Inference Providers

·

Metrics for top trending models

DeepSeek-V4.1-Flash
novita
fastest
$0.30$1.201,048,5760.98103YesNo
DeepSeek-V4.1-Flash
--1,048,5760.8650YesYes
DeepSeek-V4.1-Flash
$0.30$1.201,048,5761.0084YesYes
DeepSeek-V4.1-Flash
deepinfra
cheapest
$0.20$0.601,048,5760.8036YesYes
Qwen3.8-27B
$0.42$3.001,000,0000.7435YesNo
Qwen3.8-27B
-------
Qwen3.8-27B
ovhcloud
fastest
$0.47$3.19262,1440.5362YesYes
Qwen3.8-27B
deepinfra
cheapest
$0.20$2.50262,1440.4030YesYes
GLM-5.3-Flash
novita
cheapest
$0.15$0.501,048,5762.2530YesNo
GLM-5.3-Flash
together
fastest
$0.15$0.501,048,5750.1892YesNo
GLM-5.3-Flash
--1,048,5761.0690YesYes
GLM-5.3-Flash
---3.5829YesNo
GLM-5.3-Flash
$0.15$0.501,048,5760.4174YesYes
GLM-5.3-Flash
$0.15$0.501,048,5760.9530YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3841.09112NoNo
Llama-3.1-8B-Instruct
nscale
fastest
$0.06$0.06131,0720.63149NoYes
Llama-3.1-8B-Instruct
$0.02$0.05131,0720.4729YesNo
Kimi-K3
$3.00$15.001,048,5760.5853YesNo
Kimi-K3
$3.00$15.001,048,5760.8347YesYes
Kimi-K3
baseten
fastest
$3.00$15.001,048,5760.6485YesYes
Kimi-K3
deepinfra
cheapest
$2.85$14.251,048,5760.6019YesYes
Ternary-Bonsai-27B-gguf
$0.00$0.00262,1440.4258YesNo
GLM-5.3
$1.40$4.401,048,5761.0168YesYes
GLM-5.3
together
fastest
$1.40$4.401,048,5750.14166YesNo
GLM-5.3
--1,048,5761.0257YesYes
GLM-5.3
---2.4454YesNo
GLM-5.3
$1.40$4.401,048,5762.0465YesYes
GLM-5.3
deepinfra
cheapest
$0.90$4.001,048,5760.5857YesYes
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.38116YesYes
Qwen3.5-9B
$0.12$0.18262,1440.4536YesYes
Qwen3.5-9B
deepinfra
cheapest
$0.10$0.15262,1440.4938YesYes
Qwen3.6-35B-A3B
$0.29$1.71-0.5937YesYes
Qwen3.6-35B-A3B
deepinfra
cheapest fastest
$0.10$0.95262,1440.5565YesYes
gemma-4-31B-it
$0.14$0.40262,1440.5229YesYes
gemma-4-31B-it
-------
gemma-4-31B-it
deepinfra
cheapest fastest
$0.13$0.38262,1440.3936YesYes
gpt-oss-120b
$0.15$0.75131,0720.50386YesYes
gpt-oss-120b
$0.05$0.25131,0720.7935YesYes
gpt-oss-120b
cerebras
fastest
$0.35$0.75131,0720.171,203YesYes
gpt-oss-120b
$0.10$0.40131,0720.7697YesYes
gpt-oss-120b
$0.15$0.60131,0720.2291YesYes
gpt-oss-120b
$0.15$0.60131,0720.47165YesYes
gpt-oss-120b
$0.17$0.68-0.6677YesYes
gpt-oss-120b
$0.10$0.50128,0720.34187YesYes
gpt-oss-120b
$0.09$0.47131,0720.3818YesYes
gpt-oss-120b
deepinfra
cheapest
$0.04$0.17131,0720.4031YesYes
Muse-Glimmer-30B
together
fastest
$0.35$1.50131,0720.23108YesYes
Muse-Glimmer-30B
--131,0720.2361YesNo
Muse-Glimmer-30B
deepinfra
cheapest
$0.30$1.20131,0720.2559YesYes
Qwen3-8B
$0.07$0.1840,9600.73129YesNo
DeepSeek-V4-Flash-0731
$0.44$1.321,048,5760.56131YesNo
DeepSeek-V4-Flash-0731
$0.14$0.281,048,5761.2830YesNo
DeepSeek-V4-Flash-0731
--1,048,5760.61125YesYes
DeepSeek-V4-Flash-0731
---1.3144YesYes
DeepSeek-V4-Flash-0731
baseten
fastest
$0.13$0.261,048,5760.37193YesYes
DeepSeek-V4-Flash-0731
deepinfra
