Hugging Face Inference Providers


moonshotai/Kimi-K2-Thinking Kimi-K2-Thinking	novita cheapest	0.48	2	262144	1.01	24	Yes	No
moonshotai/Kimi-K2-Thinking Kimi-K2-Thinking	nebius	0.6	2.5	262144	0.34	83	Yes	Yes
moonshotai/Kimi-K2-Thinking Kimi-K2-Thinking	together fastest	1.2	4	262144	0.78	110	Yes	Yes
deepseek-ai/DeepSeek-OCR DeepSeek-OCR	novita	0.024	0.024	8192	0.65	196	No	Yes
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	novita cheapest	0.02	0.05	16384	0.64	84	No	No
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	nebius	0.03	0.09	131072	0.35	194	No	Yes
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	cerebras fastest	0.1	0.1	-	0.26	1243	No	No
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	sambanova	0.1	0.2	16384	0.38	733	Yes	Yes
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	nscale	0.06	0.06	131072	0.94	58	No	No
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	fireworks-ai	-	-	-	-	-	-	-
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	scaleway	-	-	-	0.38	74	Yes	Yes
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	ovhcloud	-	-	-	0.40	42	Yes	No
allenai/Olmo-3-32B-Think Olmo-3-32B-Think	publicai	-	-	-	2.83	41	No	Yes
allenai/Olmo-3-7B-Instruct Olmo-3-7B-Instruct	publicai	-	-	-	1.78	36	No	No
allenai/Olmo-3-7B-Think Olmo-3-7B-Think	publicai	-	-	-	2.84	106	No	Yes
openai/gpt-oss-20b gpt-oss-20b	groq fastest	0.1	0.5	131072	0.15	844	Yes	No
openai/gpt-oss-20b gpt-oss-20b	novita	0.032	0.12	131072	0.90	169	No	Yes
openai/gpt-oss-20b gpt-oss-20b	nebius	0.05	0.2	131072	0.31	157	Yes	Yes
openai/gpt-oss-20b gpt-oss-20b	nscale	0.05	0.2	131072	0.95	58	Yes	Yes
openai/gpt-oss-20b gpt-oss-20b	hyperbolic cheapest	0.1	0.1	131072	0.58	148	No	No
openai/gpt-oss-20b gpt-oss-20b	together	0.05	0.2	131072	0.26	162	Yes	Yes
openai/gpt-oss-20b gpt-oss-20b	fireworks-ai	0.05	0.2	131072	0.59	151	Yes	No
openai/gpt-oss-20b gpt-oss-20b	ovhcloud	-	-	-	0.30	78	Yes	Yes
Qwen/Qwen3-VL-8B-Instruct Qwen3-VL-8B-Instruct	novita	0.064	0.4	131072	0.75	69	Yes	No
zai-org/GLM-4.6 GLM-4.6	novita cheapest	0.44	1.76	204800	1.04	60	Yes	No
zai-org/GLM-4.6 GLM-4.6	cerebras fastest	-	-	-	0.23	398	Yes	No
zai-org/GLM-4.6 GLM-4.6	zai-org	-	-	-	2.67	52	Yes	No
openai/gpt-oss-120b gpt-oss-120b	groq	0.15	0.75	131072	0.17	427	Yes	No
openai/gpt-oss-120b gpt-oss-120b	novita cheapest	0.04	0.2	131072	0.84	127	No	Yes
openai/gpt-oss-120b gpt-oss-120b	nebius	0.15	0.6	131072	0.58	31	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	cerebras fastest	0.25	0.69	-	0.25	715	Yes	No
openai/gpt-oss-120b gpt-oss-120b	sambanova	0.22	0.59	131072	0.43	508	No	No
openai/gpt-oss-120b gpt-oss-120b	nscale	0.1	0.4	131072	0.74	91	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	hyperbolic	0.3	0.3	131072	0.70	271	Yes	No
openai/gpt-oss-120b gpt-oss-120b	together	0.15	0.6	131072	0.31	144	Yes	No
openai/gpt-oss-120b gpt-oss-120b	fireworks-ai	0.15	0.6	131072	0.44	112	Yes	No
openai/gpt-oss-120b gpt-oss-120b	scaleway	-	-	-	0.55	112	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	ovhcloud	-	-	-	0.37	115	Yes	Yes
MiniMaxAI/MiniMax-M2 MiniMax-M2	novita	0.3	1.2	204800	0.90	69	No	No
meta-llama/Llama-3.2-3B-Instruct Llama-3.2-3B-Instruct	novita cheapest	0.024	0.04	32768	0.80	115	Yes	No
meta-llama/Llama-3.2-3B-Instruct Llama-3.2-3B-Instruct	sambanova	-	-	-	-	-	-	-
meta-llama/Llama-3.2-3B-Instruct Llama-3.2-3B-Instruct	hyperbolic	0.1	0.1	131072	0.60	128	No	No
meta-llama/Llama-3.2-3B-Instruct Llama-3.2-3B-Instruct	together fastest	0.06	0.06	131072	0.25	153	Yes	No
PrimeIntellect/INTELLECT-3-FP8 INTELLECT-3-FP8	nebius	0.2	1.1	131072	0.48	39	Yes	No
Qwen/Qwen3-VL-30B-A3B-Instruct Qwen3-VL-30B-A3B-Instruct	novita	0.16	0.56	131072	0.70	95	Yes	Yes
Qwen/Qwen2.5-7B-Instruct Qwen2.5-7B-Instruct	together	0.3	0.3	32768	0.22	138	Yes	Yes
deepseek-ai/DeepSeek-V3.2-Exp DeepSeek-V3.2-Exp	novita	0.216	0.328	163840	0.77	32	Yes	Yes
deepseek-ai/DeepSeek-R1 DeepSeek-R1	novita cheapest	0.56	2	64000	0.73	25	Yes	No
deepseek-ai/DeepSeek-R1 DeepSeek-R1	sambanova fastest	-	-	-	0.81	197	Yes	Yes
deepseek-ai/DeepSeek-R1 DeepSeek-R1	hyperbolic	2	2	163840	0.68	47	No	No
deepseek-ai/DeepSeek-R1 DeepSeek-R1	together	3	7	163840	0.47	53	No	Yes
deepseek-ai/DeepSeek-R1 DeepSeek-R1	fireworks-ai	-	-	-	-	-	-	-
Qwen/Qwen3-4B-Instruct-2507 Qwen3-4B-Instruct-2507	nscale	0.01	0.03	262144	0.80	91	Yes	No
Qwen/Qwen3-Next-80B-A3B-Instruct Qwen3-Next-80B-A3B-Instruct	novita	0.12	1.2	131072	0.73	139	Yes	Yes
Qwen/Qwen3-Next-80B-A3B-Instruct Qwen3-Next-80B-A3B-Instruct	hyperbolic cheapest	0.3	0.3	262144	0.55	148	Yes	No
Qwen/Qwen3-Next-80B-A3B-Instruct Qwen3-Next-80B-A3B-Instruct	together fastest	0.15	1.5	262144	0.65	150	Yes	Yes
Qwen/Qwen3-Coder-30B-A3B-Instruct Qwen3-Coder-30B-A3B-Instruct	nebius cheapest fastest	0.1	0.3	262144	0.30	131	Yes	Yes
