Inference Providers

·

Metrics for top trending models

DeepSeek-V4.1-Flash-1017
novita
cheapest
$0.30$1.201,048,5761.2095YesNo
DeepSeek-V4.1-Flash-1017
together
fastest
$0.30$1.201,048,5760.22186YesNo
DeepSeek-V4.1-Flash-1017
$0.30$1.201,048,5764.15119YesYes
Qwen3.8-27B
$0.42$3.001,000,0001.3229YesNo
Qwen3.8-27B
cerebras
cheapest fastest
$0.99$1.4965,5360.18469YesYes
Qwen3.8-27B
$0.47$3.19262,1442.0017YesYes
Qwen3.8-27B
$0.20$2.50262,1440.2646YesYes
Muse-Spark-Open-816B-A42B
$1.25$4.251,048,5760.36131YesYes
Beam-1.0-501B-A23B
$0.40$1.201,048,5760.32350YesYes
DeepSeek-V4.1-Flash
$0.30$1.201,048,5761.00108YesNo
DeepSeek-V4.1-Flash
$0.30$1.201,048,5760.12292YesNo
DeepSeek-V4.1-Flash
--1,048,5760.4898YesYes
DeepSeek-V4.1-Flash
baseten
fastest
$0.30$1.201,048,5760.24299YesYes
DeepSeek-V4.1-Flash
deepinfra
cheapest
$0.20$0.601,048,5761.7688YesYes
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4
together
cheapest fastest
$0.15$0.50262,1440.16326YesNo
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4
$0.20$0.501,048,5760.46324YesYes
GLM-5.3-Flash
novita
cheapest
$0.15$0.501,048,5761.8263YesYes
GLM-5.3-Flash
together
fastest
$0.15$0.501,048,5750.26168YesNo
GLM-5.3-Flash
--1,048,5760.7699YesYes
GLM-5.3-Flash
---2.3545YesYes
GLM-5.3-Flash
$0.15$0.501,048,5764.97114YesYes
GLM-5.3-Flash
$0.15$0.501,048,5760.4615YesYes
Kimi-K3
$3.00$15.001,048,5760.5334YesNo
Kimi-K3
$3.00$15.001,048,5762.6030YesYes
Kimi-K3
baseten
fastest
$3.00$15.001,048,5760.6770YesYes
Kimi-K3
deepinfra
cheapest
$2.85$14.251,048,5760.8465YesYes
Llama-3.1-8B-Instruct
novita
cheapest fastest
$0.02$0.0516,3840.50172NoNo
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.34121NoYes
Llama-3.1-8B-Instruct
$0.02$0.05131,0720.4826YesNo
Muse-Spark-Open-816B-A42B-NVFP4
$1.25$4.251,048,5760.17166YesNo
GLM-5.3
$1.40$4.401,048,5761.0578YesYes
GLM-5.3
together
fastest
$1.40$4.401,048,5750.37102YesNo
GLM-5.3
--1,048,5760.5859YesYes
GLM-5.3
---2.2852YesYes
GLM-5.3
$1.40$4.401,048,5760.3098YesYes
GLM-5.3
deepinfra
cheapest
$0.90$4.001,048,5760.6666YesYes
Muse-Glimmer-30B
together
fastest
$0.35$1.50131,0720.25104YesYes
Muse-Glimmer-30B
deepinfra
cheapest
$0.30$1.20131,0720.6675YesNo
gemma-4-31B-it
novita
cheapest
$0.14$0.40262,1440.6820YesYes
gemma-4-31B-it
deepinfra
fastest
$0.20$0.40262,1440.3741YesYes
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.6754YesYes
Qwen3.5-9B
$0.12$0.18262,1440.6224YesYes
Qwen3.5-9B
deepinfra
cheapest
$0.10$0.15262,1440.3823YesYes
MiMo-V2.6-Pro-RL
$0.44$0.871,048,5761.4429YesNo
Ling-3.1-flash
$0.30$0.90262,1440.9887YesNo
Qwen3.6-35B-A3B
$0.29$1.71-0.52152YesYes
Qwen3.6-35B-A3B
deepinfra
cheapest fastest