cheapest
$0.06$0.181,048,5760.8427YesYes
Qwen3.8-2.4T-A95B
$2.00$6.001,000,0001.1431YesYes
Qwen3.8-2.4T-A95B
together
fastest
$2.00$6.001,010,0000.5997YesNo
Qwen3.8-2.4T-A95B
--262,1441.4739YesYes
Qwen3.8-2.4T-A95B
deepinfra
cheapest
$2.00$6.00262,1440.4775YesYes
DeepSeek-R1
$0.70$2.5064,0000.8018YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.20711YesYes
gpt-oss-20b
$0.04$0.15131,0720.56124NoYes
gpt-oss-20b
$0.05$0.20131,0720.59154YesYes
gpt-oss-20b
-------
gpt-oss-20b
$0.05$0.18131,0720.3664YesYes
gpt-oss-20b
deepinfra
cheapest
$0.03$0.14131,0720.6692YesYes
Qwen3-Coder-Next
$0.20$1.50262,1441.25123YesNo
DeepSeek-V4-Pro
$1.60$3.201,048,5760.7732YesNo
DeepSeek-V4-Pro
-------
DeepSeek-V4-Pro
baseten
fastest
$1.74$3.481,048,5760.6982YesNo
DeepSeek-V4-Pro
deepinfra
cheapest
$1.30$2.601,048,5761.0120YesYes
DeepSeek-V4-Flash
novita
fastest
$0.14$0.281,048,5761.41106YesNo
DeepSeek-V4-Flash
deepinfra
cheapest
$0.09$0.181,048,5760.6523YesYes
gemma-4-26B-A4B-it
$0.13$0.40262,1440.6114YesYes
gemma-4-26B-A4B-it
scaleway
fastest
$0.29$0.57-0.47127YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.2320YesYes
Hy4-preview
$0.83$2.501,000,0001.7534YesYes
Qwen3.6-27B
ovhcloud
cheapest fastest
$0.47$3.19262,1440.8958YesYes
Qwen3.6-27B
$0.32$3.20262,1440.9635YesYes
MiniMax-M3
$0.30$1.201,000,0001.2693YesNo
MiniMax-M3
$0.30$1.20524,2880.6146YesNo
MiniMax-M3
fireworks-ai
fastest
$0.30$1.20512,0000.6496YesYes
MiniMax-M3
deepinfra
cheapest
$0.28$1.10524,2884.3717YesYes
DeepSeek-V4-Flash-Vision-Exp
novita
cheapest fastest
$0.44$1.321,048,5760.52128YesNo
DeepSeek-V4-Flash-Vision-Exp
--1,048,5760.7068YesYes
DeepSeek-V4-Flash-Vision-Exp
-------
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.6851YesYes
Ling-3.0-flash-Fin
novita
cheapest fastest
$0.00$0.00262,1440.60253YesNo
Ling-3.0-flash-Fin
$0.06$0.18262,1440.3585YesYes
Inkling
together
cheapest
$1.00$4.05524,2880.15109YesYes
Inkling
--1,048,5760.3999YesYes
Inkling
baseten
fastest
$1.00$4.051,048,5760.29130YesYes
Inkling
$0.95$4.05524,2880.4982YesYes
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
--262,1440.53246YesYes
Inkling-Small
-------
Inkling-Small
baseten
cheapest fastest
$0.50$1.201,048,5760.33196YesYes
Inkling-Small
$0.45$1.20524,2880.31108YesYes
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.4012,2880.5347YesNo
Llama-3.3-70B-Instruct
$1.04$1.04131,0720.4880YesYes
Llama-3.3-70B-Instruct
scaleway
fastest
$1.03$1.03-0.5882YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.3031YesNo
Ling-3.0-flash-VL
novita
cheapest fastest
$0.00$0.00262,1440.8495YesNo
Ling-3.0-flash-VL
$0.06$0.18131,0722.2161YesYes
Apertus-v1.5-70B
$0.82$2.92-1.2426NoYes
Qwen3-Coder-30B-A3B-Instruct
$0.23$0.91-0.42133YesYes
gemma-3-4b-it
$0.05$0.10131,0721.4916YesYes
GLM-4.7-Flash
novita
cheapest fastest
$0.07$0.40200,0001.8667YesNo
GLM-4.7-Flash
-------
