Hugging Face AI models — pricing & benchmarks

Official siteDocsPricingAPI

We’re on a journey to advance and democratize artificial intelligence through open source and open science. Inference platform · Community · Hub · Inference Endpoints · Model Registry · Open Source

Intelligence vs Price

Best value among Hugging Face models on this chart: GLM-5.2 · MiniMax M3 · DeepSeek V4 Flash (and 4 more on the dashed frontier). Hover any dot for full pricing, or click a creator in the legend to isolate.

Hugging Face 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-5.2	Zhipu AI	0.93	3.00	1.0M	131K	compare (5)	51.1#1	68.8#1
MiniMax M3	MiniMax	0.3	1.20	1.0M	512K	compare (5)	44.4#2	58.6#4
DeepSeek V4 Pro	DeepSeek	0.435	0.87	1.0M	384K	compare (7)	44.3#3	59.4#3
Kimi K2.6	Moonshot AI (Kimi)	0.66	3.40	262K	262K	compare (8)	42.8#4	56.0#6
Kimi K2.7 Code	Moonshot AI (Kimi)	0.74	3.50	262K	33K	compare (5)	41.9#5	60.8#2
DeepSeek V4 Flash	DeepSeek	0.09	0.18	1.0M	384K	compare (10)	40.3#6	56.2#5
GLM-5.1	Zhipu AI	0.966	3.04	203K	131K	compare (6)	40.2#7	55.8#7
GLM-5	Zhipu AI	0.573	1.92	203K	131K	compare (9)	39.5#8	N/A
MiniMax M2.7	MiniMax	0.18	0.55	1.0M	197K	compare (6)	38.1#9	52.6#8
Kimi K2.5	Moonshot AI (Kimi)	0.375	2.02	262K	98K	compare (12)	38.1#10	N/A
Nemotron 3 Ultra 550B A55B	NVIDIA	0.5	2.20	1.0M	66K	compare (3)	37.8#11	49.3#9
Qwen3.5 27B	Alibaba	0.195	1.56	262K	66K	compare (3)	33.8#12	N/A
Qwen3.5 397B A17B	Alibaba	0.385	2.45	262K	66K	compare (5)	33.7#13	48.2#10
MiniMax M2.5	MiniMax	0.12	0.48	1.0M	197K	compare (8)	33.7#14	N/A
GLM-4.7	Zhipu AI	0.4	1.75	205K	131K	compare (13)	33.7#15	45.3#13
Qwen3.5 122B A10B	Alibaba	0.25	1.75	262K	66K	compare (4)	32.3#16	45.7#12
MiniMax M2.1	MiniMax	0.3	1.20	1.0M	131K	compare (8)	31.4#17	N/A
Qwen3.5 35B A3B	Alibaba	0.14	1.00	262K	82K	compare (3)	29.3#18	N/A
MiniMax M2	MiniMax	0.255	1.02	205K	131K	compare (9)	28.3#19	N/A
InclusionAI Ling 2.6 1T	Inclusionai	0.075	0.625	262K	33K	compare (2)	26.1#20	N/A
DeepSeek V3.2	DeepSeek	0.229	0.343	164K	66K	compare (13)	24.7#21	N/A
GPT OSS 120B	OpenAI	0.03	0.15	131K	131K	compare (23)	23.8#22	30.4#14
GLM-4.6	Zhipu AI	0.43	1.74	205K	131K	compare (10)	23.0#23	N/A
GLM-4.7 Flash	Zhipu AI	0.06	0.4	203K	131K	compare (4)	22.9#24	N/A
Qwen3.5 9B	Alibaba	0.1	0.15	262K	33K	compare (2)	21.4#25	28.7#15
DeepSeek V3.1 Terminus	DeepSeek	0.27	0.95	164K	66K	compare (6)	21.4#26	N/A
Qwen3 Coder Next	Alibaba	0.11	0.8	262K	8K	compare (5)	21.2#27	N/A
DeepSeek V3.1	DeepSeek	0.27	1.00	164K	33K	compare (14)	21.0#28	N/A
Kimi K2	Moonshot AI (Kimi)	0.57	2.30	262K	100K	compare (4)	19.4#29	47.1#11
Qwen3 Coder 480B A35B Instruct	Alibaba	0.22	1.30	262K	66K	compare (8)	18.0#30	N/A
MiniMax M1 80k	MiniMax	0.1	0.1	1.0M	40K	compare (3)	17.7#31	N/A
GLM-4.5 Air	Zhipu AI	0.125	0.45	131K	98K	compare (7)	16.5#32	N/A
DeepSeek V3 324	DeepSeek	0.2	0.4	164K	16K	compare (13)	15.4#33	21.2#16
GPT OSS 20B	OpenAI	0.0145	0.07	131K	131K	compare (18)	14.9#34	20.7#17
Qwen3 VL 235B A22B Instruct	Alibaba	0.2	0.88	262K	129K	compare (7)	14.3#35	N/A
