Inference Providers

·

Metrics for top trending models

DeepSeek-V4.1-Flash-1017
novita
cheapest
$0.30$1.201,048,5761.1491YesNo
DeepSeek-V4.1-Flash-1017
together
fastest
$0.30$1.201,048,5760.30193YesNo
DeepSeek-V4.1-Flash-1017
---0.58161YesYes
DeepSeek-V4.1-Flash-1017
$0.30$1.201,048,5760.32127YesNo
Qwen3.8-27B
$0.42$3.001,000,0000.8337YesYes
Qwen3.8-27B
cerebras
cheapest fastest
$0.99$1.4965,5360.37828YesYes
Qwen3.8-27B
$0.20$2.501,048,5760.43119YesYes
Qwen3.8-27B
---0.59118YesYes
Qwen3.8-27B
$0.47$3.19262,1443.0436YesYes
Qwen3.8-27B
$0.20$2.50262,1440.4054YesYes
MiniMax-M3.1-Flash
$0.15$0.601,000,0001.5262YesNo
DeepSeek-V4.1-Flash
$0.30$1.201,048,5760.9683YesNo
DeepSeek-V4.1-Flash
together
fastest
$0.30$1.201,048,5760.17262YesNo
DeepSeek-V4.1-Flash
--1,048,5760.53103YesYes
DeepSeek-V4.1-Flash
$0.30$1.201,048,5760.21198YesYes
DeepSeek-V4.1-Flash
deepinfra
cheapest
$0.20$0.601,048,5760.52108YesYes
Llama-3.1-8B-Instruct
novita
cheapest fastest
$0.02$0.0516,3840.53159NoNo
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.43135NoYes
Llama-3.1-8B-Instruct
$0.02$0.05131,0720.6342YesNo
GLM-5.3-Flash
novita
cheapest
$0.15$0.501,048,5762.4340YesYes
GLM-5.3-Flash
together
fastest
$0.15$0.501,048,5750.70151YesNo
GLM-5.3-Flash
--1,048,5760.58128YesYes
GLM-5.3-Flash
---1.0540YesYes
GLM-5.3-Flash
$0.15$0.501,048,5760.7677YesYes
GLM-5.3-Flash
$0.15$0.501,048,5760.38110YesYes
Kimi-K3
$3.00$15.001,048,5761.7448YesNo
Kimi-K3
$3.00$15.001,048,5761.5948YesYes
Kimi-K3
$3.00$15.001,048,5760.7773YesNo
Kimi-K3
deepinfra
cheapest fastest
$2.85$14.251,048,5760.37131YesYes
gemma-4-31B-it
novita
cheapest
$0.14$0.40262,1440.8913YesYes
gemma-4-31B-it
deepinfra
fastest
$0.20$0.40262,1440.3833YesYes
GLM-5.3
$1.40$4.401,048,5761.2193YesYes
GLM-5.3
$1.40$4.401,048,5760.61109YesYes
GLM-5.3
$1.40$4.401,048,5750.34112YesNo
GLM-5.3
--1,048,5760.5578YesYes
GLM-5.3
---1.4047YesYes
GLM-5.3
scaleway
fastest
---0.55220YesYes
GLM-5.3
$1.40$4.401,048,5760.9061YesYes
GLM-5.3
deepinfra
cheapest
$0.90$4.001,048,5760.5548YesYes
Beam-1.0-501B-A23B
$0.40$1.201,048,5760.32299YesYes
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.2091YesNo
Qwen3.5-9B
$0.12$0.18262,1440.2734YesYes
Qwen3.5-9B
deepinfra
cheapest
$0.10$0.15262,1440.3330YesYes
Qwen3.6-35B-A3B
scaleway
fastest
$0.29$1.71-0.60100YesYes
Qwen3.6-35B-A3B
deepinfra
cheapest
$0.10$0.95262,1440.2983YesYes
gpt-oss-120b
$0.15$0.75131,0720.25429YesYes
gpt-oss-120b
$0.05$0.25131,0720.48208YesYes
gpt-oss-120b
cerebras
fastest
$0.35$0.75131,0720.20985YesYes
gpt-oss-120b
$0.10$0.40131,0720.47121YesYes
gpt-oss-120b
$0.15$0.60131,0720.19104YesNo
gpt-oss-120b
$0.15$0.60131,0720.39186YesYes
gpt-oss-120b
$0.17$0.68-0.39123YesYes
gpt-oss-120b
$0.10$0.50128,0720.16141YesYes
gpt-oss-120b
$0.09$0.47131,0720.3921YesYes
gpt-oss-120b
deepinfra
cheapest
$0.04$0.17131,0720.2650YesNo
Muse-Spark-Open-816B-A42B
$1.25$4.251,048,5760.60119YesYes
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4
together
cheapest fastest
$0.15$0.50262,1440.17364YesNo
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4
$0.20$0.501,048,5760.32347YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.25779YesYes
gpt-oss-20b
-------
gpt-oss-20b
$0.05$0.20131,0720.41160YesYes
gpt-oss-20b
$0.05$0.18131,0720.3457YesYes
gpt-oss-20b
deepinfra
cheapest
$0.03$0.14131,0720.40122YesYes
Qwen3.8-2.4T-A95B
$2.00$6.001,000,0001.8833YesNo
Qwen3.8-2.4T-A95B
$2.00$6.001,010,0001.5136YesNo
Qwen3.8-2.4T-A95B
fireworks-ai
