Hugging Face Inference Providers


deepseek-ai/DeepSeek-V4-Pro DeepSeek-V4-Pro	novita cheapest	$1.69	$3.38	1,048,576	0.40	30	Yes	No
deepseek-ai/DeepSeek-V4-Pro DeepSeek-V4-Pro	together fastest	$2.10	$4.40	512,000	1.17	43	Yes	Yes
deepseek-ai/DeepSeek-V4-Pro DeepSeek-V4-Pro	deepinfra	$1.74	$3.48	65,536	0.55	37	Yes	Yes
deepseek-ai/DeepSeek-V4-Flash DeepSeek-V4-Flash	novita cheapest fastest	$0.14	$0.28	1,048,576	0.72	75	Yes	No
deepseek-ai/DeepSeek-V4-Flash DeepSeek-V4-Flash	deepinfra	$0.14	$0.28	1,048,576	0.94	30	Yes	Yes
Qwen/Qwen3.6-35B-A3B Qwen3.6-35B-A3B	deepinfra	$0.15	$0.95	262,144	0.25	80	Yes	Yes
google/gemma-4-31B-it gemma-4-31B-it	novita fastest	$0.14	$0.40	262,144	0.73	18	Yes	Yes
google/gemma-4-31B-it gemma-4-31B-it	together	$0.20	$0.50	262,144	0.50	13	Yes	Yes
google/gemma-4-31B-it gemma-4-31B-it	deepinfra cheapest	$0.13	$0.38	262,144	0.42	16	Yes	Yes
moonshotai/Kimi-K2.6 Kimi-K2.6	novita	-	-	-	-	-	-	-
moonshotai/Kimi-K2.6 Kimi-K2.6	together	$1.20	$4.50	262,144	0.39	35	Yes	Yes
moonshotai/Kimi-K2.6 Kimi-K2.6	fireworks-ai fastest	-	-	262,144	0.80	72	Yes	No
moonshotai/Kimi-K2.6 Kimi-K2.6	deepinfra cheapest	$0.75	$3.50	262,144	0.80	19	Yes	No
google/gemma-4-26B-A4B-it gemma-4-26B-A4B-it	novita	$0.13	$0.40	262,144	0.68	59	Yes	Yes
google/gemma-4-26B-A4B-it gemma-4-26B-A4B-it	deepinfra cheapest fastest	$0.07	$0.34	262,144	0.30	61	Yes	Yes
zai-org/GLM-5.1 GLM-5.1	together	$1.40	$4.40	202,752	0.93	24	No	Yes
zai-org/GLM-5.1 GLM-5.1	fireworks-ai	-	-	202,752	1.16	30	Yes	No
zai-org/GLM-5.1 GLM-5.1	zai-org	-	-	-	3.44	32	Yes	No
zai-org/GLM-5.1 GLM-5.1	deepinfra cheapest fastest	$1.05	$3.50	202,752	0.79	69	Yes	Yes
inclusionAI/Ling-2.6-1T Ling-2.6-1T	novita	$0.30	$2.50	262,144	1.09	74	Yes	Yes
Qwen/Qwen3.5-9B Qwen3.5-9B	together cheapest fastest	$0.10	$0.15	262,144	0.25	66	Yes	No
Qwen/Qwen3.5-9B Qwen3.5-9B	ovhcloud	$0.12	$0.18	262,144	0.49	41	Yes	Yes
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	novita cheapest	$0.02	$0.05	16,384	0.46	70	No	No
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	cerebras fastest	$0.10	$0.10	-	0.14	1,415	No	No
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	sambanova	-	-	-	-	-	-	-
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	nscale	$0.06	$0.06	131,072	2.42	19	No	Yes
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	scaleway	-	-	-	0.23	154	Yes	Yes
Qwen/Qwen3-Coder-Next Qwen3-Coder-Next	novita	$0.20	$1.50	262,144	1.59	112	Yes	No
openai/gpt-oss-120b gpt-oss-120b	groq	$0.15	$0.75	131,072	0.13	442	Yes	No
openai/gpt-oss-120b gpt-oss-120b	novita cheapest	$0.05	$0.25	131,072	0.58	21	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	cerebras fastest	$0.25	$0.69	-	0.13	1,009	Yes	No
openai/gpt-oss-120b gpt-oss-120b	sambanova	$0.22	$0.59	131,072	1.29	475	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	nscale	$0.10	$0.40	131,072	0.91	109	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	together	$0.15	$0.60	131,072	0.33	113	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	fireworks-ai	$0.15	$0.60	131,072	0.25	88	Yes	No
openai/gpt-oss-120b gpt-oss-120b	scaleway	-	-	-	0.30	182	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	ovhcloud	$0.09	$0.47	131,072	0.44	116	Yes	Yes
MiniMaxAI/MiniMax-M2.7 MiniMax-M2.7	novita cheapest	$0.30	$1.20	204,800	1.05	37	Yes	No
MiniMaxAI/MiniMax-M2.7 MiniMax-M2.7	together	$0.30	$1.20	196,608	0.59	26	Yes	Yes
MiniMaxAI/MiniMax-M2.7 MiniMax-M2.7	fireworks-ai fastest	-	-	196,608	1.51	107	Yes	No
openai/gpt-oss-20b gpt-oss-20b	groq fastest	$0.10	$0.50	131,072	0.09	830	Yes	No
openai/gpt-oss-20b gpt-oss-20b	novita cheapest	$0.04	$0.15	131,072	0.61	47	No	Yes
openai/gpt-oss-20b gpt-oss-20b	nscale	$0.05	$0.20	131,072	0.88	155	Yes	Yes
openai/gpt-oss-20b gpt-oss-20b	together	$0.05	$0.20	131,072	0.30	118	Yes	Yes
openai/gpt-oss-20b gpt-oss-20b	fireworks-ai	$0.05	$0.20	131,072	0.51	90	Yes	No
openai/gpt-oss-20b gpt-oss-20b	ovhcloud	$0.05	$0.18	131,072	0.48	69	Yes	Yes
Qwen/Qwen3-Coder-30B-A3B-Instruct Qwen3-Coder-30B-A3B-Instruct	scaleway fastest	-	-	-	0.33	92	Yes	No
Qwen/Qwen3-Coder-30B-A3B-Instruct Qwen3-Coder-30B-A3B-Instruct	ovhcloud cheapest	$0.07	$0.26	262,144	0.51	59	Yes	Yes
Qwen/Qwen3-8B Qwen3-8B	nscale cheapest	$0.07	$0.18	40,960	0.96	55	Yes	No
Qwen/Qwen3-8B Qwen3-8B	fireworks-ai fastest	-	-	40,960	0.25	75	Yes	No
Qwen/Qwen2.5-7B-Instruct Qwen2.5-7B-Instruct	together	$0.30	$0.30	32,768	0.25	90	Yes	Yes
Qwen/Qwen3-VL-8B-Instruct Qwen3-VL-8B-Instruct	novita	$0.08	$0.50	131,072	0.80	57	Yes	No
Qwen/Qwen3-VL-8B-Instruct Qwen3-VL-8B-Instruct	together	-	-	-	-	-	-	-
meta-llama/Meta-Llama-3-8B-Instruct Meta-Llama-3-8B-Instruct	novita	$0.04	$0.04	8,192	0.38	74	No	Yes
Qwen/Qwen3.5-397B-A17B Qwen3.5-397B-A17B	novita cheapest	$0.60	$3.60	262,144	1.22	46	Yes	No
Qwen/Qwen3.5-397B-A17B Qwen3.5-397B-A17B	together fastest	$0.60	$3.60	262,144	0.75	132	Yes	Yes
Qwen/Qwen3.5-397B-A17B Qwen3.5-397B-A17B	scaleway	-	-	-	0.39	101	Yes	Yes
Qwen/Qwen3.5-397B-A17B Qwen3.5-397B-A17B	deepinfra	$0.49	$3.60	262,144	0.28	85	Yes	Yes
