Hugging Face Inference Providers


deepseek-ai/DeepSeek-V4.1-Flash-1017 DeepSeek-V4.1-Flash-1017	novita cheapest	$0.30	$1.20	1,048,576	1.05	110	Yes	No
deepseek-ai/DeepSeek-V4.1-Flash-1017 DeepSeek-V4.1-Flash-1017	together fastest	$0.30	$1.20	1,048,576	0.14	307	Yes	No
deepseek-ai/DeepSeek-V4.1-Flash-1017 DeepSeek-V4.1-Flash-1017	baseten	$0.30	$1.20	1,048,576	4.51	138	Yes	Yes
Qwen/Qwen3.8-27B Qwen3.8-27B	novita	$0.42	$3.00	1,000,000	1.50	31	Yes	No
Qwen/Qwen3.8-27B Qwen3.8-27B	cerebras cheapest fastest	$0.99	$1.49	65,536	0.18	867	Yes	Yes
Qwen/Qwen3.8-27B Qwen3.8-27B	ovhcloud	$0.47	$3.19	262,144	0.43	67	Yes	Yes
Qwen/Qwen3.8-27B Qwen3.8-27B	deepinfra	$0.20	$2.50	262,144	0.33	27	Yes	Yes
meta-models/Muse-Spark-Open-816B-A42B Muse-Spark-Open-816B-A42B	baseten	$1.25	$4.25	1,048,576	0.31	105	Yes	Yes
reflection/Beam-1.0-501B-A23B Beam-1.0-501B-A23B	baseten	$0.40	$1.20	1,048,576	0.23	336	Yes	Yes
deepseek-ai/DeepSeek-V4.1-Flash DeepSeek-V4.1-Flash	novita	$0.30	$1.20	1,048,576	1.10	83	Yes	No
deepseek-ai/DeepSeek-V4.1-Flash DeepSeek-V4.1-Flash	together fastest	$0.30	$1.20	1,048,576	0.14	262	Yes	No
deepseek-ai/DeepSeek-V4.1-Flash DeepSeek-V4.1-Flash	fireworks-ai	-	-	1,048,576	0.79	91	Yes	Yes
deepseek-ai/DeepSeek-V4.1-Flash DeepSeek-V4.1-Flash	baseten	$0.30	$1.20	1,048,576	1.35	184	Yes	Yes
deepseek-ai/DeepSeek-V4.1-Flash DeepSeek-V4.1-Flash	deepinfra cheapest	$0.20	$0.60	1,048,576	0.99	76	Yes	Yes
nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4	together cheapest	$0.15	$0.50	262,144	0.15	318	Yes	No
nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4	baseten fastest	$0.20	$0.50	1,048,576	0.25	355	Yes	Yes
meta-models/Muse-Spark-Open-816B-A42B-NVFP4 Muse-Spark-Open-816B-A42B-NVFP4	together	$1.25	$4.25	1,048,576	0.14	162	Yes	No
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	novita cheapest fastest	$0.02	$0.05	16,384	0.44	181	No	No
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	nscale	$0.06	$0.06	131,072	0.42	157	No	No
meta-llama/Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct	deepinfra	$0.02	$0.05	131,072	0.45	27	Yes	No
zai-org/GLM-5.3-Flash GLM-5.3-Flash	novita cheapest	$0.15	$0.50	1,048,576	3.10	48	Yes	Yes
zai-org/GLM-5.3-Flash GLM-5.3-Flash	together fastest	$0.15	$0.50	1,048,575	0.26	159	Yes	No
zai-org/GLM-5.3-Flash GLM-5.3-Flash	fireworks-ai	-	-	1,048,576	0.60	109	Yes	Yes
zai-org/GLM-5.3-Flash GLM-5.3-Flash	zai-org	-	-	-	2.91	40	Yes	Yes
zai-org/GLM-5.3-Flash GLM-5.3-Flash	baseten	$0.15	$0.50	1,048,576	4.39	54	Yes	Yes
zai-org/GLM-5.3-Flash GLM-5.3-Flash	deepinfra	$0.15	$0.50	1,048,576	2.01	8	Yes	Yes
zai-org/GLM-5.3 GLM-5.3	novita	$1.40	$4.40	1,048,576	1.10	62	Yes	Yes
zai-org/GLM-5.3 GLM-5.3	together fastest	$1.40	$4.40	1,048,575	0.38	100	Yes	No
zai-org/GLM-5.3 GLM-5.3	fireworks-ai	-	-	1,048,576	0.72	29	Yes	Yes
zai-org/GLM-5.3 GLM-5.3	zai-org	-	-	-	2.66	46	Yes	Yes
zai-org/GLM-5.3 GLM-5.3	baseten	$1.40	$4.40	1,048,576	3.35	45	Yes	Yes
zai-org/GLM-5.3 GLM-5.3	deepinfra cheapest	$0.90	$4.00	1,048,576	0.78	60	Yes	Yes
moonshotai/Kimi-K3 Kimi-K3	together	$3.00	$15.00	1,048,576	0.54	34	Yes	No
moonshotai/Kimi-K3 Kimi-K3	fireworks-ai	$3.00	$15.00	1,048,576	0.85	29	Yes	Yes
moonshotai/Kimi-K3 Kimi-K3	baseten fastest	$3.00	$15.00	1,048,576	0.86	46	Yes	Yes
moonshotai/Kimi-K3 Kimi-K3	deepinfra cheapest	$2.85	$14.25	1,048,576	0.69	13	Yes	Yes
reflection/Beam-1.0-501B-A23B-NVFP4 Beam-1.0-501B-A23B-NVFP4	together	$0.40	$1.20	1,048,576	0.13	201	Yes	No
inclusionAI/Ling-3.1-flash Ling-3.1-flash	novita	$0.30	$0.90	262,144	1.12	68	Yes	No
google/gemma-4-31B-it gemma-4-31B-it	novita cheapest fastest	$0.14	$0.40	262,144	0.63	19	Yes	Yes
google/gemma-4-31B-it gemma-4-31B-it	deepinfra	$0.20	$0.40	262,144	0.40	17	Yes	Yes
meta-models/Muse-Glimmer-30B Muse-Glimmer-30B	together	$0.35	$1.50	131,072	0.24	91	Yes	Yes
meta-models/Muse-Glimmer-30B Muse-Glimmer-30B	deepinfra cheapest fastest	$0.30	$1.20	131,072	0.21	110	Yes	Yes
XiaomiMiMo/MiMo-V2.6-Pro-RL MiMo-V2.6-Pro-RL	novita	$0.44	$0.87	1,048,576	1.41	24	Yes	No
Qwen/Qwen3.5-9B Qwen3.5-9B	together fastest	$0.17	$0.25	262,144	0.35	80	Yes	Yes
Qwen/Qwen3.5-9B Qwen3.5-9B	ovhcloud	$0.12	$0.18	262,144	0.49	38	Yes	Yes
Qwen/Qwen3.5-9B Qwen3.5-9B	deepinfra cheapest	$0.10	$0.15	262,144	0.67	15	Yes	Yes
google/gemma-4-26B-A4B-it gemma-4-26B-A4B-it	novita	$0.13	$0.40	262,144	0.42	111	Yes	Yes
google/gemma-4-26B-A4B-it gemma-4-26B-A4B-it	scaleway fastest	$0.29	$0.57	-	0.35	163	Yes	Yes
google/gemma-4-26B-A4B-it gemma-4-26B-A4B-it	deepinfra cheapest	$0.07	$0.34	262,144	0.47	61	Yes	Yes
Qwen/Qwen3.6-35B-A3B Qwen3.6-35B-A3B	scaleway fastest	$0.29	$1.71	-	0.39	164	Yes	Yes
Qwen/Qwen3.6-35B-A3B Qwen3.6-35B-A3B	deepinfra cheapest	$0.10	$0.95	262,144	0.23	97	Yes	Yes