Qwen/Qwen3-Coder-30B-A3B-Instruct Qwen3-Coder-30B-A3B-Instruct	fireworks-ai	-	-	-	-	-	-	-
Qwen/Qwen3-Coder-30B-A3B-Instruct Qwen3-Coder-30B-A3B-Instruct	scaleway	-	-	-	0.40	82	Yes	No
Qwen/Qwen3-Coder-30B-A3B-Instruct Qwen3-Coder-30B-A3B-Instruct	ovhcloud	-	-	-	0.45	107	Yes	Yes
Qwen/Qwen3-8B Qwen3-8B	nscale	0.07	0.18	40960	0.85	57	Yes	No
google/gemma-3-27b-it gemma-3-27b-it	nebius cheapest fastest	0.2	0.6	110000	0.43	77	No	Yes
google/gemma-3-27b-it gemma-3-27b-it	scaleway	-	-	-	0.62	43	Yes	No
nvidia/NVIDIA-Nemotron-Nano-12B-v2 NVIDIA-Nemotron-Nano-12B-v2	nebius	0.07	0.2	131072	0.31	125	No	Yes
meta-llama/Meta-Llama-3-8B-Instruct Meta-Llama-3-8B-Instruct	groq	-	-	-	-	-	-	-
meta-llama/Meta-Llama-3-8B-Instruct Meta-Llama-3-8B-Instruct	novita	0.032	0.032	8192	0.70	84	No	No
meta-llama/Meta-Llama-3-8B-Instruct Meta-Llama-3-8B-Instruct	together	-	-	-	-	-	-	-
meta-llama/Llama-3.2-1B-Instruct Llama-3.2-1B-Instruct	novita	-	-	131000	0.66	206	No	No
meta-llama/Llama-3.2-1B-Instruct Llama-3.2-1B-Instruct	sambanova	-	-	-	-	-	-	-
moonshotai/Kimi-K2-Instruct Kimi-K2-Instruct	novita cheapest	0.456	1.84	131072	0.93	32	Yes	Yes
moonshotai/Kimi-K2-Instruct Kimi-K2-Instruct	nebius fastest	0.5	2.4	131072	0.42	62	Yes	Yes
moonshotai/Kimi-K2-Instruct Kimi-K2-Instruct	together	1	3	131072	0.64	47	Yes	Yes
moonshotai/Kimi-K2-Instruct Kimi-K2-Instruct	fireworks-ai	-	-	-	-	-	-	-
Qwen/Qwen2.5-VL-7B-Instruct Qwen2.5-VL-7B-Instruct	hyperbolic	0.2	0.2	32768	0.47	32	No	No
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	groq	0.59	0.79	131072	0.14	276	Yes	No
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	novita cheapest	0.104	0.312	131072	0.65	41	Yes	No
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	nebius	0.25	0.75	131072	0.37	137	Yes	Yes
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	cerebras fastest	0.85	1.2	-	0.26	1105	Yes	No
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	sambanova	0.6	1.2	131072	0.37	366	No	No
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	nscale	0.4	0.4	131072	0.93	17	No	Yes
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	hyperbolic	0.4	0.4	131072	0.71	119	No	No
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	together	0.88	0.88	131072	0.46	136	Yes	Yes
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	fireworks-ai	0.9	0.9	131072	0.79	146	No	No
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	scaleway	-	-	-	0.59	35	Yes	Yes
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	ovhcloud	-	-	-	1.31	30	Yes	Yes
Qwen/Qwen3-32B Qwen3-32B	groq fastest	0.29	0.59	131072	0.19	289	Yes	No
Qwen/Qwen3-32B Qwen3-32B	novita	0.08	0.36	40960	0.73	49	No	No
Qwen/Qwen3-32B Qwen3-32B	nebius	0.1	0.3	40960	0.33	46	Yes	Yes
Qwen/Qwen3-32B Qwen3-32B	cerebras	0.4	0.8	-	0.24	130	No	No
Qwen/Qwen3-32B Qwen3-32B	sambanova	0.4	0.8	32768	1.84	232	Yes	Yes
Qwen/Qwen3-32B Qwen3-32B	nscale cheapest	0.08	0.25	40960	0.91	25	Yes	Yes
Qwen/Qwen3-32B Qwen3-32B	ovhcloud	-	-	-	0.43	41	Yes	Yes
Qwen/Qwen3-4B-Thinking-2507 Qwen3-4B-Thinking-2507	nscale	0.01	0.03	262144	0.96	89	Yes	No
deepseek-ai/DeepSeek-R1-0528-Qwen3-8B DeepSeek-R1-0528-Qwen3-8B	novita	0.048	0.072	128000	0.67	81	No	No
HuggingFaceTB/SmolLM3-3B SmolLM3-3B	hf-inference	-	-	-	0.16	87	Yes	Yes
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	novita cheapest	0.072	0.464	131072	1.10	22	Yes	Yes
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	nebius	0.2	0.6	262144	0.45	78	Yes	Yes
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	cerebras fastest	0.6	1.2	-	0.29	503	Yes	No
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	nscale	0.2	0.6	32768	0.96	24	Yes	Yes
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	hyperbolic	2	2	262144	1.15	44	Yes	No
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	together	0.2	0.6	262144	0.39	42	Yes	Yes
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	fireworks-ai	0.22	0.88	262144	0.82	55	Yes	No
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	scaleway	-	-	-	0.47	82	Yes	Yes
moonshotai/Kimi-K2-Instruct-0905 Kimi-K2-Instruct-0905	groq fastest	-	-	262144	0.19	179	Yes	No
moonshotai/Kimi-K2-Instruct-0905 Kimi-K2-Instruct-0905	novita cheapest	0.48	2	262144	0.55	37	Yes	Yes
moonshotai/Kimi-K2-Instruct-0905 Kimi-K2-Instruct-0905	together	1	3	262144	0.62	49	Yes	Yes
zai-org/GLM-4.5-Air GLM-4.5-Air	novita cheapest fastest	0.104	0.68	131072	0.60	63	Yes	No
zai-org/GLM-4.5-Air GLM-4.5-Air	nebius	0.2	1.2	131072	0.42	21	Yes	Yes
zai-org/GLM-4.5-Air GLM-4.5-Air	fireworks-ai	-	-	-	-	-	-	-
zai-org/GLM-4.5-Air GLM-4.5-Air	zai-org	-	-	-	2.69	63	Yes	No
Qwen/Qwen3-VL-235B-A22B-Instruct Qwen3-VL-235B-A22B-Instruct	novita	0.24	1.2	131072	0.88	41	Yes	No
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B DeepSeek-R1-Distill-Qwen-1.5B	nscale	0.1	0.1	131072	0.77	139	No	No
