02	0.03	131K	16K	compare (6)	N/A	N/A
PaddleOCR VL	PaddlePaddle (Baidu)	0.02	0.02	16K	16K	compare (1)	N/A	N/A
Qwen2.5 7B Instruct	Alibaba	0.04	0.07	131K	33K	compare (4)	N/A	N/A
Qwen2.5 VL 72B Instruct	Alibaba	0.13	0.4	131K	128K	compare (6)	N/A	N/A
Qwen3 235B A22B	Alibaba	0.09	0.1	262K	131K	compare (9)	N/A	N/A
Qwen3 235B A22B Thinking	Alibaba	0.149	0.88	262K	33K	compare (9)	N/A	N/A
Qwen3 32B	Alibaba	0.05	0.1	131K	41K	compare (15)	N/A	N/A
Qwen3 4B	Alibaba	0.03	0.03	128K	20K	compare (3)	N/A	N/A
Qwen3 8B	Alibaba	0.035	0.138	131K	20K	compare (6)	N/A	N/A
Qwen3 Embedding 0.6B	Alibaba	0.01	N/A	33K	N/A	compare (3)	N/A	N/A
Qwen3 Embedding 8B	Alibaba	0.02	N/A	41K	4K	compare (4)	N/A	N/A
Qwen3 Next 80B A3B Thinking	Alibaba	0.0975	0.78	262K	66K	compare (9)	N/A	N/A
Qwen3 Omni 30B A3B Thinking	Alibaba	0.25	0.97	66K	16K	compare (1)	N/A	N/A
Qwen3 Reranker 8B	Alibaba	0.05	0.05	41K	4K	compare (1)	N/A	N/A
Qwen3 VL 235B A22B Thinking	Alibaba	0.22	0.88	262K	33K	compare (5)	N/A	N/A
Qwen3 VL 30B A3B Thinking	Alibaba	0.13	0.6	262K	33K	compare (4)	N/A	N/A
Skywork R1 4 Lite	Skywork	0.2	0.6	262K	66K	compare (1)	N/A	N/A
WizardLM 2 8x22B	Microsoft	0.48	0.48	66K	8K	compare (4)	N/A	N/A

Novita

Intelligence vs Price

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

Novita models