deepseek-ai/DeepSeek-OCR DeepSeek-OCR	novita	$0.03	$0.03	8,192	1.09	114	No	No
deepseek-ai/DeepSeek-R1 DeepSeek-R1	novita	$0.70	$2.50	64,000	1.75	21	No	Yes
deepseek-ai/DeepSeek-R1 DeepSeek-R1	sambanova	-	-	-	-	-	-	-
deepseek-ai/DeepSeek-R1 DeepSeek-R1	hyperbolic cheapest fastest	$2.00	$2.00	163,840	0.77	98	No	No
deepseek-ai/DeepSeek-R1 DeepSeek-R1	together	$3.00	$7.00	163,840	0.50	88	No	Yes
deepseek-ai/DeepSeek-V3.2 DeepSeek-V3.2	novita cheapest	$0.27	$0.40	163,840	2.25	27	Yes	Yes
deepseek-ai/DeepSeek-V3.2 DeepSeek-V3.2	fireworks-ai fastest	-	-	163,840	2.41	55	Yes	No
stepfun-ai/Step-3.5-Flash Step-3.5-Flash	deepinfra	$0.10	$0.30	262,144	0.27	67	Yes	No
moonshotai/Kimi-K2.5 Kimi-K2.5	novita	$0.60	$3.00	262,144	0.79	36	Yes	Yes
moonshotai/Kimi-K2.5 Kimi-K2.5	together cheapest	$0.50	$2.80	262,144	0.39	19	Yes	Yes
moonshotai/Kimi-K2.5 Kimi-K2.5	fireworks-ai fastest	-	-	262,144	0.74	92	Yes	No
Qwen/Qwen3-Next-80B-A3B-Instruct Qwen3-Next-80B-A3B-Instruct	novita	$0.15	$1.50	131,072	0.91	77	Yes	No
Qwen/Qwen3-14B Qwen3-14B	nscale	$0.07	$0.20	40,960	0.95	50	Yes	No
meta-llama/Llama-3.2-1B-Instruct Llama-3.2-1B-Instruct	novita	-	-	131,000	0.45	197	No	No
zai-org/GLM-5 GLM-5	novita cheapest	$1.00	$3.20	202,800	1.65	44	Yes	No
zai-org/GLM-5 GLM-5	together fastest	$1.00	$3.20	202,752	0.59	95	Yes	Yes
zai-org/GLM-5 GLM-5	fireworks-ai	-	-	202,752	2.15	55	Yes	No
zai-org/GLM-5 GLM-5	zai-org	-	-	-	3.44	43	Yes	No
MiniMaxAI/MiniMax-M2.5 MiniMax-M2.5	novita cheapest	$0.30	$1.20	204,800	0.94	56	Yes	No
MiniMaxAI/MiniMax-M2.5 MiniMax-M2.5	fireworks-ai fastest	-	-	-	0.53	144	Yes	No
Qwen/Qwen3-Coder-480B-A35B-Instruct Qwen3-Coder-480B-A35B-Instruct	novita cheapest	$0.38	$1.55	262,144	1.38	56	Yes	Yes
Qwen/Qwen3-Coder-480B-A35B-Instruct Qwen3-Coder-480B-A35B-Instruct	hyperbolic fastest	$2.00	$2.00	262,144	0.60	76	No	No
Qwen/Qwen3-Coder-480B-A35B-Instruct Qwen3-Coder-480B-A35B-Instruct	together	$2.00	$2.00	262,144	0.18	41	Yes	Yes
Qwen/Qwen3.5-27B Qwen3.5-27B	novita	$0.30	$2.40	262,144	0.60	64	Yes	No
Qwen/Qwen3-4B-Instruct-2507 Qwen3-4B-Instruct-2507	nscale	$0.01	$0.03	262,144	0.92	67	Yes	No
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B DeepSeek-R1-Distill-Qwen-1.5B	nscale	$0.10	$0.10	131,072	0.88	139	No	No
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B DeepSeek-R1-Distill-Qwen-14B	nscale	$0.20	$0.20	131,072	0.91	37	No	Yes
zai-org/GLM-4.7-Flash GLM-4.7-Flash	novita cheapest fastest	$0.07	$0.40	200,000	0.93	74	No	No
zai-org/GLM-4.7-Flash GLM-4.7-Flash	zai-org	-	-	-	2.28	65	No	No
moonshotai/Kimi-K2-Instruct-0905 Kimi-K2-Instruct-0905	novita	$0.60	$2.50	262,144	1.34	16	No	Yes
zai-org/GLM-4.7 GLM-4.7	novita cheapest	$0.60	$2.20	204,800	0.65	67	Yes	No
zai-org/GLM-4.7 GLM-4.7	cerebras fastest	-	-	-	0.12	451	Yes	No
zai-org/GLM-4.7 GLM-4.7	fireworks-ai	-	-	202,752	0.89	122	Yes	No
zai-org/GLM-4.7 GLM-4.7	zai-org	-	-	-	2.12	58	Yes	No
XiaomiMiMo/MiMo-V2-Flash MiMo-V2-Flash	novita	$0.10	$0.30	262,144	1.15	115	Yes	No
moonshotai/Kimi-K2-Instruct Kimi-K2-Instruct	novita	$0.57	$2.30	131,072	1.39	27	Yes	No
Qwen/Qwen3.5-35B-A3B Qwen3.5-35B-A3B	novita	$0.25	$2.00	262,144	1.74	105	Yes	No
katanemo/Arch-Router-1.5B Arch-Router-1.5B	hf-inference	-	-	-	0.10	77	No	Yes
Qwen/Qwen3.5-122B-A10B Qwen3.5-122B-A10B	novita fastest	$0.40	$3.20	262,144	1.28	101	Yes	No
Qwen/Qwen3.5-122B-A10B Qwen3.5-122B-A10B	deepinfra cheapest	$0.29	$2.40	262,144	0.24	65	Yes	Yes
deepseek-ai/DeepSeek-V3 DeepSeek-V3	novita	$0.40	$1.30	64,000	1.09	33	Yes	No
deepseek-ai/DeepSeek-V3 DeepSeek-V3	together cheapest fastest	$1.25	$1.25	131,072	0.53	34	Yes	Yes
Qwen/Qwen2.5-Coder-7B-Instruct Qwen2.5-Coder-7B-Instruct	nscale	$0.01	$0.03	131,072	0.80	61	No	Yes
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B DeepSeek-R1-Distill-Qwen-32B	nscale	$0.30	$0.30	131,072	0.85	28	No	Yes
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B DeepSeek-R1-Distill-Qwen-7B	nscale	$0.15	$0.15	131,072	0.95	66	No	No
Qwen/Qwen2.5-Coder-32B-Instruct Qwen2.5-Coder-32B-Instruct	nscale cheapest	$0.06	$0.20	131,072	0.93	28	No	Yes
Qwen/Qwen2.5-Coder-32B-Instruct Qwen2.5-Coder-32B-Instruct	scaleway fastest	-	-	-	0.32	95	Yes	No
MiniMaxAI/MiniMax-M2.1 MiniMax-M2.1	novita	$0.30	$1.20	204,800	1.23	57	Yes	No
zai-org/GLM-4.6 GLM-4.6	novita cheapest fastest	$0.55	$2.20	204,800	2.79	31	Yes	No
zai-org/GLM-4.6 GLM-4.6	zai-org	-	-	-	2.85	11	Yes	No
meta-llama/Llama-Guard-4-12B Llama-Guard-4-12B	together	$0.20	$0.20	1,048,576	0.15	13	No	No
CohereLabs/tiny-aya-global tiny-aya-global	cohere	-	-	-	0.72	113	No	No
Qwen/Qwen3-VL-30B-A3B-Instruct Qwen3-VL-30B-A3B-Instruct	novita cheapest	$0.20	$0.70	131,072	0.61	116	Yes	Yes
Qwen/Qwen3-VL-30B-A3B-Instruct Qwen3-VL-30B-A3B-Instruct	fireworks-ai fastest	-	-	262,144	0.31	138	Yes	No
deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324	novita cheapest	$0.27	$1.12	163,840	1.51	32	Yes	No
deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324	sambanova	-	-	-	-	-	-	-
deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324	hyperbolic fastest	$1.25	$1.25	163,840	0.82	59	No	No
deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324	together	$1.25	$1.25	131,072	0.55	27	Yes	Yes
Qwen/Qwen2.5-VL-72B-Instruct Qwen2.5-VL-72B-Instruct	ovhcloud	$1.01	$1.01	32,768	0.45	34	No	Yes
Qwen/Qwen3-VL-235B-A22B-Thinking Qwen3-VL-235B-A22B-Thinking	novita	$0.98	$3.95	131,072	1.40	46	Yes	No
swiss-ai/Apertus-8B-Instruct-2509 Apertus-8B-Instruct-2509	publicai	$0.10	$0.20	-	0.66	120	No	Yes
Qwen/Qwen3-Coder-Next-FP8 Qwen3-Coder-Next-FP8	together	$0.50	$1.20	262,144	0.44	147	Yes	Yes
meta-llama/Llama-3.1-70B-Instruct Llama-3.1-70B-Instruct	scaleway	-	-	-	0.33	85	Yes	Yes
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	groq fastest	$0.59	$0.79	131,072	0.26	288	Yes	No
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	novita cheapest	$0.14	$0.40	131,072	0.50	47	Yes	No
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	sambanova	$0.60	$1.20	131,072	0.53	280	Yes	Yes
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	nscale	$0.40	$0.40	131,072	0.89	17	No	Yes
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	hyperbolic	$0.40	$0.40	131,072	1.71	34	No	No
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	together	$0.88	$0.88	131,072	0.83	93	Yes	Yes
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	fireworks-ai	$0.90	$0.90	131,072	0.32	128	No	No
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	scaleway	-	-	-	0.25	85	Yes	Yes
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	ovhcloud	$0.74	$0.74	131,072	0.35	35	Yes	No
meta-llama/Llama-4-Maverick-17B-128E-Instruct Llama-4-Maverick-17B-128E-Instruct	sambanova	$0.63	$1.80	131,072	2.32	256	Yes	Yes
deepseek-ai/DeepSeek-R1-Distill-Llama-70B DeepSeek-R1-Distill-Llama-70B	novita	$0.80	$0.80	8,192	0.40	41	No	No
deepseek-ai/DeepSeek-R1-Distill-Llama-70B DeepSeek-R1-Distill-Llama-70B	nscale cheapest	$0.75	$0.75	131,072	1.00	16	No	Yes
deepseek-ai/DeepSeek-R1-Distill-Llama-70B DeepSeek-R1-Distill-Llama-70B	scaleway fastest	-	-	-	0.33	84	Yes	Yes
zai-org/GLM-5.1-FP8 GLM-5.1-FP8	fireworks-ai	-	-	202,752	0.95	31	Yes	No
zai-org/GLM-5.1-FP8 GLM-5.1-FP8	zai-org fastest	-	-	-	3.51	33	Yes	No
zai-org/GLM-4.5 GLM-4.5	novita cheapest fastest	$0.60	$2.20	131,072	0.61	57	Yes	No
zai-org/GLM-4.5 GLM-4.5	zai-org	-	-	-	2.42	53	Yes	No
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	novita cheapest	$0.09	$0.58	131,072	1.14	47	Yes	Yes
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	cerebras fastest	$0.60	$1.20	-	0.14	605	Yes	No
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	nscale	$0.20	$0.60	32,768	1.11	19	Yes	Yes
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	together	$0.20	$0.60	262,144	0.29	45	Yes	Yes
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	scaleway	-	-	-	0.72	42	Yes	Yes
utter-project/EuroLLM-22B-Instruct-2512 EuroLLM-22B-Instruct-2512	publicai	$0.10	$0.20	-	2.31	3	No	No
aisingapore/Gemma-SEA-LION-v4-27B-IT Gemma-SEA-LION-v4-27B-IT	publicai	$0.20	$0.40	-	1.11	48	No	Yes
Qwen/Qwen3-235B-A22B Qwen3-235B-A22B	novita	$0.20	$0.80	40,960	0.73	16	No	No
Qwen/Qwen3-235B-A22B Qwen3-235B-A22B	nscale cheapest fastest	$0.20	$0.60	32,000	1.04	31	Yes	Yes
deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528	novita cheapest	$0.70	$2.50	163,840	2.37	24	Yes	No
deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528	sambanova	-	-	-	-	-	-	-
deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528	hyperbolic	$3.00	$3.00	163,840	0.78	57	No	No
deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528	together fastest	$3.00	$7.00	163,840	0.49	99	No	Yes
zai-org/GLM-4.6V-FP8 GLM-4.6V-FP8	zai-org	-	-	-	3.26	38	Yes	No
CohereLabs/c4ai-command-r7b-12-2024 c4ai-command-r7b-12-2024	cohere	-	-	-	0.27	73	Yes	No
meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct	groq fastest	$0.11	$0.34	131,072	0.29	382	Yes	No
meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct	novita	$0.18	$0.59	131,072	0.67	43	No	No
meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct	nscale cheapest	$0.09	$0.29	890,000	0.83	33	Yes	Yes
Sao10K/L3-8B-Stheno-v3.2 L3-8B-Stheno-v3.2	novita	$0.05	$0.05	8,192	0.63	82	No	No
alpindale/WizardLM-2-8x22B WizardLM-2-8x22B	novita	$0.62	$0.62	65,535	1.00	12	No	No
Qwen/Qwen3-30B-A3B Qwen3-30B-A3B	novita	$0.09	$0.45	40,960	0.70	31	Yes	No
deepseek-ai/DeepSeek-R1-Distill-Llama-8B DeepSeek-R1-Distill-Llama-8B	nscale	$0.05	$0.05	131,072	0.97	27	No	Yes
moonshotai/Kimi-K2-Thinking Kimi-K2-Thinking	novita	$0.60	$2.50	262,144	1.24	57	Yes	No
MiniMaxAI/MiniMax-M2 MiniMax-M2	novita	$0.30	$1.20	204,800	0.86	64	Yes	No
mistralai/Mixtral-8x22B-Instruct-v0.1 Mixtral-8x22B-Instruct-v0.1	nscale	$1.20	$1.20	65,536	0.92	20	No	Yes
deepseek-ai/DeepSeek-V3.2-Exp DeepSeek-V3.2-Exp	novita	$0.27	$0.41	163,840	1.22	28	Yes	Yes
Qwen/Qwen3-VL-235B-A22B-Instruct Qwen3-VL-235B-A22B-Instruct	novita	$0.30	$1.50	131,072	0.54	36	Yes	Yes