baichuan-inc/Baichuan-M2-32B Baichuan-M2-32B	novita	0.056	0.056	131072	2.02	34	No	Yes
Qwen/Qwen3-30B-A3B-Instruct-2507 Qwen3-30B-A3B-Instruct-2507	nebius	0.1	0.3	262144	0.37	106	Yes	Yes
Qwen/Qwen3-Next-80B-A3B-Thinking Qwen3-Next-80B-A3B-Thinking	novita	0.12	1.2	131072	0.73	140	Yes	No
Qwen/Qwen3-Next-80B-A3B-Thinking Qwen3-Next-80B-A3B-Thinking	hyperbolic cheapest	0.3	0.3	262144	0.54	185	Yes	No
Qwen/Qwen3-Next-80B-A3B-Thinking Qwen3-Next-80B-A3B-Thinking	together fastest	0.15	1.5	262144	0.48	202	Yes	Yes
Qwen/Qwen3-VL-235B-A22B-Thinking Qwen3-VL-235B-A22B-Thinking	novita	0.784	3.16	131072	1.22	33	No	No
deepseek-ai/DeepSeek-V3.1-Terminus DeepSeek-V3.1-Terminus	novita	0.216	0.8	131072	1.10	31	Yes	Yes
Qwen/Qwen3-Coder-480B-A35B-Instruct Qwen3-Coder-480B-A35B-Instruct	novita cheapest	0.29	1.2	262144	0.94	46	Yes	Yes
Qwen/Qwen3-Coder-480B-A35B-Instruct Qwen3-Coder-480B-A35B-Instruct	nebius fastest	0.4	1.8	262144	0.39	58	Yes	Yes
Qwen/Qwen3-Coder-480B-A35B-Instruct Qwen3-Coder-480B-A35B-Instruct	cerebras	-	-	-	-	-	-	-
Qwen/Qwen3-Coder-480B-A35B-Instruct Qwen3-Coder-480B-A35B-Instruct	hyperbolic	2	2	262144	1.66	55	Yes	No
Qwen/Qwen3-Coder-480B-A35B-Instruct Qwen3-Coder-480B-A35B-Instruct	together	2	2	262144	0.53	51	Yes	Yes
Qwen/Qwen3-Coder-480B-A35B-Instruct Qwen3-Coder-480B-A35B-Instruct	fireworks-ai	0.45	1.8	262144	0.65	37	Yes	No
Qwen/Qwen3-30B-A3B Qwen3-30B-A3B	novita cheapest	0.072	0.36	40960	0.89	124	No	No
Qwen/Qwen3-30B-A3B Qwen3-30B-A3B	fireworks-ai fastest	0.15	0.6	131072	0.53	164	Yes	No
zai-org/GLM-4.5 GLM-4.5	novita cheapest	0.48	1.76	131072	0.62	56	Yes	No
zai-org/GLM-4.5 GLM-4.5	nebius	0.6	2.2	131072	0.45	38	Yes	Yes
zai-org/GLM-4.5 GLM-4.5	fireworks-ai fastest	0.55	2.19	131072	0.81	89	Yes	No
zai-org/GLM-4.5 GLM-4.5	zai-org	-	-	-	3.01	52	Yes	No
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B DeepSeek-R1-Distill-Qwen-14B	novita cheapest fastest	0.12	0.12	32768	0.82	59	No	No
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B DeepSeek-R1-Distill-Qwen-14B	nscale	0.2	0.2	131072	0.84	37	No	Yes
Qwen/Qwen2.5-VL-72B-Instruct Qwen2.5-VL-72B-Instruct	nebius	0.25	0.75	32000	0.28	30	No	Yes
Qwen/Qwen2.5-VL-72B-Instruct Qwen2.5-VL-72B-Instruct	hyperbolic cheapest fastest	0.6	0.6	32768	0.49	39	No	No
Qwen/Qwen2.5-VL-72B-Instruct Qwen2.5-VL-72B-Instruct	ovhcloud	-	-	-	0.55	25	No	Yes
google/gemma-2-2b-it gemma-2-2b-it	nebius	0.02	0.06	8192	0.31	180	No	Yes
Qwen/Qwen2.5-Coder-7B-Instruct Qwen2.5-Coder-7B-Instruct	nscale	0.01	0.03	131072	0.76	61	No	Yes
meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct	groq fastest	0.11	0.34	131072	0.29	342	Yes	No
meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct	novita	0.08	0.4	131072	0.33	44	No	No
meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct	sambanova	-	-	-	-	-	-	-
meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct	nscale cheapest	0.09	0.29	890000	0.77	33	Yes	Yes
meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct	together	0.18	0.59	1048576	0.29	90	Yes	Yes
meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct	fireworks-ai	-	-	-	-	-	-	-
Qwen/Qwen2.5-Coder-3B-Instruct Qwen2.5-Coder-3B-Instruct	nscale	0.01	0.03	32768	0.80	80	No	Yes
deepseek-ai/DeepSeek-V3.1 DeepSeek-V3.1	novita cheapest	0.216	0.8	131072	0.93	32	Yes	No
deepseek-ai/DeepSeek-V3.1 DeepSeek-V3.1	together	0.6	1.7	131072	1.23	64	Yes	No
deepseek-ai/DeepSeek-V3.1 DeepSeek-V3.1	fireworks-ai fastest	-	-	163840	0.88	83	Yes	No
Qwen/Qwen3-14B Qwen3-14B	nscale	0.07	0.2	40960	0.93	47	Yes	No
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B DeepSeek-R1-Distill-Qwen-7B	nscale	0.15	0.15	131072	0.85	66	No	No
Qwen/Qwen2.5-72B-Instruct Qwen2.5-72B-Instruct	novita cheapest	0.304	0.32	32000	2.15	27	Yes	No
Qwen/Qwen2.5-72B-Instruct Qwen2.5-72B-Instruct	hyperbolic	0.4	0.4	131072	1.35	49	Yes	No
Qwen/Qwen2.5-72B-Instruct Qwen2.5-72B-Instruct	together fastest	1.2	1.2	131072	0.32	84	Yes	Yes
Qwen/Qwen2.5-72B-Instruct Qwen2.5-72B-Instruct	fireworks-ai	-	-	-	-	-	-	-
Qwen/Qwen3-30B-A3B-Thinking-2507 Qwen3-30B-A3B-Thinking-2507	nebius	0.1	0.3	262144	0.35	105	Yes	Yes
zai-org/GLM-4.6-FP8 GLM-4.6-FP8	zai-org	-	-	-	2.39	64	No	No
meta-llama/Meta-Llama-3-70B-Instruct Meta-Llama-3-70B-Instruct	groq	-	-	-	-	-	-	-
meta-llama/Meta-Llama-3-70B-Instruct Meta-Llama-3-70B-Instruct	novita	0.51	0.74	8192	0.80	29	No	Yes
meta-llama/Meta-Llama-3-70B-Instruct Meta-Llama-3-70B-Instruct	hyperbolic cheapest	0.4	0.4	8192	0.62	103	No	No
meta-llama/Meta-Llama-3-70B-Instruct Meta-Llama-3-70B-Instruct	together fastest	0.88	0.88	8192	0.36	108	No	Yes
deepseek-ai/DeepSeek-R1-Distill-Llama-8B DeepSeek-R1-Distill-Llama-8B	novita	-	-	-	-	-	-	-