$0.10$0.95262,1440.38173YesYes
gemma-4-26B-A4B-it
$0.13$0.40262,1440.71127YesYes
gemma-4-26B-A4B-it
scaleway
fastest
$0.29$0.57-0.36174YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.2669YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0724.95166YesYes
gpt-oss-20b
-------
gpt-oss-20b
$0.05$0.20131,0720.53160YesYes
gpt-oss-20b
$0.05$0.18131,0720.6953YesYes
gpt-oss-20b
deepinfra
cheapest
$0.03$0.14131,0720.30158YesYes
gpt-oss-120b
$0.15$0.75131,0720.36425YesYes
gpt-oss-120b
$0.05$0.25131,0724.4578YesYes
gpt-oss-120b
cerebras
fastest
$0.35$0.75131,0720.521,005YesYes
gpt-oss-120b
$0.10$0.40131,0723.9287YesYes
gpt-oss-120b
$0.15$0.60131,0720.24193YesYes
gpt-oss-120b
$0.15$0.60131,0720.39178YesYes
gpt-oss-120b
$0.17$0.68-0.44107YesYes
gpt-oss-120b
$0.10$0.50128,0720.20229YesYes
gpt-oss-120b
$0.09$0.47131,0721.6427YesYes
gpt-oss-120b
deepinfra
cheapest
$0.04$0.17131,0720.2369YesYes
MiMo-V2.6-Flash-RL
$0.14$0.281,048,5762.5736YesNo
DeepSeek-V4-Pro
$1.60$3.201,048,5760.4560YesNo
DeepSeek-V4-Pro
-------
DeepSeek-V4-Pro
deepinfra
cheapest fastest
$1.30$2.601,048,5760.3172YesYes
Qwen3-8B
$0.07$0.1840,9600.36147YesNo
DeepSeek-R1
$0.70$2.5064,0001.2928YesYes
MiniMax-M3
$0.30$1.201,000,0000.9058YesNo
MiniMax-M3
$0.30$1.20524,2880.3369YesNo
MiniMax-M3
fireworks-ai
fastest
$0.30$1.20512,0000.5691YesYes
MiniMax-M3
deepinfra
cheapest
$0.28$1.10524,2880.7018YesYes
DeepSeek-V4-Flash
-------
DeepSeek-V4-Flash
$0.09$0.181,048,5760.4948YesYes
Qwen3.8-2.4T-A95B
$2.00$6.001,000,0001.6936YesNo
Qwen3.8-2.4T-A95B
together
fastest
$2.00$6.001,010,0000.41125YesNo
Qwen3.8-2.4T-A95B
--262,1440.60111YesYes
Qwen3.8-2.4T-A95B
deepinfra
cheapest
$2.00$6.00262,1440.8179YesYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1444.9697YesYes
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
--262,1440.40368YesYes
Qwen3-14B
nscale
cheapest fastest
$0.07$0.2040,9600.5091YesNo
Qwen3-14B
$0.12$0.2440,9600.2131YesYes
GLM-5.2
$1.40$4.401,048,5761.4160YesYes
GLM-5.2
together
fastest
$1.40$4.401,048,5750.21183YesNo
GLM-5.2
---2.3257YesNo
GLM-5.2
$2.05$6.27-0.47131YesYes
GLM-5.2
$1.40$4.401,048,5760.8284YesYes
GLM-5.2
deepinfra
cheapest
$0.75$2.401,048,5761.2953YesYes
Qwen3.5-35B-A3B
novita
fastest
$0.25$2.00262,1441.0281YesNo
Qwen3.5-35B-A3B
deepinfra
cheapest
$0.14$1.00262,1440.3480YesYes
Hy4-preview
novita
cheapest
$0.83$2.501,000,0003.1836YesYes
Hy4-preview
deepinfra
fastest
$0.83$2.501,048,5760.7739YesYes
Beam-1.0-501B-A23B-NVFP4
$0.40$1.201,048,5760.14221YesNo
Inkling
together
cheapest fastest
$1.00$4.05524,2880.29112YesYes
Inkling
--1,048,5760.45100YesYes
Inkling
-------
Inkling
$0.95$4.05524,2880.5894YesYes