openai/gpt-oss-20b gpt-oss-20b	groq fastest	$0.10	$0.50	131,072	0.52	610	Yes	Yes
openai/gpt-oss-20b gpt-oss-20b	novita	-	-	-	-	-	-	-
openai/gpt-oss-20b gpt-oss-20b	nscale	$0.05	$0.20	131,072	0.37	167	Yes	Yes
openai/gpt-oss-20b gpt-oss-20b	ovhcloud	$0.05	$0.18	131,072	0.33	56	Yes	Yes
openai/gpt-oss-20b gpt-oss-20b	deepinfra cheapest	$0.03	$0.14	131,072	0.45	143	Yes	Yes
XiaomiMiMo/MiMo-V2.6-Flash-RL MiMo-V2.6-Flash-RL	novita	$0.14	$0.28	1,048,576	1.92	28	Yes	No
openai/gpt-oss-120b gpt-oss-120b	groq	$0.15	$0.75	131,072	0.34	413	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	novita	$0.05	$0.25	131,072	4.26	100	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	cerebras fastest	$0.35	$0.75	131,072	0.22	1,108	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	nscale	$0.10	$0.40	131,072	0.42	110	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	together	$0.15	$0.60	131,072	0.20	58	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	fireworks-ai	$0.15	$0.60	131,072	0.41	148	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	scaleway	$0.17	$0.68	-	0.64	59	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	baseten	$0.10	$0.50	128,072	0.19	176	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	ovhcloud	$0.09	$0.47	131,072	0.47	25	Yes	Yes
openai/gpt-oss-120b gpt-oss-120b	deepinfra cheapest	$0.04	$0.17	131,072	0.26	68	Yes	Yes
deepseek-ai/DeepSeek-V4-Pro DeepSeek-V4-Pro	novita	$1.60	$3.20	1,048,576	0.69	47	Yes	No
deepseek-ai/DeepSeek-V4-Pro DeepSeek-V4-Pro	baseten	-	-	-	-	-	-	-
deepseek-ai/DeepSeek-V4-Pro DeepSeek-V4-Pro	deepinfra cheapest fastest	$1.30	$2.60	1,048,576	0.46	75	Yes	Yes
Qwen/Qwen3-8B Qwen3-8B	nscale	$0.07	$0.18	40,960	0.30	121	Yes	No
deepseek-ai/DeepSeek-R1 DeepSeek-R1	novita	$0.70	$2.50	64,000	1.24	17	Yes	Yes
Qwen/Qwen3.8-2.4T-A95B Qwen3.8-2.4T-A95B	novita	$2.00	$6.00	1,000,000	1.30	36	Yes	No
Qwen/Qwen3.8-2.4T-A95B Qwen3.8-2.4T-A95B	together fastest	$2.00	$6.00	1,010,000	0.33	127	Yes	No
Qwen/Qwen3.8-2.4T-A95B Qwen3.8-2.4T-A95B	fireworks-ai	-	-	262,144	0.84	77	Yes	Yes
Qwen/Qwen3.8-2.4T-A95B Qwen3.8-2.4T-A95B	deepinfra cheapest	$2.00	$6.00	262,144	3.54	36	Yes	Yes
MiniMaxAI/MiniMax-M3 MiniMax-M3	novita cheapest	$0.30	$1.20	1,000,000	0.78	34	Yes	No
MiniMaxAI/MiniMax-M3 MiniMax-M3	together	$0.30	$1.20	524,288	0.34	61	Yes	No
MiniMaxAI/MiniMax-M3 MiniMax-M3	fireworks-ai fastest	$0.30	$1.20	512,000	0.78	84	Yes	Yes
MiniMaxAI/MiniMax-M3 MiniMax-M3	deepinfra	-	-	-	-	-	-	-
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp DeepSeek-V4-Flash-Vision-Exp	novita	-	-	-	-	-	-	-
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp DeepSeek-V4-Flash-Vision-Exp	deepinfra	$0.44	$1.32	1,048,576	0.48	93	Yes	Yes
deepseek-ai/DeepSeek-V4-Flash DeepSeek-V4-Flash	novita	-	-	-	-	-	-	-
deepseek-ai/DeepSeek-V4-Flash DeepSeek-V4-Flash	deepinfra	$0.09	$0.18	1,048,576	1.26	17	Yes	Yes
thinkingmachines/Inkling-Small Inkling-Small	baseten	-	-	-	-	-	-	-
thinkingmachines/Inkling-Small Inkling-Small	deepinfra	$0.45	$1.20	524,288	0.33	162	Yes	Yes
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	groq	-	-	-	-	-	-	-
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	novita cheapest	$0.14	$0.40	12,288	1.12	49	Yes	No
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	together	$1.04	$1.04	131,072	1.20	45	Yes	Yes
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	scaleway fastest	$1.03	$1.03	-	0.34	74	Yes	Yes
meta-llama/Llama-3.3-70B-Instruct Llama-3.3-70B-Instruct	ovhcloud	$0.74	$0.74	131,072	0.39	28	Yes	Yes
thinkingmachines/Inkling Inkling	together cheapest	$1.00	$4.05	524,288	0.21	108	Yes	Yes
thinkingmachines/Inkling Inkling	fireworks-ai	-	-	1,048,576	0.63	93	Yes	No
thinkingmachines/Inkling Inkling	baseten	-	-	-	-	-	-	-
thinkingmachines/Inkling Inkling	deepinfra fastest	$0.95	$4.05	524,288	0.36	159	Yes	Yes
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16	fireworks-ai	-	-	262,144	0.26	303	Yes	Yes
Qwen/Qwen3.5-35B-A3B Qwen3.5-35B-A3B	novita	$0.25	$2.00	262,144	1.13	63	Yes	No
Qwen/Qwen3.5-35B-A3B Qwen3.5-35B-A3B	deepinfra cheapest fastest	$0.14	$1.00	262,144	0.39	144	Yes	Yes
swiss-ai/Apertus-v1.5-70B Apertus-v1.5-70B	publicai	$0.82	$2.92	-	0.55	53	Yes	Yes
Qwen/Qwen3-14B Qwen3-14B	nscale cheapest fastest	$0.07	$0.20	40,960	0.42	110	Yes	Yes
Qwen/Qwen3-14B Qwen3-14B	deepinfra	$0.12	$0.24	40,960	0.21	100	Yes	Yes
zai-org/GLM-4.7-Flash GLM-4.7-Flash	novita cheapest fastest	$0.07	$0.40	200,000	1.36	61	Yes	No
zai-org/GLM-4.7-Flash GLM-4.7-Flash	zai-org	-	-	-	-	-	-	-
zai-org/GLM-4.7-Flash GLM-4.7-Flash	deepinfra	$0.06	$0.40	202,752	1.17	7	Yes	Yes
Qwen/Qwen3.5-27B Qwen3.5-27B	novita cheapest	$0.30	$2.40	262,144	1.83	63	Yes	No
Qwen/Qwen3.5-27B Qwen3.5-27B	deepinfra fastest	$0.26	$2.60	262,144	0.25	68	Yes	Yes