deepseek-ai/DeepSeek-R1-Distill-Llama-8B DeepSeek-R1-Distill-Llama-8B	nscale	0.05	0.05	131072	0.87	57	No	Yes
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B DeepSeek-R1-Distill-Qwen-32B	novita cheapest	0.24	0.24	64000	0.76	23	No	Yes
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B DeepSeek-R1-Distill-Qwen-32B	nscale fastest	0.3	0.3	131072	0.90	25	No	Yes
Qwen/QwQ-32B QwQ-32B	groq	-	-	-	-	-	-	-
Qwen/QwQ-32B QwQ-32B	nebius	-	-	-	-	-	-	-
Qwen/QwQ-32B QwQ-32B	sambanova	-	-	-	-	-	-	-
Qwen/QwQ-32B QwQ-32B	nscale cheapest fastest	0.18	0.2	131072	0.94	27	Yes	Yes
Qwen/QwQ-32B QwQ-32B	hyperbolic	0.4	0.4	131072	2.29	18	Yes	No
Qwen/QwQ-32B QwQ-32B	fireworks-ai	-	-	-	-	-	-	-
zai-org/GLM-4.5-Air-FP8 GLM-4.5-Air-FP8	together	0.2	1.1	131072	0.35	113	Yes	Yes
katanemo/Arch-Router-1.5B Arch-Router-1.5B	hf-inference	-	-	-	0.13	70	No	Yes
openai/gpt-oss-safeguard-20b gpt-oss-safeguard-20b	groq	-	-	131072	0.13	851	Yes	No
zai-org/GLM-4.5V GLM-4.5V	novita cheapest fastest	0.48	1.44	65536	0.82	76	Yes	No
zai-org/GLM-4.5V GLM-4.5V	zai-org	-	-	-	3.36	46	Yes	No
deepcogito/cogito-671b-v2.1 cogito-671b-v2.1	together cheapest fastest	1.25	1.25	163840	0.23	73	No	Yes
deepcogito/cogito-671b-v2.1 cogito-671b-v2.1	fireworks-ai	-	-	163840	1.14	23	Yes	No
aisingapore/Qwen-SEA-LION-v4-32B-IT Qwen-SEA-LION-v4-32B-IT	publicai	-	-	-	2.61	41	Yes	Yes
NousResearch/Hermes-4-405B Hermes-4-405B	nebius	1	3	131072	0.43	37	No	No
Sao10K/L3-70B-Euryale-v2.1 L3-70B-Euryale-v2.1	novita	1.48	1.48	8192	0.76	40	No	No
marin-community/marin-8b-instruct marin-8b-instruct	together	0.18	0.18	4096	0.24	178	No	Yes
alpindale/WizardLM-2-8x22B WizardLM-2-8x22B	novita	0.496	0.496	65535	0.43	46	No	No
Sao10K/L3-8B-Stheno-v3.2 L3-8B-Stheno-v3.2	novita	0.05	0.05	8192	0.69	62	No	No
Qwen/Qwen3-VL-30B-A3B-Thinking Qwen3-VL-30B-A3B-Thinking	novita	0.16	0.8	131072	0.70	89	Yes	Yes
deepseek-ai/DeepSeek-V3 DeepSeek-V3	novita cheapest	0.32	1.04	64000	1.41	28	Yes	No
deepseek-ai/DeepSeek-V3 DeepSeek-V3	together fastest	1.25	1.25	131072	0.61	29	Yes	Yes
deepseek-ai/DeepSeek-V3 DeepSeek-V3	fireworks-ai	-	-	-	-	-	-	-
deepcogito/cogito-671b-v2.1-FP8 cogito-671b-v2.1-FP8	together	1.25	1.25	163840	0.25	72	No	Yes
Qwen/Qwen2.5-VL-32B-Instruct Qwen2.5-VL-32B-Instruct	fireworks-ai	0.22	0.88	128000	0.39	60	No	No
Qwen/Qwen3-235B-A22B Qwen3-235B-A22B	novita	0.16	0.64	40960	1.11	37	No	No
Qwen/Qwen3-235B-A22B Qwen3-235B-A22B	nscale cheapest	0.2	0.6	32000	1.07	23	Yes	Yes
Qwen/Qwen3-235B-A22B Qwen3-235B-A22B	together	0.2	0.6	40960	0.43	46	Yes	Yes
Qwen/Qwen3-235B-A22B Qwen3-235B-A22B	fireworks-ai fastest	0.22	0.88	131072	0.58	64	Yes	No
Qwen/Qwen2.5-Coder-32B-Instruct Qwen2.5-Coder-32B-Instruct	nscale cheapest	0.06	0.2	131072	0.92	28	No	Yes
Qwen/Qwen2.5-Coder-32B-Instruct Qwen2.5-Coder-32B-Instruct	hyperbolic	0.2	0.2	32768	1.26	47	No	No
Qwen/Qwen2.5-Coder-32B-Instruct Qwen2.5-Coder-32B-Instruct	together	-	-	-	-	-	-	-
Qwen/Qwen2.5-Coder-32B-Instruct Qwen2.5-Coder-32B-Instruct	scaleway fastest	-	-	-	0.45	96	Yes	No
meta-llama/Llama-4-Maverick-17B-128E-Instruct Llama-4-Maverick-17B-128E-Instruct	groq cheapest fastest	0.2	0.6	131072	0.21	474	Yes	No
meta-llama/Llama-4-Maverick-17B-128E-Instruct Llama-4-Maverick-17B-128E-Instruct	sambanova	-	-	-	-	-	-	-
meta-llama/Llama-4-Maverick-17B-128E-Instruct Llama-4-Maverick-17B-128E-Instruct	fireworks-ai	0.22	0.88	1048576	0.40	87	Yes	No
deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324	novita cheapest	0.216	0.896	163840	1.10	31	Yes	Yes
deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324	nebius	0.75	2.25	32768	0.93	117	No	No
deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324	sambanova fastest	3	4.5	131072	0.98	133	No	No
deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324	hyperbolic	1.25	1.25	163840	0.77	50	No	No
deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324	together	1.25	1.25	131072	0.95	34	Yes	Yes
deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324	fireworks-ai	0.9	0.9	163840	0.97	55	Yes	No
mistralai/Mixtral-8x22B-Instruct-v0.1 Mixtral-8x22B-Instruct-v0.1	nscale cheapest	1.2	1.2	65536	0.88	25	No	Yes
mistralai/Mixtral-8x22B-Instruct-v0.1 Mixtral-8x22B-Instruct-v0.1	together	-	-	-	-	-	-	-
mistralai/Mixtral-8x22B-Instruct-v0.1 Mixtral-8x22B-Instruct-v0.1	fireworks-ai fastest	1.2	1.2	65536	0.34	69	No	No
Qwen/Qwen2.5-Coder-7B Qwen2.5-Coder-7B	nebius	0.03	0.09	32768	0.44	173	No	Yes
google/gemma-2-9b-it gemma-2-9b-it	groq	-	-	-	-	-	-	-
google/gemma-2-9b-it gemma-2-9b-it	nebius	0.03	0.09	8192	0.29	136	No	Yes
baidu/ERNIE-4.5-0.3B-PT ERNIE-4.5-0.3B-PT	novita	-	-	120000	1.20	102	No	No
NousResearch/Hermes-2-Pro-Llama-3-8B Hermes-2-Pro-Llama-3-8B	novita	0.14	0.14	8192	0.78	97	No	No
swiss-ai/Apertus-8B-Instruct-2509 Apertus-8B-Instruct-2509	publicai	-	-	-	1.34	80	No	Yes