Qwen/Qwen3-4B-Thinking-2507 Qwen3-4B-Thinking-2507	nscale	$0.01	$0.03	262,144	0.88	89	Yes	No
Qwen/Qwen2.5-72B-Instruct Qwen2.5-72B-Instruct	novita	$0.38	$0.40	32,000	0.58	37	Yes	No
google/gemma-3n-E4B-it gemma-3n-E4B-it	together	$0.06	$0.12	32,768	0.23	56	No	Yes
Qwen/Qwen3-32B Qwen3-32B	groq fastest	$0.29	$0.59	131,072	0.23	255	Yes	No
Qwen/Qwen3-32B Qwen3-32B	novita	$0.10	$0.45	40,960	0.60	45	No	No
Qwen/Qwen3-32B Qwen3-32B	nscale cheapest	$0.08	$0.25	40,960	1.05	27	Yes	No
Qwen/Qwen3-32B Qwen3-32B	ovhcloud	$0.09	$0.25	32,768	0.49	32	Yes	Yes
EssentialAI/rnj-1-instruct rnj-1-instruct	together	$0.15	$0.15	32,768	0.20	122	Yes	Yes
Qwen/Qwen2.5-Coder-3B-Instruct Qwen2.5-Coder-3B-Instruct	nscale	$0.01	$0.03	32,768	0.86	84	No	Yes
Qwen/Qwen3-VL-30B-A3B-Thinking Qwen3-VL-30B-A3B-Thinking	novita cheapest	$0.20	$1.00	131,072	0.98	110	Yes	No
Qwen/Qwen3-VL-30B-A3B-Thinking Qwen3-VL-30B-A3B-Thinking	fireworks-ai fastest	-	-	262,144	0.32	125	Yes	No
deepseek-ai/DeepSeek-V3.1 DeepSeek-V3.1	novita cheapest	$0.27	$1.00	131,072	1.64	28	Yes	Yes
deepseek-ai/DeepSeek-V3.1 DeepSeek-V3.1	together	$0.60	$1.70	131,072	0.50	33	Yes	Yes
deepseek-ai/DeepSeek-V3.1 DeepSeek-V3.1	fireworks-ai fastest	-	-	163,840	0.43	47	No	No
CohereLabs/tiny-aya-fire tiny-aya-fire	cohere	-	-	-	0.28	120	No	No
CohereLabs/tiny-aya-earth tiny-aya-earth	cohere	-	-	-	0.30	120	No	No
CohereLabs/tiny-aya-water tiny-aya-water	cohere	-	-	-	0.22	121	No	No
deepcogito/cogito-671b-v2.1-FP8 cogito-671b-v2.1-FP8	together	$1.25	$1.25	163,840	0.44	89	No	No
CohereLabs/command-a-translate-08-2025 command-a-translate-08-2025	cohere	-	-	-	0.39	68	Yes	No
CohereLabs/command-a-reasoning-08-2025 command-a-reasoning-08-2025	cohere	-	-	-	0.30	52	Yes	No
CohereLabs/command-a-vision-07-2025 command-a-vision-07-2025	cohere	-	-	-	0.15	47	No	No
zai-org/GLM-4.5-Air GLM-4.5-Air	novita cheapest	$0.13	$0.85	131,072	0.74	49	Yes	No
zai-org/GLM-4.5-Air GLM-4.5-Air	zai-org fastest	-	-	-	1.75	78	Yes	No
zai-org/GLM-4.5V GLM-4.5V	novita cheapest	$0.60	$1.80	65,536	0.92	26	Yes	No
zai-org/GLM-4.5V GLM-4.5V	zai-org fastest	-	-	-	2.51	43	Yes	No
CohereLabs/c4ai-command-r7b-arabic-02-2025 c4ai-command-r7b-arabic-02-2025	cohere	-	-	-	0.28	82	Yes	No
zai-org/GLM-4.6-FP8 GLM-4.6-FP8	zai-org	-	-	-	3.46	15	No	No
zai-org/GLM-4.5V-FP8 GLM-4.5V-FP8	zai-org	-	-	-	2.33	40	Yes	No
zai-org/GLM-4.6V GLM-4.6V	zai-org	-	-	-	2.94	38	Yes	No
zai-org/GLM-4.6V-Flash GLM-4.6V-Flash	novita cheapest	$0.30	$0.90	131,072	1.01	50	Yes	No
zai-org/GLM-4.6V-Flash GLM-4.6V-Flash	zai-org fastest	-	-	-	3.03	58	Yes	No
CohereLabs/aya-vision-32b aya-vision-32b	cohere	-	-	-	0.23	37	No	No
CohereLabs/aya-expanse-32b aya-expanse-32b	cohere	-	-	-	0.35	38	No	No
zai-org/GLM-4.7-FP8 GLM-4.7-FP8	zai-org	-	-	-	2.94	56	Yes	No
CohereLabs/c4ai-command-r-08-2024 c4ai-command-r-08-2024	cohere	-	-	-	1.02	32	Yes	No
CohereLabs/c4ai-command-a-03-2025 c4ai-command-a-03-2025	cohere	-	-	-	0.64	19	Yes	No
google/gemma-3-27b-it gemma-3-27b-it	scaleway	-	-	-	0.45	48	Yes	No
swiss-ai/Apertus-70B-Instruct-2509 Apertus-70B-Instruct-2509	publicai	$0.82	$2.92	-	0.60	60	No	Yes
deepseek-ai/DeepSeek-V3.1-Terminus DeepSeek-V3.1-Terminus	novita	$0.27	$1.00	131,072	1.55	26	Yes	Yes
allenai/Olmo-3-7B-Instruct Olmo-3-7B-Instruct	publicai	$0.10	$0.20	-	-	-	Yes	No
aisingapore/Qwen-SEA-LION-v4-32B-IT Qwen-SEA-LION-v4-32B-IT	publicai	$0.25	$0.50	-	1.47	44	Yes	Yes
dicta-il/DictaLM-3.0-24B-Thinking DictaLM-3.0-24B-Thinking	publicai	$0.20	$0.40	-	1.05	63	Yes	Yes
Qwen/Qwen3-Next-80B-A3B-Thinking Qwen3-Next-80B-A3B-Thinking	novita	$0.15	$1.50	131,072	0.85	82	Yes	No
Qwen/Qwen3-235B-A22B-Thinking-2507 Qwen3-235B-A22B-Thinking-2507	novita	$0.30	$3.00	131,072	0.95	39	Yes	No
baidu/ERNIE-4.5-VL-424B-A47B-Base-PT ERNIE-4.5-VL-424B-A47B-Base-PT	novita	$0.42	$1.25	123,000	1.10	45	No	No
baidu/ERNIE-4.5-300B-A47B-Base-PT ERNIE-4.5-300B-A47B-Base-PT	novita	$0.28	$1.10	123,000	1.41	21	No	No
MiniMaxAI/MiniMax-M1-80k MiniMax-M1-80k	novita	$0.55	$2.20	1,000,000	1.16	67	Yes	No
deepseek-ai/DeepSeek-Prover-V2-671B DeepSeek-Prover-V2-671B	novita	$0.70	$2.50	160,000	2.90	10	No	No
zai-org/GLM-4-32B-0414 GLM-4-32B-0414	novita	$0.55	$1.66	32,000	0.96	43	No	No
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 Llama-4-Maverick-17B-128E-Instruct-FP8	novita	$0.27	$0.85	1,048,576	0.44	47	No	Yes
Sao10K/L3-8B-Lunaris-v1 L3-8B-Lunaris-v1	novita	$0.05	$0.05	8,192	0.72	41	No	No
Sao10K/L3-70B-Euryale-v2.1 L3-70B-Euryale-v2.1	novita	$1.48	$1.48	8,192	0.62	31	No	No
NousResearch/Hermes-2-Pro-Llama-3-8B Hermes-2-Pro-Llama-3-8B	novita	$0.14	$0.14	8,192	0.36	114	No	No
meta-llama/Meta-Llama-3-70B-Instruct Meta-Llama-3-70B-Instruct	novita	$0.51	$0.74	8,192	0.61	24	No	Yes
zai-org/AutoGLM-Phone-9B-Multilingual AutoGLM-Phone-9B-Multilingual	novita	$0.04	$0.14	65,536	0.74	43	No	No
Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 Qwen3-Coder-480B-A35B-Instruct-FP8	together	$2.00	$2.00	262,144	0.19	40	Yes	Yes
openai/gpt-oss-safeguard-20b gpt-oss-safeguard-20b	groq	-	-	131,072	0.14	763	Yes	No