zai-org/GLM-5.2 GLM-5.2	novita	$1.40	$4.40	1,048,576	1.35	55	Yes	Yes
zai-org/GLM-5.2 GLM-5.2	together fastest	$1.40	$4.40	1,048,575	0.24	204	Yes	No
zai-org/GLM-5.2 GLM-5.2	zai-org	-	-	-	2.29	50	Yes	No
zai-org/GLM-5.2 GLM-5.2	scaleway	$2.05	$6.27	-	0.44	118	Yes	Yes
zai-org/GLM-5.2 GLM-5.2	baseten	$1.40	$4.40	1,048,576	0.52	83	Yes	Yes
zai-org/GLM-5.2 GLM-5.2	deepinfra cheapest	$0.75	$2.40	1,048,576	0.62	59	Yes	Yes
google/gemma-3-4b-it gemma-3-4b-it	deepinfra	$0.05	$0.10	131,072	0.34	85	Yes	Yes
Qwen/Qwen3-235B-A22B Qwen3-235B-A22B	novita	-	-	-	-	-	-	-
Qwen/Qwen3-235B-A22B Qwen3-235B-A22B	nscale	$0.20	$0.60	32,000	0.44	15	Yes	Yes
Qwen/Qwen2.5-Coder-7B-Instruct Qwen2.5-Coder-7B-Instruct	nscale	$0.01	$0.03	131,072	0.35	142	No	Yes
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B DeepSeek-R1-Distill-Qwen-7B	nscale	$0.15	$0.15	131,072	0.40	143	No	Yes
Qwen/Qwen2.5-Coder-32B-Instruct Qwen2.5-Coder-32B-Instruct	nscale	$0.06	$0.20	131,072	0.44	54	No	Yes
speakleash/Bielik-11B-v3.0-Instruct Bielik-11B-v3.0-Instruct	publicai	$0.40	$0.40	-	1.82	52	Yes	Yes
Qwen/Qwen3.6-27B Qwen3.6-27B	ovhcloud cheapest	$0.47	$3.19	262,144	4.68	43	Yes	Yes
Qwen/Qwen3.6-27B Qwen3.6-27B	deepinfra fastest	$0.32	$3.20	262,144	0.34	79	Yes	Yes
Qwen/Qwen3-4B-Instruct-2507 Qwen3-4B-Instruct-2507	nscale	$0.01	$0.03	262,144	0.42	140	Yes	No
prism-ml/Ternary-Bonsai-27B-gguf Ternary-Bonsai-27B-gguf	together	$0.00	$0.00	262,144	0.45	56	Yes	No
tencent/Hy4-preview Hy4-preview	novita cheapest fastest	$0.83	$2.50	1,000,000	2.56	42	Yes	Yes
tencent/Hy4-preview Hy4-preview	deepinfra	$0.83	$2.50	1,048,576	0.69	39	Yes	Yes
moonshotai/Kimi-K2.6 Kimi-K2.6	novita cheapest fastest	$0.80	$3.40	262,144	1.80	38	Yes	No
moonshotai/Kimi-K2.6 Kimi-K2.6	baseten	-	-	-	-	-	-	-
moonshotai/Kimi-K2.6 Kimi-K2.6	deepinfra	$0.75	$3.50	262,144	0.92	17	Yes	Yes
moonshotai/Kimi-K2.5 Kimi-K2.5	novita	$0.60	$3.00	262,144	1.55	53	Yes	Yes
moonshotai/Kimi-K2.5 Kimi-K2.5	deepinfra cheapest fastest	$0.45	$2.25	262,144	0.42	122	Yes	Yes
deepseek-ai/DeepSeek-V3.1-Terminus DeepSeek-V3.1-Terminus	novita	-	-	-	-	-	-	-
deepseek-ai/DeepSeek-V3.1-Terminus DeepSeek-V3.1-Terminus	deepinfra	$0.27	$0.95	163,840	0.36	37	Yes	Yes
deepseek-ai/DeepSeek-V4-Flash-0731 DeepSeek-V4-Flash-0731	novita	$0.44	$1.32	1,048,576	0.74	85	Yes	No
deepseek-ai/DeepSeek-V4-Flash-0731 DeepSeek-V4-Flash-0731	together	$0.14	$0.28	1,048,576	0.75	66	Yes	No
deepseek-ai/DeepSeek-V4-Flash-0731 DeepSeek-V4-Flash-0731	scaleway	-	-	-	0.79	61	Yes	Yes
deepseek-ai/DeepSeek-V4-Flash-0731 DeepSeek-V4-Flash-0731	baseten fastest	$0.13	$0.26	1,048,576	4.90	118	Yes	Yes
deepseek-ai/DeepSeek-V4-Flash-0731 DeepSeek-V4-Flash-0731	deepinfra cheapest	$0.06	$0.18	1,048,576	0.39	48	Yes	Yes
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4	fireworks-ai	$0.60	$2.40	262,144	0.56	60	Yes	Yes
Qwen/Qwen3-30B-A3B Qwen3-30B-A3B	novita	-	-	-	-	-	-	-
Qwen/Qwen3-30B-A3B Qwen3-30B-A3B	deepinfra	$0.12	$0.50	40,960	0.18	46	Yes	Yes
Qwen/Qwen3-VL-30B-A3B-Instruct Qwen3-VL-30B-A3B-Instruct	novita	$0.20	$0.70	131,072	0.87	24	Yes	Yes
Qwen/Qwen3-VL-30B-A3B-Instruct Qwen3-VL-30B-A3B-Instruct	deepinfra cheapest fastest	$0.15	$0.60	262,144	0.30	28	Yes	Yes
microsoft/phi-4 phi-4	deepinfra	$0.07	$0.14	16,384	0.43	98	No	Yes
Qwen/Qwen3.5-122B-A10B Qwen3.5-122B-A10B	novita fastest	$0.40	$3.20	262,144	1.15	126	Yes	No
Qwen/Qwen3.5-122B-A10B Qwen3.5-122B-A10B	deepinfra cheapest	$0.29	$2.40	262,144	0.23	45	Yes	Yes
stepfun-ai/Step-3.5-Flash Step-3.5-Flash	deepinfra	$0.10	$0.30	262,144	2.23	21	Yes	Yes
zai-org/GLM-5.1 GLM-5.1	zai-org	-	-	-	-	-	-	-
zai-org/GLM-5.1 GLM-5.1	deepinfra	$1.05	$3.50	202,752	0.65	22	Yes	Yes
moonshotai/Kimi-K2.7-Code Kimi-K2.7-Code	novita fastest	$0.95	$4.00	262,144	1.73	35	Yes	Yes
moonshotai/Kimi-K2.7-Code Kimi-K2.7-Code	baseten	-	-	-	-	-	-	-
moonshotai/Kimi-K2.7-Code Kimi-K2.7-Code	deepinfra cheapest	$0.68	$3.40	262,144	0.71	29	Yes	Yes
ibm-granite/granite-4.2-3b granite-4.2-3b	deepinfra	$0.03	$0.12	131,072	0.48	121	Yes	No
zai-org/GLM-4.6 GLM-4.6	novita	$0.55	$2.20	204,800	3.89	25	Yes	No
zai-org/GLM-4.6 GLM-4.6	zai-org	-	-	-	-	-	-	-
zai-org/GLM-4.6 GLM-4.6	deepinfra cheapest fastest	$0.50	$2.00	202,752	0.49	53	Yes	Yes
zai-org/GLM-4.7 GLM-4.7	novita fastest	$0.60	$2.20	204,800	4.32	24	Yes	No
zai-org/GLM-4.7 GLM-4.7	zai-org	-	-	-	-	-	-	-
zai-org/GLM-4.7 GLM-4.7	baseten	-	-	-	-	-	-	-
zai-org/GLM-4.7 GLM-4.7	deepinfra cheapest	$0.40	$1.75	202,752	0.48	17	Yes	Yes
ibm-granite/granite-4.2-8b granite-4.2-8b	deepinfra	$0.06	$0.25	131,072	0.22	125	Yes	No
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16	deepinfra	$1.00	$5.00	262,144	0.76	38	Yes	Yes
Qwen/Qwen3.5-397B-A17B Qwen3.5-397B-A17B	novita	$0.60	$3.60	262,144	1.39	60	Yes	No