aisingapore/Gemma-SEA-LION-v4-27B-IT Gemma-SEA-LION-v4-27B-IT	publicai	-	-	-	1.81	48	No	Yes
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 Llama-4-Maverick-17B-128E-Instruct-FP8	novita cheapest	0.136	0.68	1048576	0.46	35	No	No
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 Llama-4-Maverick-17B-128E-Instruct-FP8	together fastest	0.27	0.85	1048576	0.35	90	Yes	Yes
deepcogito/cogito-v2-preview-llama-70B cogito-v2-preview-llama-70B	together	0.88	0.88	32768	1.61	50	Yes	Yes
Qwen/Qwen3-235B-A22B-FP8 Qwen3-235B-A22B-FP8	together	0.2	0.6	40960	0.44	41	Yes	Yes
deepcogito/cogito-v2-preview-llama-109B-MoE cogito-v2-preview-llama-109B-MoE	together	0.18	0.59	32767	0.69	85	Yes	Yes
deepcogito/cogito-v2-preview-llama-405B cogito-v2-preview-llama-405B	together	3.5	3.5	32768	0.83	26	Yes	Yes
zai-org/GLM-4.5V-FP8 GLM-4.5V-FP8	zai-org	-	-	-	3.14	44	Yes	No
deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528	novita cheapest	0.56	2	163840	0.68	27	Yes	No
deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528	nebius	0.8	2.4	163840	0.51	17	Yes	Yes
deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528	sambanova fastest	5	7	131072	1.29	182	No	No
deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528	hyperbolic	3	3	163840	0.69	50	No	No
deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528	together	3	7	163840	0.49	53	No	Yes
deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528	fireworks-ai	3	8	163840	0.87	37	Yes	No
Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 Qwen3-Coder-480B-A35B-Instruct-FP8	together	2	2	262144	0.53	52	Yes	Yes
SentientAGI/Dobby-Unhinged-Llama-3.3-70B Dobby-Unhinged-Llama-3.3-70B	fireworks-ai	0.9	0.9	131072	0.37	50	No	No
Qwen/Qwen3-235B-A22B-Thinking-2507 Qwen3-235B-A22B-Thinking-2507	novita	0.24	2.4	131072	0.38	37	Yes	No
Qwen/Qwen3-235B-A22B-Thinking-2507 Qwen3-235B-A22B-Thinking-2507	nebius cheapest	0.2	0.8	262144	0.48	30	Yes	Yes
Qwen/Qwen3-235B-A22B-Thinking-2507 Qwen3-235B-A22B-Thinking-2507	cerebras	-	-	-	-	-	-	-
Qwen/Qwen3-235B-A22B-Thinking-2507 Qwen3-235B-A22B-Thinking-2507	fireworks-ai fastest	0.22	0.88	262144	0.75	66	Yes	No
NousResearch/Hermes-4-70B Hermes-4-70B	nebius	0.13	0.4	131072	0.28	76	No	No
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 Llama-3_1-Nemotron-Ultra-253B-v1	nebius	0.6	1.8	131072	0.45	39	No	Yes
meta-llama/Llama-Guard-4-12B Llama-Guard-4-12B	groq	0.2	0.2	131072	0.17	13	No	No
CohereLabs/command-a-translate-08-2025 command-a-translate-08-2025	cohere	-	-	-	0.21	64	Yes	No
CohereLabs/command-a-reasoning-08-2025 command-a-reasoning-08-2025	cohere	-	-	-	0.19	94	Yes	No
CohereLabs/command-a-vision-07-2025 command-a-vision-07-2025	cohere	-	-	-	0.23	40	No	No
CohereLabs/aya-vision-32b aya-vision-32b	cohere	-	-	-	0.37	56	No	No
CohereLabs/aya-expanse-32b aya-expanse-32b	cohere	-	-	-	0.21	39	No	No
CohereLabs/c4ai-command-r-08-2024 c4ai-command-r-08-2024	cohere	-	-	-	0.24	57	Yes	No
CohereLabs/c4ai-command-r7b-12-2024 c4ai-command-r7b-12-2024	cohere	-	-	-	0.25	114	Yes	No
CohereLabs/c4ai-command-a-03-2025 c4ai-command-a-03-2025	cohere	-	-	-	0.27	54	Yes	No
zai-org/GLM-4.1V-9B-Thinking GLM-4.1V-9B-Thinking	novita	0.028	0.11	65536	0.78	70	No	No
deepseek-ai/DeepSeek-R1-Distill-Llama-70B DeepSeek-R1-Distill-Llama-70B	groq	-	-	-	-	-	-	-
deepseek-ai/DeepSeek-R1-Distill-Llama-70B DeepSeek-R1-Distill-Llama-70B	novita cheapest	0.64	0.64	8192	1.21	31	No	No
deepseek-ai/DeepSeek-R1-Distill-Llama-70B DeepSeek-R1-Distill-Llama-70B	sambanova fastest	0.7	1.4	131072	2.47	168	No	No
deepseek-ai/DeepSeek-R1-Distill-Llama-70B DeepSeek-R1-Distill-Llama-70B	nscale	0.75	0.75	131072	0.89	16	No	Yes
deepseek-ai/DeepSeek-R1-Distill-Llama-70B DeepSeek-R1-Distill-Llama-70B	scaleway	-	-	-	0.57	24	No	Yes
deepseek-ai/DeepSeek-R1-Distill-Llama-70B DeepSeek-R1-Distill-Llama-70B	ovhcloud	-	-	-	0.45	30	No	Yes
tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4 Llama-3.3-Swallow-70B-Instruct-v0.4	sambanova	0.6	1.2	131072	2.13	163	No	No
swiss-ai/Apertus-70B-Instruct-2509 Apertus-70B-Instruct-2509	publicai	-	-	-	1.53	58	No	Yes
baidu/ERNIE-4.5-VL-424B-A47B-Base-PT ERNIE-4.5-VL-424B-A47B-Base-PT	novita	0.336	1	123000	1.10	44	No	No
baidu/ERNIE-4.5-21B-A3B-PT ERNIE-4.5-21B-A3B-PT	novita	0.056	0.224	120000	0.85	74	No	No
baidu/ERNIE-4.5-VL-28B-A3B-PT ERNIE-4.5-VL-28B-A3B-PT	novita	0.112	0.448	30000	0.83	72	No	No
baidu/ERNIE-4.5-300B-A47B-Base-PT ERNIE-4.5-300B-A47B-Base-PT	novita	0.224	0.88	123000	0.87	28	No	Yes
MiniMaxAI/MiniMax-M1-80k MiniMax-M1-80k	novita	0.44	1.76	1000000	1.45	61	Yes	No
deepseek-ai/DeepSeek-Prover-V2-671B DeepSeek-Prover-V2-671B	novita	0.56	2	160000	0.90	22	No	No
zai-org/GLM-4-32B-0414 GLM-4-32B-0414	novita	0.55	1.66	32000	1.13	37	No	Yes
Sao10K/L3-8B-Lunaris-v1 L3-8B-Lunaris-v1	novita	0.05	0.05	8192	0.77	73	No	No