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.4012,2884.7537YesNo
Llama-3.3-70B-Instruct
scaleway
fastest
$1.03$1.03-0.3987YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0723.3024YesYes
Qwen2.5-Coder-32B-Instruct
$0.06$0.20131,0720.4445NoYes
Qwen3.5-27B
novita
cheapest
$0.30$2.40262,1441.2157YesNo
Qwen3.5-27B
deepinfra
fastest
$0.26$2.60262,1440.2179YesYes
GLM-4.7-Flash
novita
cheapest
$0.07$0.40200,0001.0359YesNo
GLM-4.7-Flash
zai-org
fastest
---1.8761YesNo
GLM-4.7-Flash
$0.06$0.40202,7520.4635YesYes
Inkling-Small
-------
Inkling-Small
$0.45$1.20524,2880.49160YesYes
Qwen3-235B-A22B
-------
Qwen3-235B-A22B
$0.20$0.6032,0000.5518YesNo
Qwen3.6-27B
ovhcloud
cheapest
$0.47$3.19262,1440.2873YesYes
Qwen3.6-27B
deepinfra
fastest
$0.32$3.20262,1440.3078YesYes
Apertus-v1.5-70B
$0.82$2.92-1.1558YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.34145NoYes
DeepSeek-V4-Flash-0731
$0.44$1.321,048,5760.5999YesNo
DeepSeek-V4-Flash-0731
---0.92109YesYes
DeepSeek-V4-Flash-0731
baseten
fastest
$0.13$0.261,048,5760.32163YesYes
DeepSeek-V4-Flash-0731
deepinfra
cheapest
$0.06$0.181,048,5760.4949YesYes
Kimi-K2.5
novita
fastest
$0.60$3.00262,1440.8942YesYes
Kimi-K2.5
deepinfra
cheapest
$0.45$2.25262,1440.5824YesYes
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0720.9514YesYes
Qwen3-VL-30B-A3B-Instruct
deepinfra
cheapest fastest
$0.15$0.60262,1440.3336YesYes
Qwen2.5-72B-Instruct
-------
Qwen2.5-72B-Instruct
$0.36$0.4032,7680.3938YesYes
GLM-4.6
$0.55$2.20204,8004.0326YesNo
GLM-4.6
zai-org
fastest
---2.6038YesNo
GLM-4.6
deepinfra
cheapest
$0.50$2.00202,7523.2917YesYes
DeepSeek-V4-Flash-Vision-Exp
-------
DeepSeek-V4-Flash-Vision-Exp
$0.44$1.321,048,5760.81118YesYes
gemma-3-4b-it
$0.05$0.10131,0720.2299YesYes
Ternary-Bonsai-27B-gguf
$0.00$0.00262,1440.3333YesNo
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
$0.60$2.40262,1440.3695YesYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.42160NoYes
Ling-3.0-flash
$0.06$0.18262,1440.74161YesNo
Ling-3.0-flash
-------
Kimi-K2.6
novita
cheapest fastest
$0.80$3.40262,1441.9273YesNo
Kimi-K2.6
-------
Kimi-K2.6
$0.75$3.50262,1440.6125YesYes
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1441.8092YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.3853YesYes
MiniMax-M2.5
$0.30$1.20204,8000.8846YesNo
phi-4
$0.07$0.1416,3840.3297NoYes
granite-4.2-8b
$0.06$0.25131,0720.7629YesNo
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
$1.00$5.00262,1440.3774YesYes
GLM-5.1
-------
GLM-5.1
$1.05$3.50202,7520.3864YesYes
Bielik-11B-v3.0-Instruct
$0.40$0.40-1.0754YesYes
Qwen3-30B-A3B
-------
Qwen3-30B-A3B
$0.12$0.5040,9600.15107YesYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.28159YesNo