deepseek-ai/DeepSeek-V4-Pro DeepSeek-V4-Pro

novita

cheapest

$1.69

$3.38

1,048,576

0.40

30

Yes

No

deepseek-ai/DeepSeek-V4-Pro DeepSeek-V4-Pro

together

fastest

$2.10

$4.40

512,000

1.17

43

Yes

deepseek-ai/DeepSeek-V4-Pro DeepSeek-V4-Pro

deepinfra

$1.74

$3.48

65,536

0.55

37

Yes

deepseek-ai/DeepSeek-V4-Flash DeepSeek-V4-Flash

novita

cheapest fastest

$0.14

$0.28

1,048,576

0.72

75

Yes

No

deepseek-ai/DeepSeek-V4-Flash DeepSeek-V4-Flash

deepinfra

$0.14

$0.28

1,048,576

0.94

30

Yes

Qwen/Qwen3.6-35B-A3B Qwen3.6-35B-A3B

deepinfra

$0.15

$0.95

262,144

0.25

80

Yes

google/gemma-4-31B-it gemma-4-31B-it

novita

fastest

$0.14

$0.40

262,144

0.73

18

Yes

google/gemma-4-31B-it gemma-4-31B-it

together

$0.20

$0.50

262,144

0.50

13

Yes

google/gemma-4-31B-it gemma-4-31B-it

deepinfra

cheapest

$0.13

$0.38

262,144

0.42

16

Yes

moonshotai/Kimi-K2.6 Kimi-K2.6

novita

-

moonshotai/Kimi-K2.6 Kimi-K2.6

together

$1.20

$4.50

262,144

0.39

35

Yes

moonshotai/Kimi-K2.6 Kimi-K2.6

fireworks-ai

fastest

-

262,144

0.80

72

Yes

No

moonshotai/Kimi-K2.6 Kimi-K2.6

deepinfra

cheapest

$0.75

$3.50

262,144

0.80

19

Yes

No

google/gemma-4-26B-A4B-it gemma-4-26B-A4B-it

novita

$0.13

$0.40

262,144

0.68

59

Yes

google/gemma-4-26B-A4B-it gemma-4-26B-A4B-it

deepinfra

cheapest fastest

$0.07

$0.34

262,144

0.30

61

Yes

zai-org/GLM-5.1 GLM-5.1

together

$1.40

$4.40

202,752

0.93

24

No

Yes

zai-org/GLM-5.1 GLM-5.1

fireworks-ai

-

202,752

1.16

30

Yes

No

zai-org/GLM-5.1 GLM-5.1

zai-org

-

3.44

32

Yes

No

zai-org/GLM-5.1 GLM-5.1

deepinfra

cheapest fastest

$1.05

$3.50

202,752

0.79

69

Yes

inclusionAI/Ling-2.6-1T Ling-2.6-1T

novita

$0.30

$2.50

262,144

1.09

74

Yes

Qwen/Qwen3.5-9B Qwen3.5-9B

together

cheapest fastest

$0.10

$0.15

262,144

0.25

66

Yes

No

Qwen/Qwen3.5-9B Qwen3.5-9B

ovhcloud

$0.12

$0.18

262,144

0.49

41

Yes

meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct

novita

cheapest

$0.02

$0.05

16,384

0.46

70

No

meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct

cerebras

fastest

$0.10

-

0.14

1,415

No

meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct

sambanova

-

meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct

nscale

$0.06

131,072

2.42

19

No

Yes

meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct

scaleway

-

0.23

154

Yes

Qwen/Qwen3-Coder-Next Qwen3-Coder-Next

novita

$0.20

$1.50

262,144

1.59

112

Yes

No

openai/gpt-oss-120b gpt-oss-120b

groq

$0.15

$0.75

131,072

0.13

442

Yes

No

openai/gpt-oss-120b gpt-oss-120b

novita

cheapest

$0.05

$0.25

131,072

0.58

21

Yes

openai/gpt-oss-120b gpt-oss-120b

cerebras

fastest

$0.25

$0.69

-

0.13

1,009

Yes

No

openai/gpt-oss-120b gpt-oss-120b

sambanova

$0.22

$0.59

131,072

1.29

475

Yes

openai/gpt-oss-120b gpt-oss-120b

nscale

$0.10

$0.40

131,072

0.91

109

Yes

openai/gpt-oss-120b gpt-oss-120b

together

$0.15

$0.60

131,072

0.33

113

Yes

openai/gpt-oss-120b gpt-oss-120b

fireworks-ai

$0.15

$0.60

131,072

0.25

88

Yes

No

openai/gpt-oss-120b gpt-oss-120b

scaleway

-

0.30

182

Yes

openai/gpt-oss-120b gpt-oss-120b

ovhcloud

$0.09

$0.47

131,072

0.44

116

Yes

MiniMaxAI/MiniMax-M2.7 MiniMax-M2.7

novita

cheapest

$0.30

$1.20

204,800

1.05

37

Yes

No

MiniMaxAI/MiniMax-M2.7 MiniMax-M2.7

together

$0.30

$1.20

196,608

0.59

26

Yes

MiniMaxAI/MiniMax-M2.7 MiniMax-M2.7

fireworks-ai

fastest

-

196,608

1.51

107

Yes

No

openai/gpt-oss-20b gpt-oss-20b

groq

fastest

$0.10

$0.50

131,072

0.09

830

Yes

No

openai/gpt-oss-20b gpt-oss-20b

novita

cheapest

$0.04

$0.15

131,072

0.61

47

No

Yes

openai/gpt-oss-20b gpt-oss-20b

nscale

$0.05

$0.20

131,072

0.88

155

Yes

openai/gpt-oss-20b gpt-oss-20b

together

$0.05

$0.20

131,072

0.30

118

Yes

openai/gpt-oss-20b gpt-oss-20b

fireworks-ai

$0.05

$0.20

131,072

0.51

90

Yes

No

openai/gpt-oss-20b gpt-oss-20b

ovhcloud

$0.05

$0.18

131,072

0.48

69

Yes

Qwen/Qwen3-Coder-30B-A3B-Instruct Qwen3-Coder-30B-A3B-Instruct

scaleway

fastest

-

0.33

92

Yes

No

Qwen/Qwen3-Coder-30B-A3B-Instruct Qwen3-Coder-30B-A3B-Instruct

ovhcloud

cheapest

$0.07

$0.26

262,144

0.51

59

Yes

Qwen/Qwen3-8B Qwen3-8B

nscale

cheapest

$0.07

$0.18

40,960

0.96

55

Yes

No

Qwen/Qwen3-8B Qwen3-8B

fireworks-ai

fastest

-

40,960

0.25

75

Yes

No

Qwen/Qwen2.5-7B-Instruct Qwen2.5-7B-Instruct

together

$0.30

32,768

0.25

90

Yes

Qwen/Qwen3-VL-8B-Instruct Qwen3-VL-8B-Instruct

novita

$0.08

$0.50

131,072