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

novita

cheapest

0.48

2

262144

1.01

24

Yes

No

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

nebius

0.6

2.5

262144

0.34

83

Yes

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

together

fastest

1.2

4

262144

0.78

110

Yes

deepseek-ai/DeepSeek-OCR DeepSeek-OCR

novita

0.024

8192

0.65

196

No

Yes

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

novita

cheapest

0.02

0.05

16384

0.64

84

No

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

nebius

0.03

0.09

131072

0.35

194

No

Yes

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

cerebras

fastest

0.1

-

0.26

1243

No

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

sambanova

0.1

0.2

16384

0.38

733

Yes

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

nscale

0.06

131072

0.94

58

No

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

fireworks-ai

-

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

scaleway

-

0.38

74

Yes

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

ovhcloud

-

0.40

42

Yes

No

allenai/Olmo-3-32B-Think Olmo-3-32B-Think

publicai

-

2.83

41

No

Yes

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

publicai

-

1.78

36

No

allenai/Olmo-3-7B-Think Olmo-3-7B-Think

publicai

-

2.84

106

No

Yes

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

groq

fastest

0.1

0.5

131072

0.15

844

Yes

No

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

novita

0.032

0.12

131072

0.90

169

No

Yes

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

nebius

0.05

0.2

131072

0.31

157

Yes

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

nscale

0.05

0.2

131072

0.95

58

Yes

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

hyperbolic

cheapest

0.1

131072

0.58

148

No

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

together

0.05

0.2

131072

0.26

162

Yes

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

fireworks-ai

0.05

0.2

131072

0.59

151

Yes

No

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

ovhcloud

-

0.30

78

Yes

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

novita

0.064

0.4

131072

0.75

69

Yes

No

zai-org/GLM-4.6 GLM-4.6

novita

cheapest

0.44

1.76

204800

1.04

60

Yes

No

zai-org/GLM-4.6 GLM-4.6

cerebras

fastest

-

0.23

398

Yes

No

zai-org/GLM-4.6 GLM-4.6

zai-org

-

2.67

52

Yes

No

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

groq

0.15

0.75

131072

0.17

427

Yes

No

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

novita

cheapest

0.04

0.2

131072

0.84

127

No

Yes

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

nebius

0.15

0.6

131072

0.58

31

Yes

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

cerebras

fastest

0.25

0.69

-

0.25

715

Yes

No

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

sambanova

0.22

0.59

131072

0.43

508

No

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

nscale

0.1

0.4

131072

0.74

91

Yes

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

hyperbolic

0.3

131072

0.70

271

Yes

No

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

together

0.15

0.6

131072

0.31

144

Yes

No

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

fireworks-ai

0.15

0.6

131072

0.44

112

Yes

No

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

scaleway

-

0.55

112

Yes

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

ovhcloud

-

0.37

115

Yes

MiniMaxAI/MiniMax-M2 MiniMax-M2

novita

0.3

1.2

204800

0.90

69

No

meta-llama/Llama-3.2-3B-Instruct Llama-3.2-3B-Instruct

novita

cheapest

0.024

0.04

32768

0.80

115

Yes

No

meta-llama/Llama-3.2-3B-Instruct Llama-3.2-3B-Instruct

sambanova

-

meta-llama/Llama-3.2-3B-Instruct Llama-3.2-3B-Instruct

hyperbolic

0.1

131072

0.60

128

No

meta-llama/Llama-3.2-3B-Instruct Llama-3.2-3B-Instruct

together

fastest

0.06

131072

0.25

153

Yes

No

PrimeIntellect/INTELLECT-3-FP8 INTELLECT-3-FP8

nebius

0.2

1.1

131072

0.48

39

Yes

No

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

novita

0.16

0.56

131072

0.70

95

Yes

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

together

0.3

32768

0.22

138

Yes

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

novita

0.216

0.328

163840

0.77

32

Yes

deepseek-ai/DeepSeek-R1 DeepSeek-R1

novita

cheapest

0.56

2

64000

0.73

25

Yes

No

deepseek-ai/DeepSeek-R1 DeepSeek-R1

sambanova

fastest

-

0.81

197

Yes

deepseek-ai/DeepSeek-R1 DeepSeek-R1

hyperbolic

2

163840

0.68

47

No

deepseek-ai/DeepSeek-R1 DeepSeek-R1

together

3

7

163840

0.47

53

No

Yes

deepseek-ai/DeepSeek-R1 DeepSeek-R1

fireworks-ai

-

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

nscale

0.01

0.03

262144

0.80

91

Yes

No

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

novita

0.12

1.2

131072

0.73

139

Yes

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

hyperbolic

cheapest

0.3

262144

0.55

148

Yes

No

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

together

fastest

0.15

1.5

262144

0.65

150

Yes

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

nebius

cheapest fastest

0.1

0.3

262144

0.30

131

Yes

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

fireworks-ai

-

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

scaleway

-

0.40

82

Yes

No

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

ovhcloud

-

0.45

107

Yes

Qwen/Qwen3-8B Qwen3-8B

nscale

0.07

0.18

40960

0.85

57

Yes

No

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

nebius

cheapest fastest

0.2

0.6

110000

0.43

77

No

Yes

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

scaleway

-

0.62

43

Yes

No

nvidia/NVIDIA-Nemotron-Nano-12B-v2 NVIDIA-Nemotron-Nano-12B-v2

nebius

0.07

0.2

131072

0.31

125

No

Yes

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

groq

-

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

novita

0.032

8192

0.70

84

No

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

together

-

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

novita

-

131000

0.66

206

No

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

sambanova

-

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

novita

cheapest

0.456

1.84

131072

0.93

32

Yes

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

nebius

fastest

0.5

2.4

131072

0.42

62

Yes

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

together

1

3

131072

0.64

47

Yes

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

fireworks-ai

-

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

hyperbolic

0.2

32768

0.47

32

No

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

groq

0.59

0.79

131072

0.14

276

Yes

No

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

novita

cheapest

0.104

0.312

131072

0.65

41

Yes

No

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

nebius

0.25

0.75

131072

0.37

137

Yes

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

cerebras

fastest

0.85

1.2

-

0.26

1105

Yes

No

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

sambanova

0.6

1.2

131072

0.37

366

No

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

nscale

0.4

131072

0.93

17

No

Yes

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

hyperbolic

0.4

131072

0.71

119

No

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

together

0.88

131072

0.46

136

Yes

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

fireworks-ai

0.9

131072

0.79

146

No

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

scaleway

-

0.59

35

Yes

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

ovhcloud

-

1.31

30

Yes

Qwen/Qwen3-32B Qwen3-32B

groq

fastest

0.29

0.59

131072

0.19

289

Yes

No

Qwen/Qwen3-32B Qwen3-32B

novita

0.08

0.36

40960

0.73

49

No

Qwen/Qwen3-32B Qwen3-32B

nebius

0.1

0.3

40960

0.33

46

Yes

Qwen/Qwen3-32B Qwen3-32B