GLM-5.3-BF16
---2.2662YesYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.4886NoYes
DeepSeek-V3.1-Terminus
-------
DeepSeek-V3.1-Terminus
$0.27$0.95163,8400.3149YesYes
MiMo-V2.5-Pro
-------
MiMo-V2.5-Pro
$1.00$3.001,048,5760.6137YesYes
MiniMax-M2.7
novita
fastest
$0.30$1.20204,8000.8643YesNo
MiniMax-M2.7
deepinfra
cheapest
$0.25$1.00196,6080.6119YesYes
granite-4.2-3b
$0.03$0.12131,0720.4129YesNo
Qwen3-VL-235B-A22B-Instruct
-------
Qwen3-VL-235B-A22B-Instruct
$0.20$0.88262,1440.7215YesYes
Qwen3-Next-80B-A3B-Instruct
-------
Qwen3-Next-80B-A3B-Instruct
$0.09$1.10262,1440.3878YesYes
GLM-4.7
$0.60$2.20204,8004.7125YesNo
GLM-4.7
zai-org
fastest
---3.2027YesNo
GLM-4.7
-------
GLM-4.7
deepinfra
cheapest
$0.40$1.75202,7520.3724YesYes
gemma-3-27b-it
$0.08$0.16131,0720.2622YesYes
DeepSeek-V3
-------
DeepSeek-V3
$0.32$0.89163,8400.5719YesYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.3730NoYes
GLM-5.3-Flash-BF16
---1.9753YesYes
GLM-5
$1.00$3.20202,8001.4548YesNo
GLM-5
---3.7376YesNo
GLM-5
deepinfra
cheapest fastest
$0.60$2.08202,7520.6985YesYes
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.4771YesYes
GLM-4.5V
novita
cheapest
$0.60$1.8065,5361.3662YesNo
GLM-4.5V
zai-org
fastest
---2.0266YesNo
Qwen3.5-397B-A17B
$0.60$3.60262,1441.5860YesNo
Qwen3.5-397B-A17B
scaleway
fastest
$0.68$4.10-0.3485YesYes
Qwen3.5-397B-A17B
$0.71$4.25262,1441.4384YesYes
Qwen3.5-397B-A17B
deepinfra
cheapest
$0.45$3.00262,1440.2053YesYes
GLM-4.5
---1.7541YesNo
Qwen3-32B
-------
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest fastest
$0.08$0.2540,9600.3641YesYes
Qwen3-32B
$0.08$0.2840,9600.2739YesNo
Apertus-8B-Instruct-2509
$0.10$0.20-1.96102NoYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.41214NoYes
Hy3
$0.13$0.53262,1441.5238YesYes
Qwen3-235B-A22B-Thinking-2507
-------
Qwen3-235B-A22B-Thinking-2507
$0.23$2.30262,1440.28114YesYes
gemma-3-12b-it
$0.05$0.15131,0720.3321YesYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.53112NoNo
DeepSeek-V3.2
-------
DeepSeek-V3.2
$0.26$0.38163,8400.3827YesYes
Kimi-K2.7-Code
novita
fastest
$0.95$4.00262,1441.4670YesYes
Kimi-K2.7-Code
-------
Kimi-K2.7-Code
deepinfra
cheapest
$0.68$3.40262,1440.5139YesYes
Ling-3.0-flash-VL
$0.08$0.22262,1440.96239YesNo
Ling-3.0-flash-VL
-------
granite-4.2-30b
$0.16$0.65131,0720.4455YesNo
gpt-oss-safeguard-20b
--131,0720.27779YesYes
Hermes-3-Llama-3.1-70B
$0.70$0.70131,0720.2027NoYes
DeepSeek-V4-Pro-0813
$1.32$3.961,048,5761.3147YesNo
DeepSeek-V4-Pro-0813
together
fastest
$1.32$3.961,048,5760.62124YesNo
DeepSeek-V4-Pro-0813
$1.32$3.961,048,5760.2995YesNo
DeepSeek-V4-Pro-0813
deepinfra