Qwen/Qwen3.5-397B-A17B Qwen3.5-397B-A17B	scaleway fastest	$0.68	$4.10	-	0.52	100	Yes	Yes
Qwen/Qwen3.5-397B-A17B Qwen3.5-397B-A17B	ovhcloud	$0.71	$4.25	262,144	0.65	73	Yes	No
Qwen/Qwen3.5-397B-A17B Qwen3.5-397B-A17B	deepinfra cheapest	$0.45	$3.00	262,144	0.32	44	Yes	Yes
Qwen/Qwen3-VL-235B-A22B-Instruct Qwen3-VL-235B-A22B-Instruct	novita	-	-	-	-	-	-	-
Qwen/Qwen3-VL-235B-A22B-Instruct Qwen3-VL-235B-A22B-Instruct	deepinfra	$0.20	$0.88	262,144	0.52	15	Yes	Yes
tencent/Hy3 Hy3	deepinfra	$0.13	$0.53	262,144	1.26	26	No	Yes
google/gemma-3-12b-it gemma-3-12b-it	deepinfra	$0.05	$0.15	131,072	0.29	28	Yes	Yes
inclusionAI/Ling-3.0-flash Ling-3.0-flash	novita cheapest fastest	$0.06	$0.18	262,144	0.79	256	Yes	No
inclusionAI/Ling-3.0-flash Ling-3.0-flash	deepinfra	$0.06	$0.18	131,072	0.52	24	Yes	No
XiaomiMiMo/MiMo-V2.5-Pro MiMo-V2.5-Pro	novita	-	-	-	-	-	-	-
XiaomiMiMo/MiMo-V2.5-Pro MiMo-V2.5-Pro	deepinfra	$1.00	$3.00	1,048,576	1.08	15	Yes	Yes
google/gemma-3-27b-it gemma-3-27b-it	deepinfra	$0.08	$0.16	131,072	0.30	20	Yes	No
Sao10K/L3-8B-Stheno-v3.2 L3-8B-Stheno-v3.2	novita	$0.05	$0.05	8,192	0.52	109	No	No
Qwen/Qwen3-4B-Thinking-2507 Qwen3-4B-Thinking-2507	nscale	$0.01	$0.03	262,144	0.40	151	Yes	Yes
Qwen/Qwen3-Next-80B-A3B-Instruct Qwen3-Next-80B-A3B-Instruct	novita	-	-	-	-	-	-	-
Qwen/Qwen3-Next-80B-A3B-Instruct Qwen3-Next-80B-A3B-Instruct	deepinfra	$0.09	$1.10	262,144	0.53	104	Yes	Yes
MiniMaxAI/MiniMax-M2.7 MiniMax-M2.7	novita fastest	$0.30	$1.20	204,800	0.86	31	Yes	No
MiniMaxAI/MiniMax-M2.7 MiniMax-M2.7	deepinfra cheapest	$0.25	$1.00	196,608	0.64	22	Yes	Yes
mistralai/Mixtral-8x22B-Instruct-v0.1 Mixtral-8x22B-Instruct-v0.1	nscale	$1.20	$1.20	65,536	0.45	37	Yes	Yes
Qwen/Qwen3-32B Qwen3-32B	groq	-	-	-	-	-	-	-
Qwen/Qwen3-32B Qwen3-32B	novita	-	-	-	-	-	-	-
Qwen/Qwen3-32B Qwen3-32B	nscale cheapest fastest	$0.08	$0.25	40,960	0.33	42	Yes	Yes
Qwen/Qwen3-32B Qwen3-32B	deepinfra	$0.08	$0.28	40,960	0.29	23	Yes	Yes
MiniMaxAI/MiniMax-M2.5 MiniMax-M2.5	novita	$0.30	$1.20	204,800	0.92	29	Yes	No
Qwen/Qwen2.5-Coder-3B-Instruct Qwen2.5-Coder-3B-Instruct	nscale	$0.01	$0.03	32,768	0.35	180	No	Yes
Qwen/Qwen2.5-72B-Instruct Qwen2.5-72B-Instruct	novita	-	-	-	-	-	-	-
Qwen/Qwen2.5-72B-Instruct Qwen2.5-72B-Instruct	deepinfra	$0.36	$0.40	32,768	0.48	27	Yes	Yes
zai-org/GLM-5 GLM-5	novita	$1.00	$3.20	202,800	1.60	43	Yes	No
zai-org/GLM-5 GLM-5	zai-org fastest	-	-	-	3.91	57	Yes	No
zai-org/GLM-5 GLM-5	deepinfra cheapest	$0.60	$2.08	202,752	0.52	53	Yes	Yes
zai-org/GLM-5.3-BF16 GLM-5.3-BF16	zai-org	-	-	-	2.26	62	Yes	Yes
zai-org/GLM-5.3-Flash-BF16 GLM-5.3-Flash-BF16	zai-org	-	-	-	2.67	38	Yes	Yes
swiss-ai/Apertus-8B-Instruct-2509 Apertus-8B-Instruct-2509	publicai	$0.10	$0.20	-	0.98	119	No	Yes
Qwen/Qwen2.5-VL-72B-Instruct Qwen2.5-VL-72B-Instruct	ovhcloud	$1.01	$1.01	32,768	0.67	32	No	Yes
ibm-granite/granite-4.2-30b granite-4.2-30b	deepinfra	$0.16	$0.65	131,072	0.27	126	Yes	No
Qwen/Qwen3-235B-A22B-Thinking-2507 Qwen3-235B-A22B-Thinking-2507	novita	-	-	-	-	-	-	-
Qwen/Qwen3-235B-A22B-Thinking-2507 Qwen3-235B-A22B-Thinking-2507	deepinfra	$0.23	$2.30	262,144	0.29	62	Yes	Yes
deepseek-ai/DeepSeek-V3 DeepSeek-V3	novita	-	-	-	-	-	-	-
deepseek-ai/DeepSeek-V3 DeepSeek-V3	deepinfra	$0.32	$0.89	163,840	0.60	21	Yes	Yes
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	novita	-	-	-	-	-	-	-
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	nscale	$0.20	$0.60	32,768	0.52	15	Yes	Yes
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	scaleway fastest	$0.86	$2.57	-	3.92	26	Yes	Yes
Qwen/Qwen3-235B-A22B-Instruct-2507 Qwen3-235B-A22B-Instruct-2507	deepinfra cheapest	$0.09	$0.55	262,144	3.90	19	Yes	Yes
CohereLabs/tiny-aya-water tiny-aya-water	cohere	-	-	-	0.18	132	No	No
deepseek-ai/DeepSeek-V4-Pro-0813 DeepSeek-V4-Pro-0813	novita	$1.32	$3.96	1,048,576	1.07	48	Yes	No
deepseek-ai/DeepSeek-V4-Pro-0813 DeepSeek-V4-Pro-0813	together fastest	$1.32	$3.96	1,048,576	0.81	118	Yes	No
deepseek-ai/DeepSeek-V4-Pro-0813 DeepSeek-V4-Pro-0813	baseten	$1.32	$3.96	1,048,576	0.67	81	Yes	No
deepseek-ai/DeepSeek-V4-Pro-0813 DeepSeek-V4-Pro-0813	deepinfra cheapest	$1.30	$2.60	1,048,576	0.37	45	Yes	Yes
prism-ml/Ternary-Bonsai-27B-AWQ-4bit Ternary-Bonsai-27B-AWQ-4bit	together	$0.00	$0.00	262,144	0.30	76	Yes	No
stepfun-ai/Step-3.7-Flash Step-3.7-Flash	deepinfra	$0.20	$1.15	262,144	3.79	17	Yes	Yes
CohereLabs/c4ai-command-r7b-12-2024 c4ai-command-r7b-12-2024	cohere	-	-	-	0.19	75	Yes	Yes
inclusionAI/Ling-3.0-flash-Fin Ling-3.0-flash-Fin	novita fastest	$0.08	$0.22	262,144	0.82	116	Yes	No
inclusionAI/Ling-3.0-flash-Fin Ling-3.0-flash-Fin	deepinfra cheapest	$0.06	$0.18	262,144	0.45	23	Yes	Yes
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B DeepSeek-R1-Distill-Qwen-14B	nscale	$0.20	$0.20	131,072	4.40	73	No	Yes