cerebras

0.4

0.8

-

0.24

130

No

Qwen/Qwen3-32B Qwen3-32B

sambanova

0.4

0.8

32768

1.84

232

Yes

Qwen/Qwen3-32B Qwen3-32B

nscale

cheapest

0.08

0.25

40960

0.91

25

Yes

Qwen/Qwen3-32B Qwen3-32B

ovhcloud

-

0.43

41

Yes

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

nscale

0.01

0.03

262144

0.96

89

Yes

No

deepseek-ai/DeepSeek-R1-0528-Qwen3-8B DeepSeek-R1-0528-Qwen3-8B

novita

0.048

0.072

128000

0.67

81

No

HuggingFaceTB/SmolLM3-3B SmolLM3-3B

hf-inference

-

0.16

87

Yes

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

novita

cheapest

0.072

0.464

131072

1.10

22

Yes

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

nebius

0.2

0.6

262144

0.45

78

Yes

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

cerebras

fastest

0.6

1.2

-

0.29

503

Yes

No

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

nscale

0.2

0.6

32768

0.96

24

Yes

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

hyperbolic

2

262144

1.15

44

Yes

No

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

together

0.2

0.6

262144

0.39

42

Yes

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

fireworks-ai

0.22

0.88

262144

0.82

55

Yes

No

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

scaleway

-

0.47

82

Yes

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

groq

fastest

-

262144

0.19

179

Yes

No

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

novita

cheapest

0.48

2

262144

0.55

37

Yes

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

together

1

3

262144

0.62

49

Yes

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

novita

cheapest fastest

0.104

0.68

131072

0.60

63

Yes

No

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

nebius

0.2

1.2

131072

0.42

21

Yes

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

fireworks-ai

-

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

zai-org

-

2.69

63

Yes

No

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

novita

0.24

1.2

131072

0.88

41

Yes

No

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

nscale

0.1

131072

0.77

139

No

baichuan-inc/Baichuan-M2-32B Baichuan-M2-32B

novita

0.056

131072

2.02

34

No

Yes

Qwen/Qwen3-30B-A3B-Instruct-2507 Qwen3-30B-A3B-Instruct-2507

nebius

0.1

0.3

262144

0.37

106

Yes

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

novita

0.12

1.2

131072

0.73

140

Yes

No

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

hyperbolic

cheapest

0.3

262144

0.54

185

Yes

No

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

together

fastest

0.15

1.5

262144

0.48

202

Yes

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

novita

0.784

3.16

131072

1.22

33

No

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

novita

0.216

0.8

131072

1.10

31

Yes

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

novita

cheapest

0.29

1.2

262144

0.94

46

Yes

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

nebius

fastest

0.4

1.8

262144

0.39

58

Yes

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

cerebras

-

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

hyperbolic

2

262144

1.66

55

Yes

No

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

together

2

262144

0.53

51

Yes

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

fireworks-ai

0.45

1.8

262144

0.65

37

Yes

No

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

novita

cheapest

0.072

0.36

40960

0.89

124

No

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

fireworks-ai

fastest

0.15

0.6

131072

0.53

164

Yes

No

zai-org/GLM-4.5 GLM-4.5

novita

cheapest

0.48

1.76

131072

0.62

56

Yes

No

zai-org/GLM-4.5 GLM-4.5

nebius

0.6

2.2

131072

0.45

38

Yes

zai-org/GLM-4.5 GLM-4.5

fireworks-ai

fastest

0.55

2.19

131072

0.81

89

Yes

No

zai-org/GLM-4.5 GLM-4.5

zai-org

-

3.01

52

Yes

No

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

novita

cheapest fastest

0.12

32768

0.82

59

No

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

nscale

0.2

131072

0.84

37

No

Yes

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

nebius

0.25

0.75

32000

0.28

30

No

Yes

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

hyperbolic

cheapest fastest

0.6

32768

0.49

39

No

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

ovhcloud

-

0.55

25

No

Yes

google/gemma-2-2b-it gemma-2-2b-it

nebius

0.02

0.06

8192

0.31

180

No

Yes

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

nscale

0.01

0.03

131072

0.76

61

No

Yes

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

groq

fastest

0.11

0.34

131072

0.29

342

Yes

No

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

novita

0.08

0.4

131072

0.33

44

No

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

sambanova

-

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

nscale

cheapest

0.09

0.29

890000

0.77

33

Yes

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

together

0.18

0.59

1048576

0.29

90

Yes

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

fireworks-ai

-

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

nscale

0.01

0.03

32768

0.80

80

No

Yes

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

novita

cheapest

0.216

0.8

131072

0.93

32

Yes

No

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

together

0.6

1.7

131072

1.23

64

Yes

No

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

fireworks-ai

fastest

-

163840

0.88

83

Yes

No

Qwen/Qwen3-14B Qwen3-14B

nscale

0.07

0.2

40960

0.93

47

Yes

No

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

nscale

0.15

131072

0.85

66

No

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

novita

cheapest

0.304

0.32

32000

2.15

27

Yes

No

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

hyperbolic

0.4

131072

1.35

49

Yes

No

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

together

fastest

1.2

131072

0.32

84

Yes

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

fireworks-ai

-

Qwen/Qwen3-30B-A3B-Thinking-2507 Qwen3-30B-A3B-Thinking-2507

nebius

0.1

0.3

262144

0.35

105

Yes

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

zai-org

-

2.39

64

No

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

groq

-

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

novita

0.51

0.74

8192

0.80

29

No

Yes

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

hyperbolic

cheapest

0.4

8192

0.62

103

No

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

together

fastest

0.88

8192

0.36

108

No

Yes

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

novita

-

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

nscale

0.05

131072

0.87

57

No

Yes

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

novita

cheapest

0.24

64000

0.76

23

No

Yes

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

nscale

fastest

0.3

131072

0.90

25

No

Yes

Qwen/QwQ-32B QwQ-32B

groq

-

Qwen/QwQ-32B QwQ-32B

nebius

-

Qwen/QwQ-32B QwQ-32B

sambanova

-

Qwen/QwQ-32B QwQ-32B

nscale

cheapest fastest

0.18

0.2

131072

0.94

27

Yes

Qwen/QwQ-32B QwQ-32B

hyperbolic

0.4

131072

2.29

18

Yes

No

Qwen/QwQ-32B QwQ-32B

fireworks-ai

-

zai-org/GLM-4.5-Air-FP8 GLM-4.5-Air-FP8

together

0.2

1.1

131072

0.35

113

Yes

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

hf-inference

-

0.13

70

No

Yes

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

groq

-

131072

0.13

851

Yes

No

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

novita

cheapest fastest

0.48

1.44

65536

0.82

76

Yes

No

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

zai-org

-

3.36

46

Yes

No

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

together

cheapest fastest

1.25

163840

0.23

73

No

Yes

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

fireworks-ai

-

163840

1.14

23

Yes

No