cheapest
$1.30$2.601,048,5760.3464YesYes
tiny-aya-water
---0.21133NoNo
Tev1-4B-experimental
$0.04$0.0032,7680.1736YesNo
Llama-Guard-4-12B
$0.18$0.18163,8400.2611NoNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
$0.24$0.90163,8400.5591YesYes
Step-3.7-Flash
$0.20$1.15262,1443.1315YesYes
Ternary-Bonsai-27B-AWQ-4bit
$0.00$0.00262,1440.3857YesNo
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.4915YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
$0.86$2.57-0.3986YesYes
Qwen3-235B-A22B-Instruct-2507
deepinfra
cheapest
$0.09$0.55262,1440.9429YesYes
Llama-4-Scout-17B-16E-Instruct
-------
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0722.9816NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest fastest
$0.09$0.29890,0000.4167YesYes
Llama-4-Scout-17B-16E-Instruct
$0.10$0.30327,6800.3433YesYes
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0720.9887YesNo
GLM-4.5-Air
zai-org
fastest
---1.4891YesNo
Kimi-K2-Instruct
$0.57$2.30131,0721.1851YesNo
Ling-3.0-flash-Fin
$0.08$0.22262,1440.90109YesNo
Ling-3.0-flash-Fin
-------
c4ai-command-r7b-12-2024
---0.2377YesYes
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0721.4726YesNo
GLM-4.6V-Flash
zai-org
fastest
---1.4179YesNo
command-a-vision-07-2025
---0.1846NoYes
c4ai-command-a-03-2025
---0.4015YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.5032,0001.4947YesYes
GLM-4.7-FP8
---2.2951YesNo
c4ai-command-r-08-2024
---0.443YesYes
command-a-reasoning-08-2025
---0.20104YesYes
GLM-4.6V-FP8
---2.7257YesNo
command-a-translate-08-2025
---0.3871YesYes
GLM-4.6V
---3.4255YesNo
tiny-aya-global
---0.17134NoNo
GLM-4.5V-FP8
---1.8673YesNo
aya-vision-32b
---0.2041NoNo
aya-expanse-32b
---0.2648NoNo
c4ai-command-r7b-arabic-02-2025
---0.20121YesNo
GLM-5.2-FP8
---2.9855YesNo
tiny-aya-fire
---0.19113NoNo
tiny-aya-earth
---0.17134NoNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1440.9642YesYes
MiniMax-M1-80k
$0.55$2.201,000,0001.0249YesNo
DeepSeek-R1-0528
$0.70$2.50163,8401.2723YesYes
DeepSeek-R1-0528
deepinfra
cheapest fastest
$0.50$2.15163,8400.6327YesYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.5641NoYes
WizardLM-2-8x22B
$0.62$0.6265,5350.7126NoNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.33137NoYes
MiMo-V2.5
-------
MiMo-V2.5
$0.14$0.28262,1444.357YesYes
Apertus-70B-Instruct-2509
$0.82$2.92-1.9313YesYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40131,0721.2450NoYes
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.4996NoNo
Qwen-SEA-LION-v4.5-27B-IT
$0.20$0.40262,1441.4448YesYes
Nemotron-SEA-LION-v4.8-120B-A12B
$0.50$2.00262,1441.9465YesYes
DeepSeek-V3.1
-------
DeepSeek-V3.1
$0.25$0.95163,8401.119YesYes