zai-org/GLM-4.5V GLM-4.5V	novita cheapest	$0.60	$1.80	65,536	1.26	49	Yes	No
zai-org/GLM-4.5V GLM-4.5V	zai-org fastest	-	-	-	1.84	65	Yes	No
zai-org/GLM-4.5-Air GLM-4.5-Air	novita cheapest fastest	$0.13	$0.85	131,072	1.03	76	Yes	No
zai-org/GLM-4.5-Air GLM-4.5-Air	zai-org	-	-	-	4.50	60	Yes	No
meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct	groq	-	-	-	-	-	-	-
meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct	novita	$0.18	$0.59	131,072	0.44	61	No	No
meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct	nscale cheapest fastest	$0.09	$0.29	890,000	0.43	69	Yes	Yes
meta-llama/Llama-4-Scout-17B-16E-Instruct Llama-4-Scout-17B-16E-Instruct	deepinfra	$0.10	$0.30	327,680	0.31	52	Yes	Yes
deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528	novita	$0.70	$2.50	163,840	1.53	20	Yes	Yes
deepseek-ai/DeepSeek-R1-0528 DeepSeek-R1-0528	deepinfra cheapest fastest	$0.50	$2.15	163,840	0.75	38	Yes	Yes
moonshotai/Kimi-K2-Instruct Kimi-K2-Instruct	novita	$0.57	$2.30	131,072	1.73	60	Yes	No
deepseek-ai/DeepSeek-R1-Distill-Llama-8B DeepSeek-R1-Distill-Llama-8B	nscale	$0.05	$0.05	131,072	0.44	136	No	Yes
togethercomputer/Tev1-4B-experimental Tev1-4B-experimental	together	$0.04	$0.00	32,768	0.19	34	Yes	No
meta-llama/Llama-Guard-4-12B Llama-Guard-4-12B	deepinfra	$0.18	$0.18	163,840	0.36	7	No	No
CohereLabs/c4ai-command-r7b-arabic-02-2025 c4ai-command-r7b-arabic-02-2025	cohere	-	-	-	0.18	135	Yes	No
zai-org/GLM-4.6V-FP8 GLM-4.6V-FP8	zai-org	-	-	-	3.39	27	Yes	No
zai-org/GLM-4.6V GLM-4.6V	zai-org	-	-	-	2.61	60	Yes	No
zai-org/GLM-4.6V-Flash GLM-4.6V-Flash	novita cheapest	$0.30	$0.90	131,072	0.99	71	Yes	No
zai-org/GLM-4.6V-Flash GLM-4.6V-Flash	zai-org fastest	-	-	-	1.48	91	Yes	No
zai-org/GLM-4.5V-FP8 GLM-4.5V-FP8	zai-org	-	-	-	2.28	54	Yes	No
CohereLabs/aya-vision-32b aya-vision-32b	cohere	-	-	-	0.18	42	No	No
CohereLabs/command-a-translate-08-2025 command-a-translate-08-2025	cohere	-	-	-	0.22	71	Yes	Yes
zai-org/GLM-5.2-FP8 GLM-5.2-FP8	zai-org	-	-	-	3.77	52	Yes	No
CohereLabs/aya-expanse-32b aya-expanse-32b	cohere	-	-	-	0.21	41	No	No
zai-org/GLM-5.1-FP8 GLM-5.1-FP8	zai-org	-	-	-	4.31	26	Yes	No
CohereLabs/command-a-reasoning-08-2025 command-a-reasoning-08-2025	cohere	-	-	-	0.22	50	Yes	Yes
CohereLabs/command-a-vision-07-2025 command-a-vision-07-2025	cohere	-	-	-	4.93	35	No	Yes
CohereLabs/c4ai-command-a-03-2025 c4ai-command-a-03-2025	cohere	-	-	-	0.30	32	Yes	No
CohereLabs/c4ai-command-r-08-2024 c4ai-command-r-08-2024	cohere	-	-	-	0.18	56	Yes	Yes
inclusionAI/Ling-3.0-flash-VL Ling-3.0-flash-VL	novita fastest	$0.08	$0.22	262,144	1.01	223	Yes	No
inclusionAI/Ling-3.0-flash-VL Ling-3.0-flash-VL	deepinfra cheapest	$0.06	$0.18	131,072	0.42	27	Yes	Yes
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 Llama-4-Maverick-17B-128E-Instruct-FP8	novita	$0.27	$0.85	1,048,576	0.41	62	No	Yes
alpindale/WizardLM-2-8x22B WizardLM-2-8x22B	novita	$0.62	$0.62	65,535	0.50	26	No	No
openai/gpt-oss-safeguard-20b gpt-oss-safeguard-20b	groq	-	-	131,072	0.28	794	Yes	Yes
MiniMaxAI/MiniMax-M1-80k MiniMax-M1-80k	novita	$0.55	$2.20	1,000,000	0.93	51	Yes	No
swiss-ai/Apertus-70B-Instruct-2509 Apertus-70B-Instruct-2509	publicai	$0.82	$2.92	-	1.68	14	Yes	Yes
CohereLabs/tiny-aya-earth tiny-aya-earth	cohere	-	-	-	0.16	134	No	No
CohereLabs/tiny-aya-fire tiny-aya-fire	cohere	-	-	-	0.16	134	No	No
XiaomiMiMo/MiMo-V2.5 MiMo-V2.5	novita	-	-	-	-	-	-	-
XiaomiMiMo/MiMo-V2.5 MiMo-V2.5	deepinfra	$0.14	$0.28	262,144	1.61	27	Yes	Yes
BSC-LT/ALIA-40b-instruct-2606 ALIA-40b-instruct-2606	publicai	$0.30	$0.60	65,536	1.89	19	Yes	Yes
aisingapore/Nemotron-SEA-LION-v4.8-120B-A12B Nemotron-SEA-LION-v4.8-120B-A12B	publicai	$0.50	$2.00	262,144	1.26	69	Yes	Yes
aisingapore/Qwen-SEA-LION-v4.5-27B-IT Qwen-SEA-LION-v4.5-27B-IT	publicai	$0.20	$0.40	262,144	0.98	54	Yes	Yes
aisingapore/Qwen-SEA-LION-v4-32B-IT Qwen-SEA-LION-v4-32B-IT	publicai	$0.25	$0.50	32,000	4.53	42	Yes	Yes
aisingapore/Gemma-SEA-LION-v4-27B-IT Gemma-SEA-LION-v4-27B-IT	publicai	$0.20	$0.40	131,072	1.30	56	No	Yes
CohereLabs/tiny-aya-global tiny-aya-global	cohere	-	-	-	0.16	134	No	No
NousResearch/Hermes-3-Llama-3.1-70B Hermes-3-Llama-3.1-70B	deepinfra	$0.70	$0.70	131,072	0.62	28	No	Yes
deepseek-ai/DeepSeek-V3.1 DeepSeek-V3.1	novita	-	-	-	-	-	-	-
deepseek-ai/DeepSeek-V3.1 DeepSeek-V3.1	deepinfra	$0.25	$0.95	163,840	3.75	9	Yes	Yes
deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324	novita	-	-	-	-	-	-	-
deepseek-ai/DeepSeek-V3-0324 DeepSeek-V3-0324	deepinfra	$0.24	$0.90	163,840	0.51	90	Yes	Yes
zai-org/AutoGLM-Phone-9B-Multilingual AutoGLM-Phone-9B-Multilingual	novita	$0.04	$0.14	65,536	0.45	101	No	No
moonshotai/Kimi-K2-Instruct-0905 Kimi-K2-Instruct-0905	novita	$0.60	$2.50	262,144	0.92	37	Yes	Yes