0.80

57

Yes

No

Qwen/Qwen3-VL-8B-Instruct Qwen3-VL-8B-Instruct

together

-

meta-llama/Meta-Llama-3-8B-Instruct Meta-Llama-3-8B-Instruct

novita

$0.04

8,192

0.38

74

No

Yes

Qwen/Qwen3.5-397B-A17B Qwen3.5-397B-A17B

novita

cheapest

$0.60

$3.60

262,144

1.22

46

Yes

No

Qwen/Qwen3.5-397B-A17B Qwen3.5-397B-A17B

together

fastest

$0.60

$3.60

262,144

0.75

132

Yes

Qwen/Qwen3.5-397B-A17B Qwen3.5-397B-A17B

scaleway

-

0.39

101

Yes

Qwen/Qwen3.5-397B-A17B Qwen3.5-397B-A17B

deepinfra

$0.49

$3.60

262,144

0.28

85

Yes

deepseek-ai/DeepSeek-OCR DeepSeek-OCR

novita

$0.03

8,192

1.09

114

No

deepseek-ai/DeepSeek-R1 DeepSeek-R1

novita

$0.70

$2.50

64,000

1.75

21

No

Yes

deepseek-ai/DeepSeek-R1 DeepSeek-R1

sambanova

-

deepseek-ai/DeepSeek-R1 DeepSeek-R1

hyperbolic

cheapest fastest

$2.00

163,840

0.77

98

No

deepseek-ai/DeepSeek-R1 DeepSeek-R1

together

$3.00

$7.00

163,840

0.50

88

No

Yes

deepseek-ai/DeepSeek-V3.2 DeepSeek-V3.2

novita

cheapest

$0.27

$0.40

163,840

2.25

27

Yes

deepseek-ai/DeepSeek-V3.2 DeepSeek-V3.2

fireworks-ai

fastest

-

163,840

2.41

55

Yes

No

stepfun-ai/Step-3.5-Flash Step-3.5-Flash

deepinfra

$0.10

$0.30

262,144

0.27

67

Yes

No

moonshotai/Kimi-K2.5 Kimi-K2.5

novita

$0.60

$3.00

262,144

0.79

36

Yes

moonshotai/Kimi-K2.5 Kimi-K2.5

together

cheapest

$0.50

$2.80

262,144

0.39

19

Yes

moonshotai/Kimi-K2.5 Kimi-K2.5

fireworks-ai

fastest

-

262,144

0.74

92

Yes

No

Qwen/Qwen3-Next-80B-A3B-Instruct Qwen3-Next-80B-A3B-Instruct

novita

$0.15

$1.50

131,072

0.91

77

Yes

No

Qwen/Qwen3-14B Qwen3-14B

nscale

$0.07

$0.20

40,960

0.95

50

Yes

No

meta-llama/Llama-3.2-1B-Instruct Llama-3.2-1B-Instruct

novita

-

131,000

0.45

197

No

zai-org/GLM-5 GLM-5

novita

cheapest

$1.00

$3.20

202,800

1.65

44

Yes

No

zai-org/GLM-5 GLM-5

together

fastest

$1.00

$3.20

202,752

0.59

95

Yes

zai-org/GLM-5 GLM-5

fireworks-ai

-

202,752

2.15

55

Yes

No

zai-org/GLM-5 GLM-5

zai-org

-

3.44

43

Yes

No

MiniMaxAI/MiniMax-M2.5 MiniMax-M2.5

novita

cheapest

$0.30

$1.20

204,800

0.94

56

Yes

No

MiniMaxAI/MiniMax-M2.5 MiniMax-M2.5

fireworks-ai

fastest

-

0.53

144

Yes

No

Qwen/Qwen3-Coder-480B-A35B-Instruct Qwen3-Coder-480B-A35B-Instruct

novita

cheapest

$0.38

$1.55

262,144

1.38

56

Yes

Qwen/Qwen3-Coder-480B-A35B-Instruct Qwen3-Coder-480B-A35B-Instruct

hyperbolic

fastest

$2.00

262,144

0.60

76

No

Qwen/Qwen3-Coder-480B-A35B-Instruct Qwen3-Coder-480B-A35B-Instruct

together

$2.00

262,144

0.18

41

Yes

Qwen/Qwen3.5-27B Qwen3.5-27B

novita

$0.30

$2.40

262,144

0.60

64

Yes

No

Qwen/Qwen3-4B-Instruct-2507 Qwen3-4B-Instruct-2507

nscale

$0.01

$0.03

262,144

0.92

67

Yes

No

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B DeepSeek-R1-Distill-Qwen-1.5B

nscale

$0.10

131,072

0.88

139

No

deepseek-ai/DeepSeek-R1-Distill-Qwen-14B DeepSeek-R1-Distill-Qwen-14B

nscale

$0.20

131,072

0.91

37

No

Yes

zai-org/GLM-4.7-Flash GLM-4.7-Flash

novita

cheapest fastest

$0.07

$0.40

200,000

0.93

74

No

zai-org/GLM-4.7-Flash GLM-4.7-Flash

zai-org

-

2.28

65

No

moonshotai/Kimi-K2-Instruct-0905 Kimi-K2-Instruct-0905

novita

$0.60

$2.50

262,144

1.34

16

No

Yes

zai-org/GLM-4.7 GLM-4.7

novita

cheapest

$0.60

$2.20

204,800

0.65

67

Yes

No

zai-org/GLM-4.7 GLM-4.7

cerebras

fastest

-

0.12

451

Yes

No

zai-org/GLM-4.7 GLM-4.7

fireworks-ai

-

202,752

0.89

122

Yes

No

zai-org/GLM-4.7 GLM-4.7

zai-org

-

2.12

58

Yes

No

XiaomiMiMo/MiMo-V2-Flash MiMo-V2-Flash

novita

$0.10

$0.30

262,144

1.15

115

Yes

No

moonshotai/Kimi-K2-Instruct Kimi-K2-Instruct

novita

$0.57

$2.30

131,072

1.39

27

Yes

No

Qwen/Qwen3.5-35B-A3B Qwen3.5-35B-A3B

novita

$0.25

$2.00

262,144

1.74

105

Yes

No

katanemo/Arch-Router-1.5B Arch-Router-1.5B

hf-inference

-

0.10

77

No

Yes

Qwen/Qwen3.5-122B-A10B Qwen3.5-122B-A10B

novita

fastest

$0.40

$3.20

262,144

1.28

101

Yes

No

Qwen/Qwen3.5-122B-A10B Qwen3.5-122B-A10B

deepinfra

cheapest

$0.29

$2.40

262,144

0.24

65

Yes

deepseek-ai/DeepSeek-V3 DeepSeek-V3

novita

$0.40

$1.30

64,000

1.09

33

Yes

No

deepseek-ai/DeepSeek-V3 DeepSeek-V3

together

cheapest fastest

$1.25

131,072

0.53

34

Yes

Qwen/Qwen2.5-Coder-7B-Instruct Qwen2.5-Coder-7B-Instruct

nscale

$0.01

$0.03

131,072

0.80

61

No

Yes

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B DeepSeek-R1-Distill-Qwen-32B

nscale

$0.30

131,072

0.85

28

No

Yes

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B DeepSeek-R1-Distill-Qwen-7B