Qwen3 Next 80B A3B Instruct	Alibaba	0.09	0.9	262K	66K	compare (10)	13.7#36	N/A
GLM-4.6V	Zhipu AI	0.3	0.9	131K	33K	compare (4)	11.0#37	N/A
Qwen3 235B A22B Instruct	Alibaba	0.09	0.58	262K	16K	compare (11)	10.9#38	N/A
Qwen3 VL 30B A3B Instruct	Alibaba	0.13	0.52	262K	33K	compare (5)	10.0#39	N/A
DeepSeek R1 Distill Llama 70B	DeepSeek	0.2	0.375	131K	8K	compare (11)	9.9#40	N/A
DeepSeek R1 Distill Qwen 14B	DeepSeek	0.07	0.07	131K	16K	compare (5)	9.8#41	N/A
Qwen2.5 72B Instruct	Alibaba	0.12	0.3	131K	16K	compare (7)	9.6#42	N/A
Llama 3.3 70B Instruct	Meta	0.1	0.2	131K	120K	compare (21)	8.6#43	11.9#18
Llama 3.1 8B Instruct	Meta	0.02	0.03	200K	128K	compare (21)	7.6#44	5.4#19
Qwen2.5 Coder 32B Instruct	Alibaba	0.05	0.1	131K	33K	compare (8)	7.1#45	N/A
GLM-4.5V	Zhipu AI	0.6	1.20	131K	32K	compare (6)	7.0#46	N/A
Qwen3 4B Instruct	Alibaba	0.01	0.03	262K	33K	compare (2)	6.8#47	N/A
DeepSeek R1 Distill Llama 8B	DeepSeek	0.025	0.025	131K	N/A	compare (3)	6.4#48	N/A
Qwen2.5 Coder 7B Instruct	Alibaba	0.01	0.03	33K	8K	compare (3)	4.5#49	N/A
Mixtral 8x22B Instruct	Mistral AI	0.6	0.6	66K	2K	compare (6)	4.4#50	N/A
AutoGLM Phone 9B Multilingual	Zhipu AI	0.035	0.138	66K	N/A	compare (2)	N/A	N/A
Cogito V2.1 671B	DeepCogito	1.25	1.25	128K	N/A	compare (2)	N/A	N/A
DeepSeek R1 528	DeepSeek	0.2	0.25	164K	33K	compare (13)	N/A	N/A
DeepSeek R1 Distill Qwen 7B	DeepSeek	0.072	0.144	131K	16K	compare (4)	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 VL 424B A47B	Baidu	0.42	1.25	131K	16K	compare (3)	N/A	N/A
Gemma 3N E4B IT	Google	0.06	0.12	33K	2K	compare (2)	N/A	N/A
Gemma 4 26B A4B IT	Google	0.06	0.3	262K	131K	compare (6)	N/A	N/A
Gemma 4 31B IT	Google	0.12	0.35	262K	131K	compare (6)	N/A	N/A
GLM-4 32B	Zhipu AI	0.1	0.1	128K	32K	compare (2)	N/A	N/A
Kimi K2 Instruct	Moonshot AI (Kimi)	0.5	2.00	262K	33K	compare (9)	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
Llama 3 8B Instruct Lite	Meta	0.14	0.14	N/A	N/A	compare (1)	N/A	N/A
Llama 3.3 70B Instruct Turbo	Meta	0.13	0.39	131K	N/A	compare (3)	N/A	N/A
Llama 3.3 70B Versatile	Meta	0.59	0.79	N/A	N/A	compare (1)	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
LlamaGuard 4 12B	Meta	0.18	0.18	164K	16K	compare (4)	N/A	N/A
Nemotron 3 Ultra	NVIDIA	0.6	2.40	N/A	N/A	compare (1)	N/A	N/A
Qwen2.5 Coder 3B Instruct	Alibaba	0.01	0.03	33K	N/A	compare (3)	N/A	N/A
Qwen2.5 Turbo 7B Instruct	Alibaba	0.3	0.3	N/A	N/A	compare (1)	N/A	N/A
Qwen2.5 VL 72B Instruct	Alibaba	0.13	0.4	131K	128K	compare (6)	N/A	N/A
Qwen3 14B	Alibaba	0.06	0.2	132K	41K	compare (7)	N/A	N/A
Qwen3 235B A22B	Alibaba	0.09	0.1	262K	131K	compare (9)	N/A	N/A
Qwen3 235B A22B Instruct Tput	Alibaba	0.2	0.6	262K	N/A	compare (2)	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 Thinking	Alibaba	0.01	0.03	N/A	N/A	compare (1)	N/A	N/A
Qwen3 8B	Alibaba	0.035	0.138	131K	20K	compare (6)	N/A	N/A
Qwen3 VL 235B A22B Thinking	Alibaba	0.22	0.88	262K	33K	compare (5)	N/A	N/A
WizardLM 2 8x22B	Microsoft	0.48	0.48	66K	8K	compare (4)	N/A	N/A

Hugging Face

Intelligence vs Price

Hugging Face modelsAPIGET/api/v1/providers/huggingface/models

Hugging Face models