deepseek-ai/DeepSeek-V4.1-Flash-1017 DeepSeek-V4.1-Flash-1017

novita

cheapest

$0.30

$1.20

1,048,576

1.05

110

Yes

No

deepseek-ai/DeepSeek-V4.1-Flash-1017 DeepSeek-V4.1-Flash-1017

together

fastest

$0.30

$1.20

1,048,576

0.14

307

Yes

No

deepseek-ai/DeepSeek-V4.1-Flash-1017 DeepSeek-V4.1-Flash-1017

baseten

$0.30

$1.20

1,048,576

4.51

138

Yes

Qwen/Qwen3.8-27B Qwen3.8-27B

novita

$0.42

$3.00

1,000,000

1.50

31

Yes

No

Qwen/Qwen3.8-27B Qwen3.8-27B

cerebras

cheapest fastest

$0.99

$1.49

65,536

0.18

867

Yes

Qwen/Qwen3.8-27B Qwen3.8-27B

ovhcloud

$0.47

$3.19

262,144

0.43

67

Yes

Qwen/Qwen3.8-27B Qwen3.8-27B

deepinfra

$0.20

$2.50

262,144

0.33

27

Yes

meta-models/Muse-Spark-Open-816B-A42B Muse-Spark-Open-816B-A42B

baseten

$1.25

$4.25

1,048,576

0.31

105

Yes

reflection/Beam-1.0-501B-A23B Beam-1.0-501B-A23B

baseten

$0.40

$1.20

1,048,576

0.23

336

Yes

deepseek-ai/DeepSeek-V4.1-Flash DeepSeek-V4.1-Flash

novita

$0.30

$1.20

1,048,576

1.10

83

Yes

No

deepseek-ai/DeepSeek-V4.1-Flash DeepSeek-V4.1-Flash

together

fastest

$0.30

$1.20

1,048,576

0.14

262

Yes

No

deepseek-ai/DeepSeek-V4.1-Flash DeepSeek-V4.1-Flash

fireworks-ai

-

1,048,576

0.79

91

Yes

deepseek-ai/DeepSeek-V4.1-Flash DeepSeek-V4.1-Flash

baseten

$0.30

$1.20

1,048,576

1.35

184

Yes

deepseek-ai/DeepSeek-V4.1-Flash DeepSeek-V4.1-Flash

deepinfra

cheapest

$0.20

$0.60

1,048,576

0.99

76

Yes

nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4

together

cheapest

$0.15

$0.50

262,144

0.15

318

Yes

No

nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4

baseten

fastest

$0.20

$0.50

1,048,576

0.25

355

Yes

meta-models/Muse-Spark-Open-816B-A42B-NVFP4 Muse-Spark-Open-816B-A42B-NVFP4

together

$1.25

$4.25

1,048,576

0.14

162

Yes

No

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

novita

cheapest fastest

$0.02

$0.05

16,384

0.44

181

No

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

nscale

$0.06

131,072

0.42

157

No

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

deepinfra

$0.02

$0.05

131,072

0.45

27

Yes

No

zai-org/GLM-5.3-Flash GLM-5.3-Flash

novita

cheapest

$0.15

$0.50

1,048,576

3.10

48

Yes

zai-org/GLM-5.3-Flash GLM-5.3-Flash

together

fastest

$0.15

$0.50

1,048,575

0.26

159

Yes

No

zai-org/GLM-5.3-Flash GLM-5.3-Flash

fireworks-ai

-

1,048,576

0.60

109

Yes

zai-org/GLM-5.3-Flash GLM-5.3-Flash

zai-org

-

2.91

40

Yes

zai-org/GLM-5.3-Flash GLM-5.3-Flash

baseten

$0.15

$0.50

1,048,576

4.39

54

Yes

zai-org/GLM-5.3-Flash GLM-5.3-Flash

deepinfra

$0.15

$0.50

1,048,576

2.01

8

Yes

zai-org/GLM-5.3 GLM-5.3

novita

$1.40

$4.40

1,048,576

1.10

62

Yes

zai-org/GLM-5.3 GLM-5.3

together

fastest

$1.40

$4.40

1,048,575

0.38

100

Yes

No

zai-org/GLM-5.3 GLM-5.3

fireworks-ai

-

1,048,576

0.72

29

Yes

zai-org/GLM-5.3 GLM-5.3

zai-org

-

2.66

46

Yes

zai-org/GLM-5.3 GLM-5.3

baseten

$1.40

$4.40

1,048,576

3.35

45

Yes

zai-org/GLM-5.3 GLM-5.3

deepinfra

cheapest

$0.90

$4.00

1,048,576

0.78

60

Yes

moonshotai/Kimi-K3 Kimi-K3

together

$3.00

$15.00

1,048,576

0.54

34

Yes

No

moonshotai/Kimi-K3 Kimi-K3

fireworks-ai

$3.00

$15.00

1,048,576

0.85

29

Yes

moonshotai/Kimi-K3 Kimi-K3

baseten

fastest

$3.00

$15.00

1,048,576

0.86

46

Yes

moonshotai/Kimi-K3 Kimi-K3

deepinfra

cheapest

$2.85

$14.25

1,048,576

0.69

13

Yes

reflection/Beam-1.0-501B-A23B-NVFP4 Beam-1.0-501B-A23B-NVFP4

together

$0.40

$1.20

1,048,576

0.13

201

Yes

No

inclusionAI/Ling-3.1-flash Ling-3.1-flash

novita

$0.30

$0.90

262,144

1.12

68

Yes

No

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

novita

cheapest fastest

$0.14

$0.40

262,144

0.63

19

Yes

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

deepinfra

$0.20

$0.40

262,144

0.40

17

Yes

meta-models/Muse-Glimmer-30B Muse-Glimmer-30B

together

$0.35

$1.50

131,072

0.24

91

Yes

meta-models/Muse-Glimmer-30B Muse-Glimmer-30B

deepinfra

cheapest fastest

$0.30

$1.20

131,072

0.21

110

Yes

XiaomiMiMo/MiMo-V2.6-Pro-RL MiMo-V2.6-Pro-RL

novita

$0.44

$0.87

1,048,576

1.41

24

Yes

No

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

together

fastest

$0.17

$0.25

262,144

0.35

80

Yes

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

ovhcloud

$0.12

$0.18

262,144

0.49

38

Yes

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

deepinfra

cheapest

$0.10

$0.15

262,144

0.67

15

Yes

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

novita

$0.13

$0.40

262,144

0.42

111

Yes

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

scaleway

fastest

$0.29

$0.57

-

0.35

163

Yes

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

deepinfra

cheapest

$0.07

$0.34

262,144

0.47

61

Yes

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

scaleway

fastest

$0.29

$1.71

-

0.39

164

Yes

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

deepinfra

cheapest

$0.10

$0.95

262,144

0.23

97

Yes

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

groq

fastest

$0.10

$0.50

131,072

0.52

610

Yes

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

novita

-

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

nscale

$0.05

$0.20

131,072

0.37

167

Yes

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

ovhcloud

$0.05

$0.18

131,072

0.33

56

Yes

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

deepinfra

cheapest

$0.03

$0.14

131,072

0.45

143

Yes

XiaomiMiMo/MiMo-V2.6-Flash-RL MiMo-V2.6-Flash-RL

novita

$0.14

$0.28

1,048,576

1.92

28

Yes

No

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

groq

$0.15

$0.75

131,072

0.34

413

Yes

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

novita

$0.05

$0.25

131,072

4.26

100

Yes

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

cerebras

fastest

$0.35

$0.75

131,072

0.22

1,108

Yes

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

nscale

$0.10

$0.40

131,072

0.42

110

Yes

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

together

$0.15

$0.60

131,072

0.20

58

Yes

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

fireworks-ai

$0.15

$0.60

131,072

0.41

148

Yes

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

scaleway

$0.17

$0.68

-

0.64

59

Yes

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

baseten

$0.10

$0.50

128,072

0.19

176

Yes

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

ovhcloud

$0.09

$0.47

131,072

0.47

25

Yes

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

deepinfra

cheapest

$0.04

$0.17

131,072

0.26

68

Yes

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

novita

$1.60

$3.20

1,048,576

0.69

47

Yes

No

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

baseten

-

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

deepinfra

cheapest fastest

$1.30

$2.60

1,048,576

0.46

75

Yes

Qwen/Qwen3-8B Qwen3-8B

nscale

$0.07

$0.18

40,960

0.30

121

Yes

No

deepseek-ai/DeepSeek-R1 DeepSeek-R1

novita

$0.70

$2.50

64,000

1.24

17

Yes

Qwen/Qwen3.8-2.4T-A95B Qwen3.8-2.4T-A95B

novita

$2.00

$6.00

1,000,000

1.30

36

Yes

No

Qwen/Qwen3.8-2.4T-A95B Qwen3.8-2.4T-A95B

together

fastest

$2.00

$6.00

1,010,000

0.33

127

Yes

No

Qwen/Qwen3.8-2.4T-A95B Qwen3.8-2.4T-A95B

fireworks-ai

-

262,144

0.84

77

Yes

Qwen/Qwen3.8-2.4T-A95B Qwen3.8-2.4T-A95B

deepinfra

cheapest

$2.00

$6.00

262,144

3.54

36

Yes

MiniMaxAI/MiniMax-M3 MiniMax-M3

novita

cheapest

$0.30

$1.20

1,000,000

0.78

34

Yes

No

MiniMaxAI/MiniMax-M3 MiniMax-M3

together

$0.30

$1.20

524,288

0.34

61

Yes

No

MiniMaxAI/MiniMax-M3 MiniMax-M3

fireworks-ai

fastest

$0.30

$1.20

512,000

0.78

84

Yes

MiniMaxAI/MiniMax-M3 MiniMax-M3

deepinfra

-

deepseek-ai/DeepSeek-V4-Flash-Vision-Exp DeepSeek-V4-Flash-Vision-Exp

novita

-

deepseek-ai/DeepSeek-V4-Flash-Vision-Exp DeepSeek-V4-Flash-Vision-Exp

deepinfra

$0.44

$1.32

1,048,576

0.48

93

Yes

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

novita

-

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

deepinfra

$0.09

$0.18

1,048,576

1.26

17

Yes

thinkingmachines/Inkling-Small Inkling-Small

baseten

-

thinkingmachines/Inkling-Small Inkling-Small

deepinfra

$0.45

$1.20

524,288

0.33

162

Yes