nscale

$0.15

131,072

0.95

66

No

Qwen/Qwen2.5-Coder-32B-Instruct Qwen2.5-Coder-32B-Instruct

nscale

cheapest

$0.06

$0.20

131,072

0.93

28

No

Yes

Qwen/Qwen2.5-Coder-32B-Instruct Qwen2.5-Coder-32B-Instruct

scaleway

fastest

-

0.32

95

Yes

No

MiniMaxAI/MiniMax-M2.1 MiniMax-M2.1

novita

$0.30

$1.20

204,800

1.23

57

Yes

No

zai-org/GLM-4.6 GLM-4.6

novita

cheapest fastest

$0.55

$2.20

204,800

2.79

31

Yes

No

zai-org/GLM-4.6 GLM-4.6

zai-org

-

2.85

11

Yes

No

meta-llama/Llama-Guard-4-12B Llama-Guard-4-12B

together

$0.20

1,048,576

0.15

13

No

CohereLabs/tiny-aya-global tiny-aya-global

cohere

-

0.72

113

No

Qwen/Qwen3-VL-30B-A3B-Instruct Qwen3-VL-30B-A3B-Instruct

novita

cheapest

$0.20

$0.70

131,072

0.61

116

Yes

Qwen/Qwen3-VL-30B-A3B-Instruct Qwen3-VL-30B-A3B-Instruct

fireworks-ai

fastest

-

262,144

0.31

138

Yes

No

deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324

novita

cheapest

$0.27

$1.12

163,840

1.51

32

Yes

No

deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324

sambanova

-

deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324

hyperbolic

fastest

$1.25

163,840

0.82

59

No

deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324

together

$1.25

131,072

0.55

27

Yes

Qwen/Qwen2.5-VL-72B-Instruct Qwen2.5-VL-72B-Instruct

ovhcloud

$1.01

32,768

0.45

34

No

Yes

Qwen/Qwen3-VL-235B-A22B-Thinking Qwen3-VL-235B-A22B-Thinking

novita

$0.98

$3.95

131,072

1.40

46

Yes

No

swiss-ai/Apertus-8B-Instruct-2509 Apertus-8B-Instruct-2509

publicai

$0.10

$0.20

-

0.66

120

No

Yes

Qwen/Qwen3-Coder-Next-FP8 Qwen3-Coder-Next-FP8

together

$0.50

$1.20

262,144

0.44

147

Yes

meta-llama/Llama-3.1-70B-Instruct Llama-3.1-70B-Instruct

scaleway

-

0.33

85

Yes

meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct

groq

fastest

$0.59

$0.79

131,072

0.26

288

Yes

No

meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct

novita

cheapest

$0.14

$0.40

131,072

0.50

47

Yes

No

meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct

sambanova

$0.60

$1.20

131,072

0.53

280

Yes

meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct

nscale

$0.40

131,072

0.89

17

No

Yes

meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct

hyperbolic

$0.40

131,072

1.71

34

No

meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct

together

$0.88

131,072

0.83

93

Yes

meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct

fireworks-ai

$0.90

131,072

0.32

128

No

meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct

scaleway

-

0.25

85

Yes

meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct

ovhcloud

$0.74

131,072

0.35

35

Yes

No

meta-llama/Llama-4-Maverick-17B-128E-Instruct Llama-4-Maverick-17B-128E-Instruct

sambanova

$0.63

$1.80

131,072

2.32

256

Yes

deepseek-ai/DeepSeek-R1-Distill-Llama-70B DeepSeek-R1-Distill-Llama-70B

novita

$0.80

8,192

0.40

41

No

deepseek-ai/DeepSeek-R1-Distill-Llama-70B DeepSeek-R1-Distill-Llama-70B

nscale

cheapest

$0.75

131,072

1.00

16

No

Yes

deepseek-ai/DeepSeek-R1-Distill-Llama-70B DeepSeek-R1-Distill-Llama-70B

scaleway

fastest

-

0.33

84

Yes

zai-org/GLM-5.1-FP8 GLM-5.1-FP8

fireworks-ai

-

202,752

0.95

31

Yes

No

zai-org/GLM-5.1-FP8 GLM-5.1-FP8

zai-org

fastest

-

3.51

33

Yes

No

zai-org/GLM-4.5 GLM-4.5

novita

cheapest fastest

$0.60

$2.20

131,072

0.61

57

Yes

No

zai-org/GLM-4.5 GLM-4.5

zai-org

-

2.42

53

Yes

No

Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507

novita

cheapest

$0.09

$0.58

131,072

1.14

47

Yes

Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507

cerebras

fastest

$0.60

$1.20

-

0.14

605

Yes

No

Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507

nscale

$0.20

$0.60

32,768

1.11

19

Yes

Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507

together

$0.20

$0.60

262,144

0.29

45

Yes

Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507

scaleway

-

0.72

42

Yes

utter-project/EuroLLM-22B-Instruct-2512 EuroLLM-22B-Instruct-2512

publicai

$0.10

$0.20

-

2.31

3

No

aisingapore/Gemma-SEA-LION-v4-27B-IT Gemma-SEA-LION-v4-27B-IT

publicai

$0.20

$0.40

-

1.11

48

No

Yes

Qwen/Qwen3-235B-A22B Qwen3-235B-A22B

novita

$0.20

$0.80

40,960

0.73

16

No

Qwen/Qwen3-235B-A22B Qwen3-235B-A22B

nscale

cheapest fastest

$0.20

$0.60

32,000

1.04

31

Yes

deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528

novita

cheapest

$0.70

$2.50

163,840

2.37

24

Yes

No

deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528

sambanova

-

deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528

hyperbolic

$3.00

163,840

0.78

57

No

deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528

together

fastest

$3.00

$7.00

163,840

0.49

99

No

Yes

zai-org/GLM-4.6V-FP8 GLM-4.6V-FP8

zai-org

-

3.26

38

Yes

No

CohereLabs/c4ai-command-r7b-12-2024 c4ai-command-r7b-12-2024

cohere

-

0.27

73

Yes

No

meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct

groq

fastest

$0.11

$0.34

131,072

0.29

382

Yes

No

meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct

novita

$0.18

$0.59

131,072

0.67

43

No

meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct

nscale

cheapest

$0.09

$0.29

890,000

0.83

33

Yes

Sao10K/L3-8B-Stheno-v3.2 L3-8B-Stheno-v3.2

novita

$0.05

8,192

0.63

82

No

alpindale/WizardLM-2-8x22B WizardLM-2-8x22B

novita

$0.62

65,535

1.00

12

No

Qwen/Qwen3-30B-A3B Qwen3-30B-A3B

novita

$0.09

$0.45

40,960

0.70

31

Yes

No

deepseek-ai/DeepSeek-R1-Distill-Llama-8B DeepSeek-R1-Distill-Llama-8B

nscale

$0.05

131,072

0.97

27

No