GLM-4.7-Flash
$0.06$0.40202,7521.5027YesYes
MiMo-V2.5-Pro
-------
MiMo-V2.5-Pro
$1.00$3.001,048,5760.4337YesYes
GLM-5.2
$1.40$4.401,048,5761.6552YesYes
GLM-5.2
together
fastest
$1.40$4.401,048,5750.23130YesNo
GLM-5.2
$1.40$4.401,048,5760.7976YesYes
GLM-5.2
---2.4656YesNo
GLM-5.2
$2.05$6.27-0.6970YesYes
GLM-5.2
$1.40$4.401,048,5760.7077YesYes
GLM-5.2
deepinfra
cheapest
$0.75$2.401,048,5760.3037YesYes
DeepSeek-V4-Pro-0813
$1.32$3.961,048,5761.1737YesNo
DeepSeek-V4-Pro-0813
together
fastest
$1.32$3.961,048,5760.5895YesNo
DeepSeek-V4-Pro-0813
--1,048,5760.6257YesYes
DeepSeek-V4-Pro-0813
$1.32$3.961,048,5763.3952YesYes
DeepSeek-V4-Pro-0813
deepinfra
cheapest
$1.30$2.601,048,5760.4176YesYes
Ling-3.0-flash
novita
cheapest fastest
$0.06$0.18262,1440.66260YesNo
Ling-3.0-flash
$0.06$0.18131,0720.9241YesYes
Ternary-Bonsai-27B-AWQ-4bit
$0.00$0.00262,1440.2664YesNo
Qwen2.5-Coder-32B-Instruct
$0.06$0.20131,0720.9748NoYes
Qwen3.5-27B
novita
cheapest
$0.30$2.40262,1441.0365YesNo
Qwen3.5-27B
deepinfra
fastest
$0.26$2.60262,1440.2767YesYes
Kimi-K2.7-Code
$0.95$4.00262,1441.6446YesYes
Kimi-K2.7-Code
-------
Kimi-K2.7-Code
$0.95$4.00262,1440.3286YesYes
Kimi-K2.7-Code
$0.95$4.00262,0000.3191YesYes
Kimi-K2.7-Code
deepinfra
cheapest fastest
$0.68$3.40262,1440.8794YesNo
phi-4
$0.07$0.1416,3840.3748NoYes
Qwen3.5-35B-A3B
novita
fastest
$0.25$2.00262,1441.3860YesNo
Qwen3.5-35B-A3B
deepinfra
cheapest
$0.14$1.00262,1440.3355YesYes
Llama-4-Scout-17B-16E-Instruct
-------
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.4753NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest fastest
$0.09$0.29890,0000.7272YesYes
Llama-4-Scout-17B-16E-Instruct
$0.10$0.30327,6800.3136YesYes
Kimi-K2.5
novita
fastest
$0.60$3.00262,1441.4470YesYes
Kimi-K2.5
deepinfra
cheapest
$0.45$2.25262,1440.7814YesYes
Qwen3-30B-A3B
-------
Qwen3-30B-A3B
$0.12$0.5040,9600.19128YesYes
MiMo-V2.5
novita
fastest
$0.17$0.341,048,5761.4335YesNo
MiMo-V2.5
deepinfra
cheapest
$0.14$0.28262,1440.6412YesYes
Bielik-11B-v3.0-Instruct
$0.40$0.40-1.6553YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
-------
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
$0.60$2.40262,1440.42115YesYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.42108NoNo
GLM-5.3-BF16
---2.9445YesNo
DeepSeek-V3.2
novita
fastest
$0.27$0.40163,8401.3038YesYes
DeepSeek-V3.2
deepinfra
cheapest
$0.26$0.38163,8400.8217YesNo
gemma-3-12b-it
$0.05$0.15131,0720.2143YesYes
gemma-3-27b-it
$0.08$0.16131,0720.4321YesYes
Qwen3-VL-30B-A3B-Instruct
novita
fastest
$0.20$0.70131,0720.65108YesYes
Qwen3-VL-30B-A3B-Instruct
deepinfra
cheapest
$0.15$0.60262,1440.2722YesYes
granite-4.2-3b
$0.03$0.12131,0720.20233YesNo
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.4349YesNo
Kimi-K2.6
$0.95$4.00262,1440.4269YesYes
Kimi-K2.6
baseten
fastest
$0.95$4.00262,0000.36113YesYes
Kimi-K2.6