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

publicai

-

2.61

41

Yes

NousResearch/Hermes-4-405B Hermes-4-405B

nebius

1

3

131072

0.43

37

No

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

novita

1.48

8192

0.76

40

No

marin-community/marin-8b-instruct marin-8b-instruct

together

0.18

4096

0.24

178

No

Yes

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

novita

0.496

65535

0.43

46

No

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

novita

0.05

8192

0.69

62

No

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

novita

0.16

0.8

131072

0.70

89

Yes

deepseek-ai/DeepSeek-V3 DeepSeek-V3

novita

cheapest

0.32

1.04

64000

1.41

28

Yes

No

deepseek-ai/DeepSeek-V3 DeepSeek-V3

together

fastest

1.25

131072

0.61

29

Yes

deepseek-ai/DeepSeek-V3 DeepSeek-V3

fireworks-ai

-

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

together

1.25

163840

0.25

72

No

Yes

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

fireworks-ai

0.22

0.88

128000

0.39

60

No

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

novita

0.16

0.64

40960

1.11

37

No

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

nscale

cheapest

0.2

0.6

32000

1.07

23

Yes

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

together

0.2

0.6

40960

0.43

46

Yes

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

fireworks-ai

fastest

0.22

0.88

131072

0.58

64

Yes

No

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

nscale

cheapest

0.06

0.2

131072

0.92

28

No

Yes

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

hyperbolic

0.2

32768

1.26

47

No

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

together

-

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

scaleway

fastest

-

0.45

96

Yes

No

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

groq

cheapest fastest

0.2

0.6

131072

0.21

474

Yes

No

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

sambanova

-

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

fireworks-ai

0.22

0.88

1048576

0.40

87

Yes

No

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

novita

cheapest

0.216

0.896

163840

1.10

31

Yes

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

nebius

0.75

2.25

32768

0.93

117

No

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

sambanova

fastest

3

4.5

131072

0.98

133

No

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

hyperbolic

1.25

163840

0.77

50

No

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

together

1.25

131072

0.95

34

Yes

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

fireworks-ai

0.9

163840

0.97

55

Yes

No

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

nscale

cheapest

1.2

65536

0.88

25

No

Yes

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

together

-

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

fireworks-ai

fastest

1.2

65536

0.34

69

No

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

nebius

0.03

0.09

32768

0.44

173

No

Yes

google/gemma-2-9b-it gemma-2-9b-it

groq

-

google/gemma-2-9b-it gemma-2-9b-it

nebius

0.03

0.09

8192

0.29

136

No

Yes

baidu/ERNIE-4.5-0.3B-PT ERNIE-4.5-0.3B-PT

novita

-

120000

1.20

102

No

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

novita

0.14

8192

0.78

97

No

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

publicai

-

1.34

80

No

Yes

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

publicai

-

1.81

48

No

Yes

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

novita

cheapest

0.136

0.68

1048576

0.46

35

No

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

together

fastest

0.27

0.85

1048576

0.35

90

Yes

deepcogito/cogito-v2-preview-llama-70B cogito-v2-preview-llama-70B

together

0.88

32768

1.61

50

Yes

Qwen/Qwen3-235B-A22B-FP8 Qwen3-235B-A22B-FP8

together

0.2

0.6

40960

0.44

41

Yes

deepcogito/cogito-v2-preview-llama-109B-MoE cogito-v2-preview-llama-109B-MoE

together

0.18

0.59

32767

0.69

85

Yes

deepcogito/cogito-v2-preview-llama-405B cogito-v2-preview-llama-405B

together

3.5

32768

0.83

26

Yes

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

zai-org

-

3.14

44

Yes

No

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

novita

cheapest

0.56

2

163840

0.68

27

Yes

No

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

nebius

0.8

2.4

163840

0.51

17

Yes

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

sambanova

fastest

5

7

131072

1.29

182

No

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

hyperbolic

3

163840

0.69

50

No

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

together

3

7

163840

0.49

53

No

Yes

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

fireworks-ai

3

8

163840

0.87

37

Yes

No

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

together

2

262144

0.53

52

Yes

SentientAGI/Dobby-Unhinged-Llama-3.3-70B Dobby-Unhinged-Llama-3.3-70B

fireworks-ai

0.9

131072

0.37

50

No

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

novita

0.24

2.4

131072

0.38

37

Yes

No

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

nebius

cheapest

0.2

0.8

262144

0.48

30

Yes

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

cerebras

-

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

fireworks-ai

fastest

0.22

0.88

262144

0.75

66

Yes

No

NousResearch/Hermes-4-70B Hermes-4-70B

nebius

0.13

0.4

131072

0.28

76

No

nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 Llama-3_1-Nemotron-Ultra-253B-v1

nebius

0.6

1.8

131072

0.45

39

No

Yes

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

groq

0.2

131072

0.17

13

No

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

cohere

-

0.21

64

Yes

No

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

cohere

-

0.19

94

Yes

No

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

cohere

-

0.23

40

No

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

cohere

-

0.37

56

No

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

cohere

-

0.21

39

No

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

cohere

-

0.24

57

Yes

No

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

cohere

-

0.25

114

Yes

No

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

cohere

-

0.27

54

Yes

No

zai-org/GLM-4.1V-9B-Thinking GLM-4.1V-9B-Thinking

novita

0.028

0.11

65536

0.78

70

No

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

groq

-

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

novita

cheapest

0.64

8192

1.21

31

No

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

sambanova

fastest

0.7

1.4

131072

2.47

168

No

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

nscale

0.75

131072

0.89

16

No

Yes

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

scaleway

-

0.57

24

No

Yes

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

ovhcloud

-

0.45

30

No

Yes

tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4 Llama-3.3-Swallow-70B-Instruct-v0.4

sambanova

0.6

1.2

131072

2.13

163

No

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

publicai

-

1.53

58

No

Yes

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

novita

0.336

1

123000

1.10

44

No

baidu/ERNIE-4.5-21B-A3B-PT ERNIE-4.5-21B-A3B-PT

novita

0.056

0.224

120000

0.85

74

No

baidu/ERNIE-4.5-VL-28B-A3B-PT ERNIE-4.5-VL-28B-A3B-PT

novita

0.112

0.448

30000

0.83

72

No

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

novita

0.224

0.88

123000

0.87

28

No

Yes

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

novita

0.44

1.76

1000000

1.45

61

Yes

No

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

novita

0.56

2

160000

0.90

22

No

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

novita

0.55

1.66

32000

1.13

37

No

Yes

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

novita

0.05

8192

0.77

73

No