Yes

moonshotai/Kimi-K2-Thinking Kimi-K2-Thinking

novita

$0.60

$2.50

262,144

1.24

57

Yes

No

MiniMaxAI/MiniMax-M2 MiniMax-M2

novita

$0.30

$1.20

204,800

0.86

64

Yes

No

mistralai/Mixtral-8x22B-Instruct-v0.1 Mixtral-8x22B-Instruct-v0.1

nscale

$1.20

65,536

0.92

20

No

Yes

deepseek-ai/DeepSeek-V3.2-Exp DeepSeek-V3.2-Exp

novita

$0.27

$0.41

163,840

1.22

28

Yes

Qwen/Qwen3-VL-235B-A22B-Instruct Qwen3-VL-235B-A22B-Instruct

novita

$0.30

$1.50

131,072

0.54

36

Yes

Qwen/Qwen3-4B-Thinking-2507 Qwen3-4B-Thinking-2507

nscale

$0.01

$0.03

262,144

0.88

89

Yes

No

Qwen/Qwen2.5-72B-Instruct Qwen2.5-72B-Instruct

novita

$0.38

$0.40

32,000

0.58

37

Yes

No

google/gemma-3n-E4B-it gemma-3n-E4B-it

together

$0.06

$0.12

32,768

0.23

56

No

Yes

Qwen/Qwen3-32B Qwen3-32B

groq

fastest

$0.29

$0.59

131,072

0.23

255

Yes

No

Qwen/Qwen3-32B Qwen3-32B

novita

$0.10

$0.45

40,960

0.60

45

No

Qwen/Qwen3-32B Qwen3-32B

nscale

cheapest

$0.08

$0.25

40,960

1.05

27

Yes

No

Qwen/Qwen3-32B Qwen3-32B

ovhcloud

$0.09

$0.25

32,768

0.49

32

Yes

EssentialAI/rnj-1-instruct rnj-1-instruct

together

$0.15

32,768

0.20

122

Yes

Qwen/Qwen2.5-Coder-3B-Instruct Qwen2.5-Coder-3B-Instruct

nscale

$0.01

$0.03

32,768

0.86

84

No

Yes

Qwen/Qwen3-VL-30B-A3B-Thinking Qwen3-VL-30B-A3B-Thinking

novita

cheapest

$0.20

$1.00

131,072

0.98

110

Yes

No

Qwen/Qwen3-VL-30B-A3B-Thinking Qwen3-VL-30B-A3B-Thinking

fireworks-ai

fastest

-

262,144

0.32

125

Yes

No

deepseek-ai/DeepSeek-V3.1 DeepSeek-V3.1

novita

cheapest

$0.27

$1.00

131,072

1.64

28

Yes

deepseek-ai/DeepSeek-V3.1 DeepSeek-V3.1

together

$0.60

$1.70

131,072

0.50

33

Yes

deepseek-ai/DeepSeek-V3.1 DeepSeek-V3.1

fireworks-ai

fastest

-

163,840

0.43

47

No

CohereLabs/tiny-aya-fire tiny-aya-fire

cohere

-

0.28

120

No

CohereLabs/tiny-aya-earth tiny-aya-earth

cohere

-

0.30

120

No

CohereLabs/tiny-aya-water tiny-aya-water

cohere

-

0.22

121

No

deepcogito/cogito-671b-v2.1-FP8 cogito-671b-v2.1-FP8

together

$1.25

163,840

0.44

89

No

CohereLabs/command-a-translate-08-2025 command-a-translate-08-2025

cohere

-

0.39

68

Yes

No

CohereLabs/command-a-reasoning-08-2025 command-a-reasoning-08-2025

cohere

-

0.30

52

Yes

No

CohereLabs/command-a-vision-07-2025 command-a-vision-07-2025

cohere

-

0.15

47

No

zai-org/GLM-4.5-Air GLM-4.5-Air

novita

cheapest

$0.13

$0.85

131,072

0.74

49

Yes

No

zai-org/GLM-4.5-Air GLM-4.5-Air

zai-org

fastest

-

1.75

78

Yes

No

zai-org/GLM-4.5V GLM-4.5V

novita

cheapest

$0.60

$1.80

65,536

0.92

26

Yes

No

zai-org/GLM-4.5V GLM-4.5V

zai-org

fastest

-

2.51

43

Yes

No

CohereLabs/c4ai-command-r7b-arabic-02-2025 c4ai-command-r7b-arabic-02-2025

cohere

-

0.28

82

Yes

No

zai-org/GLM-4.6-FP8 GLM-4.6-FP8

zai-org

-

3.46

15

No

zai-org/GLM-4.5V-FP8 GLM-4.5V-FP8

zai-org

-

2.33

40

Yes

No

zai-org/GLM-4.6V GLM-4.6V

zai-org

-

2.94

38

Yes

No

zai-org/GLM-4.6V-Flash GLM-4.6V-Flash

novita

cheapest

$0.30

$0.90

131,072

1.01

50

Yes

No

zai-org/GLM-4.6V-Flash GLM-4.6V-Flash

zai-org

fastest

-

3.03

58

Yes

No

CohereLabs/aya-vision-32b aya-vision-32b

cohere

-

0.23

37

No

CohereLabs/aya-expanse-32b aya-expanse-32b

cohere

-

0.35

38

No

zai-org/GLM-4.7-FP8 GLM-4.7-FP8

zai-org

-

2.94

56

Yes

No

CohereLabs/c4ai-command-r-08-2024 c4ai-command-r-08-2024

cohere

-

1.02

32

Yes

No

CohereLabs/c4ai-command-a-03-2025 c4ai-command-a-03-2025

cohere

-

0.64

19

Yes

No

google/gemma-3-27b-it gemma-3-27b-it

scaleway

-

0.45

48

Yes

No

swiss-ai/Apertus-70B-Instruct-2509 Apertus-70B-Instruct-2509

publicai

$0.82

$2.92

-

0.60

60

No

Yes

deepseek-ai/DeepSeek-V3.1-Terminus DeepSeek-V3.1-Terminus

novita

$0.27

$1.00

131,072

1.55

26

Yes

allenai/Olmo-3-7B-Instruct Olmo-3-7B-Instruct

publicai

$0.10

$0.20

-

Yes

No

aisingapore/Qwen-SEA-LION-v4-32B-IT Qwen-SEA-LION-v4-32B-IT

publicai

$0.25

$0.50

-

1.47

44

Yes

dicta-il/DictaLM-3.0-24B-Thinking DictaLM-3.0-24B-Thinking

publicai

$0.20

$0.40

-

1.05

63

Yes

Qwen/Qwen3-Next-80B-A3B-Thinking Qwen3-Next-80B-A3B-Thinking

novita

$0.15

$1.50

131,072

0.85

82

Yes

No

Qwen/Qwen3-235B-A22B-Thinking-2507 Qwen3-235B-A22B-Thinking-2507

novita

$0.30

$3.00

131,072

0.95

39

Yes

No

baidu/ERNIE-4.5-VL-424B-A47B-Base-PT ERNIE-4.5-VL-424B-A47B-Base-PT

novita

$0.42

$1.25

123,000

1.10

45

No

baidu/ERNIE-4.5-300B-A47B-Base-PT ERNIE-4.5-300B-A47B-Base-PT

novita

$0.28

$1.10

123,000

1.41

21

No

MiniMaxAI/MiniMax-M1-80k MiniMax-M1-80k

novita

$0.55

$2.20

1,000,000

1.16

67

Yes

No

deepseek-ai/DeepSeek-Prover-V2-671B DeepSeek-Prover-V2-671B

novita

$0.70

$2.50

160,000

2.90

10

No

zai-org/GLM-4-32B-0414 GLM-4-32B-0414

novita

$0.55

$1.66

32,000

0.96

43

No

meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 Llama-4-Maverick-17B-128E-Instruct-FP8

novita

$0.27

$0.85

1,048,576

0.44

47

No

Yes

Sao10K/L3-8B-Lunaris-v1 L3-8B-Lunaris-v1

novita

$0.05

8,192

0.72

41

No

Sao10K/L3-70B-Euryale-v2.1 L3-70B-Euryale-v2.1

novita

$1.48

8,192

0.62

31

No

NousResearch/Hermes-2-Pro-Llama-3-8B Hermes-2-Pro-Llama-3-8B

novita

$0.14

8,192

0.36

114

No

meta-llama/Meta-Llama-3-70B-Instruct Meta-Llama-3-70B-Instruct

novita

$0.51

$0.74

8,192

0.61

24

No

Yes

zai-org/AutoGLM-Phone-9B-Multilingual AutoGLM-Phone-9B-Multilingual

novita

$0.04

$0.14

65,536

0.74

43

No

Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 Qwen3-Coder-480B-A35B-Instruct-FP8

together

$2.00

262,144

0.19

40

Yes

openai/gpt-oss-safeguard-20b gpt-oss-safeguard-20b

groq

-

131,072

0.14

763

Yes

No