$0.75$3.50262,1440.7037YesYes
Hy3
$0.13$0.53262,1440.3839YesYes
Qwen3-14B
nscale
cheapest fastest
$0.07$0.2040,9600.6480YesYes
Qwen3-14B
$0.12$0.2440,9600.1919YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
$1.00$5.00262,1441.1317YesYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.3275NoYes
Step-3.7-Flash
$0.20$1.15262,1440.35126YesNo
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.8917NoNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.63129NoYes
gpt-oss-safeguard-20b
--131,0720.26698YesYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.80143NoNo
Qwen3-VL-235B-A22B-Instruct
novita
fastest
$0.30$1.50131,0720.8038YesYes
Qwen3-VL-235B-A22B-Instruct
deepinfra
cheapest
$0.20$0.88262,1441.4210YesYes
GLM-5
$1.00$3.20202,8001.1047YesNo
GLM-5
zai-org
fastest
---3.8857YesNo
GLM-5
deepinfra
cheapest
$0.60$2.08202,7520.5435YesYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.5994NoNo
MiniMax-M2.5
$0.30$1.20204,8001.0855YesNo
Qwen3.5-122B-A10B
$0.40$3.20262,1441.03108YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest fastest
$0.29$2.40262,1440.39125YesNo
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1441.0855YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
$0.24$0.90163,8400.9474YesYes
DeepSeek-V3
-------
DeepSeek-V3
$0.32$0.89163,8400.5615YesYes
Kimi-K2-Instruct
$0.57$2.30131,0721.2240YesNo
granite-4.2-8b
$0.06$0.25131,0720.26155YesNo
granite-4.2-30b
$0.16$0.65131,0720.6233YesNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.9253YesNo
tiny-aya-water
---0.18134NoNo
Llama-Guard-4-12B
-------
Llama-Guard-4-12B
$0.18$0.18163,8400.2411NoNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.99147NoYes
Qwen3-32B
-------
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest fastest
$0.08$0.2540,9600.6842YesNo
Qwen3-32B
$0.08$0.2840,9600.4629YesYes
tiny-aya-earth
---0.16134NoNo
Qwen3-235B-A22B-Instruct-2507
novita
fastest
$0.09$0.58131,0720.5351YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.8118YesYes
Qwen3-235B-A22B-Instruct-2507
$0.86$2.57-1.2425YesYes
Qwen3-235B-A22B-Instruct-2507
deepinfra
cheapest
$0.09$0.55262,1440.7112YesYes
Qwen3.5-397B-A17B
$0.60$3.60262,1441.4767YesNo
Qwen3.5-397B-A17B
$0.68$4.10-0.6434YesYes
Qwen3.5-397B-A17B
ovhcloud
fastest
$0.71$4.25262,1440.48170YesNo
Qwen3.5-397B-A17B
deepinfra
cheapest
$0.45$3.00262,1440.4939YesYes
Step-3.5-Flash
$0.10$0.30262,1440.18136YesNo
c4ai-command-r-08-2024
---0.2529YesYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1441.30141YesYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.4131NoYes
command-a-reasoning-08-2025
---0.21104YesYes
Qwen2.5-72B-Instruct
novita
cheapest
$0.38$0.4032,0000.5319YesNo
Qwen2.5-72B-Instruct
deepinfra
fastest
$0.36$0.4032,7680.3124YesYes
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0721.1476YesNo
GLM-4.5-Air
zai-org
fastest