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

groq

-

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

novita

cheapest

$0.14

$0.40

12,288

1.12

49

Yes

No

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

together

$1.04

131,072

1.20

45

Yes

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

scaleway

fastest

$1.03

-

0.34

74

Yes

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

ovhcloud

$0.74

131,072

0.39

28

Yes

thinkingmachines/Inkling Inkling

together

cheapest

$1.00

$4.05

524,288

0.21

108

Yes

thinkingmachines/Inkling Inkling

fireworks-ai

-

1,048,576

0.63

93

Yes

No

thinkingmachines/Inkling Inkling

baseten

-

thinkingmachines/Inkling Inkling

deepinfra

fastest

$0.95

$4.05

524,288

0.36

159

Yes

nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

fireworks-ai

-

262,144

0.26

303

Yes

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

novita

$0.25

$2.00

262,144

1.13

63

Yes

No

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

deepinfra

cheapest fastest

$0.14

$1.00

262,144

0.39

144

Yes

swiss-ai/Apertus-v1.5-70B Apertus-v1.5-70B

publicai

$0.82

$2.92

-

0.55

53

Yes

Qwen/Qwen3-14B Qwen3-14B

nscale

cheapest fastest

$0.07

$0.20

40,960

0.42

110

Yes

Qwen/Qwen3-14B Qwen3-14B

deepinfra

$0.12

$0.24

40,960

0.21

100

Yes

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

novita

cheapest fastest

$0.07

$0.40

200,000

1.36

61

Yes

No

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

zai-org

-

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

deepinfra

$0.06

$0.40

202,752

1.17

7

Yes

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

novita

cheapest

$0.30

$2.40

262,144

1.83

63

Yes

No

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

deepinfra

fastest

$0.26

$2.60

262,144

0.25

68

Yes

zai-org/GLM-5.2 GLM-5.2

novita

$1.40

$4.40

1,048,576

1.35

55

Yes

zai-org/GLM-5.2 GLM-5.2

together

fastest

$1.40

$4.40

1,048,575

0.24

204

Yes

No

zai-org/GLM-5.2 GLM-5.2

zai-org

-

2.29

50

Yes

No

zai-org/GLM-5.2 GLM-5.2

scaleway

$2.05

$6.27

-

0.44

118

Yes

zai-org/GLM-5.2 GLM-5.2

baseten

$1.40

$4.40

1,048,576

0.52

83

Yes

zai-org/GLM-5.2 GLM-5.2

deepinfra

cheapest

$0.75

$2.40

1,048,576

0.62

59

Yes

google/gemma-3-4b-it gemma-3-4b-it

deepinfra

$0.05

$0.10

131,072

0.34

85

Yes

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

novita

-

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

nscale

$0.20

$0.60

32,000

0.44

15

Yes

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

nscale

$0.01

$0.03

131,072

0.35

142

No

Yes

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

nscale

$0.15

131,072

0.40

143

No

Yes

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

nscale

$0.06

$0.20

131,072

0.44

54

No

Yes

speakleash/Bielik-11B-v3.0-Instruct Bielik-11B-v3.0-Instruct

publicai

$0.40

-

1.82

52

Yes

Qwen/Qwen3.6-27B Qwen3.6-27B

ovhcloud

cheapest

$0.47

$3.19

262,144

4.68

43

Yes

Qwen/Qwen3.6-27B Qwen3.6-27B

deepinfra

fastest

$0.32

$3.20

262,144

0.34

79

Yes

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

nscale

$0.01

$0.03

262,144

0.42

140

Yes

No

prism-ml/Ternary-Bonsai-27B-gguf Ternary-Bonsai-27B-gguf

together

$0.00

262,144

0.45

56

Yes

No

tencent/Hy4-preview Hy4-preview

novita

cheapest fastest

$0.83

$2.50

1,000,000

2.56

42

Yes

tencent/Hy4-preview Hy4-preview

deepinfra

$0.83

$2.50

1,048,576

0.69

39

Yes

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

novita

cheapest fastest

$0.80

$3.40

262,144

1.80

38

Yes

No

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

baseten

-

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

deepinfra

$0.75

$3.50

262,144

0.92

17

Yes

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

novita

$0.60

$3.00

262,144

1.55

53

Yes

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

deepinfra

cheapest fastest

$0.45

$2.25

262,144

0.42

122

Yes

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

novita

-

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

deepinfra

$0.27

$0.95

163,840

0.36

37

Yes

deepseek-ai/DeepSeek-V4-Flash-0731 DeepSeek-V4-Flash-0731

novita

$0.44

$1.32

1,048,576

0.74

85

Yes

No

deepseek-ai/DeepSeek-V4-Flash-0731 DeepSeek-V4-Flash-0731

together

$0.14

$0.28

1,048,576

0.75

66

Yes

No

deepseek-ai/DeepSeek-V4-Flash-0731 DeepSeek-V4-Flash-0731

scaleway

-

0.79

61

Yes

deepseek-ai/DeepSeek-V4-Flash-0731 DeepSeek-V4-Flash-0731

baseten

fastest

$0.13

$0.26

1,048,576

4.90

118

Yes

deepseek-ai/DeepSeek-V4-Flash-0731 DeepSeek-V4-Flash-0731

deepinfra

cheapest

$0.06

$0.18

1,048,576

0.39

48

Yes

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4

fireworks-ai

$0.60

$2.40

262,144

0.56

60

Yes

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

novita

-

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

deepinfra

$0.12

$0.50

40,960

0.18

46

Yes

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

novita

$0.20

$0.70

131,072

0.87

24

Yes

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

deepinfra

cheapest fastest

$0.15

$0.60

262,144

0.30

28

Yes

microsoft/phi-4 phi-4

deepinfra

$0.07

$0.14

16,384

0.43

98

No

Yes

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

novita

fastest

$0.40

$3.20

262,144

1.15

126

Yes

No

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

deepinfra

cheapest

$0.29

$2.40

262,144

0.23

45

Yes

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

deepinfra

$0.10

$0.30

262,144

2.23

21

Yes

zai-org/GLM-5.1 GLM-5.1

zai-org

-

zai-org/GLM-5.1 GLM-5.1

deepinfra

$1.05

$3.50

202,752

0.65

22

Yes

moonshotai/Kimi-K2.7-Code Kimi-K2.7-Code

novita

fastest

$0.95

$4.00

262,144

1.73

35

Yes

moonshotai/Kimi-K2.7-Code Kimi-K2.7-Code

baseten

-

moonshotai/Kimi-K2.7-Code Kimi-K2.7-Code

deepinfra

cheapest

$0.68

$3.40

262,144

0.71

29

Yes

ibm-granite/granite-4.2-3b granite-4.2-3b

deepinfra

$0.03

$0.12

131,072

0.48

121

Yes

No

zai-org/GLM-4.6 GLM-4.6

novita

$0.55

$2.20

204,800

3.89

25

Yes

No

zai-org/GLM-4.6 GLM-4.6

zai-org

-

zai-org/GLM-4.6 GLM-4.6

deepinfra

cheapest fastest

$0.50

$2.00

202,752

0.49

53

Yes

zai-org/GLM-4.7 GLM-4.7

novita

fastest

$0.60

$2.20

204,800

4.32

24

Yes

No

zai-org/GLM-4.7 GLM-4.7

zai-org

-

zai-org/GLM-4.7 GLM-4.7

baseten

-

zai-org/GLM-4.7 GLM-4.7

deepinfra

cheapest

$0.40

$1.75

202,752

0.48

17

Yes

ibm-granite/granite-4.2-8b granite-4.2-8b

deepinfra

$0.06

$0.25

131,072

0.22

125

Yes

No

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

deepinfra

$1.00

$5.00

262,144

0.76

38

Yes

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

novita

$0.60

$3.60

262,144

1.39

60

Yes

No

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

scaleway

fastest

$0.68

$4.10

-

0.52

100

Yes

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

ovhcloud

$0.71

$4.25

262,144

0.65

73

Yes

No

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

deepinfra

cheapest

$0.45

$3.00

262,144

0.32

44

Yes

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

novita

-

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

deepinfra

$0.20

$0.88

262,144

0.52

15

Yes

tencent/Hy3 Hy3

deepinfra

$0.13

$0.53

262,144

1.26

26

No

Yes

google/gemma-3-12b-it gemma-3-12b-it

deepinfra

$0.05

$0.15

131,072

0.29

28

Yes

inclusionAI/Ling-3.0-flash Ling-3.0-flash

novita

cheapest fastest

$0.06

$0.18

262,144

0.79

256

Yes

No

inclusionAI/Ling-3.0-flash Ling-3.0-flash

deepinfra

$0.06

$0.18

131,072

0.52

24

Yes

No

XiaomiMiMo/MiMo-V2.5-Pro MiMo-V2.5-Pro

novita

-

XiaomiMiMo/MiMo-V2.5-Pro MiMo-V2.5-Pro

deepinfra

$1.00

$3.00

1,048,576

1.08

15

Yes

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

deepinfra

$0.08

$0.16

131,072

0.30

20

Yes

No

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

novita

$0.05

8,192

0.52

109

No

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

nscale

$0.01

$0.03

262,144

0.40

151

Yes

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

novita

-

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

deepinfra

$0.09

$1.10

262,144

0.53

104

Yes