---1.4587YesNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0721.4692NoNo
Qwen3-Next-80B-A3B-Instruct
deepinfra
cheapest fastest
$0.09$1.10262,1440.46107YesYes
MiniMax-M2.7
novita
fastest
$0.30$1.20204,8001.5634YesNo
MiniMax-M2.7
deepinfra
cheapest
$0.25$1.00196,6080.5318YesYes
Kimi-K2-Instruct-0905
$0.60$2.50262,1440.8340YesYes
GLM-5.3-Flash-BF16
---3.7626YesNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.4487NoNo
tiny-aya-global
---0.16134NoNo
Hermes-3-Llama-3.1-70B
$0.70$0.70131,0720.2935NoYes
tiny-aya-fire
---0.16134NoNo
Apertus-70B-Instruct-2509
$0.82$2.92-1.9951YesYes
GLM-4.7
$0.60$2.20204,8003.6126YesNo
GLM-4.7
---3.0837YesNo
GLM-4.7
baseten
fastest
$0.60$2.20200,0000.30172YesYes
GLM-4.7
deepinfra
cheapest
$0.40$1.75202,7520.5914YesYes
GLM-4.7-FP8
---2.2951YesNo
GLM-4.6V-FP8
---2.4354YesNo
GLM-4.6V
---3.1451YesNo
GLM-4.5V-FP8
---3.1533YesNo
GLM-4.6-FP8
---2.5843YesNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5361.4032YesNo
GLM-4.5V
zai-org
fastest
---2.6439YesNo
GLM-4.5
---1.7541YesNo
GLM-5.2-FP8
---2.8654YesNo
command-a-translate-08-2025
---0.3270YesYes
c4ai-command-r7b-12-2024
---0.1971YesYes
c4ai-command-a-03-2025
---0.3555YesNo
aya-expanse-32b
---0.1840NoNo
aya-vision-32b
---0.2042NoNo
command-a-vision-07-2025
---0.1547NoYes
DeepSeek-V3.1
novita
fastest
$0.27$1.00131,0721.9039YesYes
DeepSeek-V3.1
deepinfra
cheapest
$0.25$0.95163,8400.6013YesYes
WizardLM-2-8x22B
$0.62$0.6265,5350.6612NoNo
GLM-4-32B-0414
$0.55$1.6632,0000.9647NoNo
Qwen3-235B-A22B
novita
fastest
$0.20$0.8040,9600.9626NoNo
Qwen3-235B-A22B
nscale
cheapest
$0.20$0.6032,0000.7716YesNo
MiniMax-M1-80k
$0.55$2.201,000,0001.1748YesNo
DeepSeek-R1-0528
$0.70$2.50163,8401.5320NoNo
DeepSeek-R1-0528
deepinfra
cheapest fastest
$0.50$2.15163,8400.7928NoNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.2841NoNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.8255YesNo
Qwen3-235B-A22B-Thinking-2507
deepinfra
cheapest fastest
$0.23$2.30262,1440.30120YesYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0721.08139NoNo
MiniMax-M2.1
$0.30$1.20204,8001.3554YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.5090NoNo
GLM-4.6V-Flash
$0.30$0.90131,0721.8843YesNo
GLM-4.6V-Flash
-------
MiniMax-M2
$0.30$1.20204,8001.2157YesNo
DeepSeek-V3.1-Terminus
novita
fastest
$0.27$1.00131,0721.7038YesYes
DeepSeek-V3.1-Terminus
deepinfra
cheapest
$0.27$0.95163,8400.5422YesYes
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.3338YesYes
GLM-4.6
$0.55$2.20204,8003.6924YesNo
GLM-4.6
-------
GLM-4.6
deepinfra
cheapest fastest
$0.50$2.00202,7520.4466YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.3246YesNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.1450NoYes
Apertus-8B-Instruct-2509
$0.10$0.20-1.50101YesYes
GLM-5.1
-------
GLM-5.1
$1.05$3.50202,7520.9411YesNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.8838NoYes