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

novita

fastest

$0.30

$1.20

204,800

0.86

31

Yes

No

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

deepinfra

cheapest

$0.25

$1.00

196,608

0.64

22

Yes

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

nscale

$1.20

65,536

0.45

37

Yes

Qwen/Qwen3-32B Qwen3-32B

groq

-

Qwen/Qwen3-32B Qwen3-32B

novita

-

Qwen/Qwen3-32B Qwen3-32B

nscale

cheapest fastest

$0.08

$0.25

40,960

0.33

42

Yes

Qwen/Qwen3-32B Qwen3-32B

deepinfra

$0.08

$0.28

40,960

0.29

23

Yes

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

novita

$0.30

$1.20

204,800

0.92

29

Yes

No

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

nscale

$0.01

$0.03

32,768

0.35

180

No

Yes

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

novita

-

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

deepinfra

$0.36

$0.40

32,768

0.48

27

Yes

zai-org/GLM-5 GLM-5

novita

$1.00

$3.20

202,800

1.60

43

Yes

No

zai-org/GLM-5 GLM-5

zai-org

fastest

-

3.91

57

Yes

No

zai-org/GLM-5 GLM-5

deepinfra

cheapest

$0.60

$2.08

202,752

0.52

53

Yes

zai-org/GLM-5.3-BF16 GLM-5.3-BF16

zai-org

-

2.26

62

Yes

zai-org/GLM-5.3-Flash-BF16 GLM-5.3-Flash-BF16

zai-org

-

2.67

38

Yes

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

publicai

$0.10

$0.20

-

0.98

119

No

Yes

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

ovhcloud

$1.01

32,768

0.67

32

No

Yes

ibm-granite/granite-4.2-30b granite-4.2-30b

deepinfra

$0.16

$0.65

131,072

0.27

126

Yes

No

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

novita

-

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

deepinfra

$0.23

$2.30

262,144

0.29

62

Yes

deepseek-ai/DeepSeek-V3 DeepSeek-V3

novita

-

deepseek-ai/DeepSeek-V3 DeepSeek-V3

deepinfra

$0.32

$0.89

163,840

0.60

21

Yes

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

novita

-

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

nscale

$0.20

$0.60

32,768

0.52

15

Yes

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

scaleway

fastest

$0.86

$2.57

-

3.92

26

Yes

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

deepinfra

cheapest

$0.09

$0.55

262,144

3.90

19

Yes

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

cohere

-

0.18

132

No

deepseek-ai/DeepSeek-V4-Pro-0813 DeepSeek-V4-Pro-0813

novita

$1.32

$3.96

1,048,576

1.07

48

Yes

No

deepseek-ai/DeepSeek-V4-Pro-0813 DeepSeek-V4-Pro-0813

together

fastest

$1.32

$3.96

1,048,576

0.81

118

Yes

No

deepseek-ai/DeepSeek-V4-Pro-0813 DeepSeek-V4-Pro-0813

baseten

$1.32

$3.96

1,048,576

0.67

81

Yes

No

deepseek-ai/DeepSeek-V4-Pro-0813 DeepSeek-V4-Pro-0813

deepinfra

cheapest

$1.30

$2.60

1,048,576

0.37

45

Yes

prism-ml/Ternary-Bonsai-27B-AWQ-4bit Ternary-Bonsai-27B-AWQ-4bit

together

$0.00

262,144

0.30

76

Yes

No

stepfun-ai/Step-3.7-Flash Step-3.7-Flash

deepinfra

$0.20

$1.15

262,144

3.79

17

Yes

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

cohere

-

0.19

75

Yes

inclusionAI/Ling-3.0-flash-Fin Ling-3.0-flash-Fin

novita

fastest

$0.08

$0.22

262,144

0.82

116

Yes

No

inclusionAI/Ling-3.0-flash-Fin Ling-3.0-flash-Fin

deepinfra

cheapest

$0.06

$0.18

262,144

0.45

23

Yes

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

nscale

$0.20

131,072

4.40

73

No

Yes

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

novita

cheapest

$0.60

$1.80

65,536

1.26

49

Yes

No

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

zai-org

fastest

-

1.84

65

Yes

No

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

novita

cheapest fastest

$0.13

$0.85

131,072

1.03

76

Yes

No

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

zai-org

-

4.50

60

Yes

No

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

groq

-

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

novita

$0.18

$0.59

131,072

0.44

61

No

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

nscale

cheapest fastest

$0.09

$0.29

890,000

0.43

69

Yes

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

deepinfra

$0.10

$0.30

327,680

0.31

52

Yes

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

novita

$0.70

$2.50

163,840

1.53

20

Yes

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

deepinfra

cheapest fastest

$0.50

$2.15

163,840

0.75

38

Yes

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

novita

$0.57

$2.30

131,072

1.73

60

Yes

No

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

nscale

$0.05

131,072

0.44

136

No

Yes

togethercomputer/Tev1-4B-experimental Tev1-4B-experimental

together

$0.04

$0.00

32,768

0.19

34

Yes

No

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

deepinfra

$0.18

163,840

0.36

7

No

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

cohere

-

0.18

135

Yes

No

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

zai-org

-

3.39

27

Yes

No

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

zai-org

-

2.61

60

Yes

No

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

novita

cheapest

$0.30

$0.90

131,072

0.99

71

Yes

No

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

zai-org

fastest

-

1.48

91

Yes

No

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

zai-org

-

2.28

54

Yes

No

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

cohere

-

0.18

42

No

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

cohere

-

0.22

71

Yes

zai-org/GLM-5.2-FP8 GLM-5.2-FP8

zai-org

-

3.77

52

Yes

No

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

cohere

-

0.21

41

No

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

zai-org

-

4.31

26

Yes

No

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

cohere

-

0.22

50

Yes

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

cohere

-

4.93

35

No

Yes

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

cohere

-

0.30

32

Yes

No

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

cohere

-

0.18

56

Yes

inclusionAI/Ling-3.0-flash-VL Ling-3.0-flash-VL

novita

fastest

$0.08

$0.22

262,144

1.01

223

Yes

No

inclusionAI/Ling-3.0-flash-VL Ling-3.0-flash-VL

deepinfra

cheapest

$0.06

$0.18

131,072

0.42

27

Yes

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

novita

$0.27

$0.85

1,048,576

0.41

62

No

Yes

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

novita

$0.62

65,535

0.50

26

No

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

groq

-

131,072

0.28

794

Yes

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

novita

$0.55

$2.20

1,000,000

0.93

51

Yes

No

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

publicai

$0.82

$2.92

-

1.68

14

Yes

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

cohere

-

0.16

134

No

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

cohere

-

0.16

134

No

XiaomiMiMo/MiMo-V2.5 MiMo-V2.5

novita

-

XiaomiMiMo/MiMo-V2.5 MiMo-V2.5

deepinfra

$0.14

$0.28

262,144

1.61

27

Yes

BSC-LT/ALIA-40b-instruct-2606 ALIA-40b-instruct-2606

publicai

$0.30

$0.60

65,536

1.89

19

Yes

aisingapore/Nemotron-SEA-LION-v4.8-120B-A12B Nemotron-SEA-LION-v4.8-120B-A12B

publicai

$0.50

$2.00

262,144

1.26

69

Yes

aisingapore/Qwen-SEA-LION-v4.5-27B-IT Qwen-SEA-LION-v4.5-27B-IT

publicai

$0.20

$0.40

262,144

0.98

54

Yes

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

publicai

$0.25

$0.50

32,000

4.53

42

Yes

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

publicai

$0.20

$0.40

131,072

1.30

56

No

Yes

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

cohere

-

0.16

134

No

NousResearch/Hermes-3-Llama-3.1-70B Hermes-3-Llama-3.1-70B

deepinfra

$0.70

131,072

0.62

28

No

Yes

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

novita

-

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

deepinfra

$0.25

$0.95

163,840

3.75

9

Yes

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

novita

-

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

deepinfra

$0.24

$0.90

163,840

0.51

90

Yes

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

novita

$0.04

$0.14

65,536

0.45

101

No

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

novita

$0.60

$2.50

262,144

0.92

37

Yes