fastest
--262,1440.6395YesYes
Qwen3.8-2.4T-A95B
deepinfra
cheapest
$2.00$6.00262,1440.3680YesYes
gemma-4-26B-A4B-it
$0.13$0.40262,1440.70103YesYes
gemma-4-26B-A4B-it
scaleway
fastest
$0.29$0.57-0.61118YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.5153YesYes
MiMo-V2.6-Pro-RL
$0.44$0.871,048,5762.5725YesNo
Muse-Glimmer-30B
together
fastest
$0.35$1.50131,0720.23105YesNo
Muse-Glimmer-30B
deepinfra
cheapest
$0.30$1.20131,0720.2659YesYes
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
--262,1440.38273YesYes
DeepSeek-R1
$0.70$2.5064,0000.9724YesYes
Qwen3-8B
$0.07$0.1840,9600.46128YesNo
DeepSeek-V4-Flash
-------
DeepSeek-V4-Flash
$0.09$0.181,048,5760.4723YesYes
granite-4.2-3b
$0.03$0.12131,0720.4114YesNo
Ling-3.1-flash
$0.30$0.901,000,0000.9976YesNo
Qwen3.8-Flash-Next-FP8
$0.15$0.471,048,5760.87160YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.34144NoYes
DeepSeek-V4-Pro
novita
fastest
$1.60$3.201,048,5760.7444YesNo
DeepSeek-V4-Pro
-------
DeepSeek-V4-Pro
deepinfra
cheapest
$1.30$2.601,048,5760.3034YesYes
Muse-Spark-Open-816B-A42B-NVFP4
$1.25$4.251,048,5760.14162YesNo
gemma-3-4b-it
$0.05$0.10131,0720.36101YesYes
Hy4-preview
novita
cheapest
$0.83$2.501,000,0002.2930YesNo
Hy4-preview
deepinfra
fastest
$0.83$2.501,048,5760.6546YesYes
MiMo-V2.6-Flash-RL
$0.14$0.281,048,5761.9725YesNo
gemma-3-12b-it
$0.05$0.15131,0720.3521YesYes
Qwen2.5-Coder-32B-Instruct
$0.06$0.20131,0720.4047NoYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.45146YesYes
Qwen3-30B-A3B
-------
Qwen3-30B-A3B
$0.12$0.5040,9600.2981YesYes
GLM-5.2
$1.40$4.401,048,5761.6557YesYes
GLM-5.2
together
fastest
$1.40$4.401,048,5750.29126YesNo
GLM-5.2
---1.0262YesNo
GLM-5.2
$2.05$6.27-0.5496YesYes
GLM-5.2
$1.40$4.401,048,5761.0947YesYes
GLM-5.2
deepinfra
cheapest
$0.75$2.401,048,5761.0043YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
$1.00$5.00262,1442.2028YesYes
gemma-3-27b-it
$0.08$0.16131,0720.3620YesNo
tiny-aya-global
---0.16134NoNo
DeepSeek-V4-Flash-0731
$0.44$1.321,048,5760.93110YesNo
DeepSeek-V4-Flash-0731
scaleway
fastest
---0.69150YesYes
DeepSeek-V4-Flash-0731
$0.13$0.261,048,5760.2976YesYes
DeepSeek-V4-Flash-0731
deepinfra
cheapest
$0.06$0.181,048,5760.4250YesYes
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.4012,2880.5047YesNo
Llama-3.3-70B-Instruct
scaleway
fastest
$1.03$1.03-0.5584YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.5528YesYes
Qwen3-14B
nscale
cheapest fastest
$0.07$0.2040,9600.4091YesYes
Qwen3-14B
$0.12$0.2440,9600.5936YesYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.4386NoYes
DeepSeek-V4-Pro-0813
$1.32$3.961,048,5760.9346YesNo
DeepSeek-V4-Pro-0813
together
fastest
$1.32$3.961,048,5760.29116YesNo
DeepSeek-V4-Pro-0813
$1.32$3.961,048,5760.5491YesNo
DeepSeek-V4-Pro-0813
deepinfra
cheapest
$1.30$2.601,048,5760.2637YesYes
DeepSeek-V4-Flash-Vision-Exp
-------
DeepSeek-V4-Flash-Vision-Exp
$0.44$1.321,048,5763.0026YesYes
Inkling
together
cheapest
$1.00$4.05524,2880.4291YesNo
Inkling
--1,048,5760.4386YesYes
Inkling
-------
Inkling
deepinfra
fastest
$0.95$4.05524,2880.35169YesYes
MiMo-V2.5-Pro
-------
MiMo-V2.5-Pro
$1.00$3.001,048,5760.5133YesYes
granite-4.2-30b
$0.16$0.65131,0720.19108YesNo
phi-4
$0.07$0.1416,3840.4197NoYes
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1441.0588YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.3038YesYes
MiniMax-M3
$0.30$1.201,000,0001.3247YesNo
MiniMax-M3
$0.30$1.20524,2880.7072YesNo
MiniMax-M3
fireworks-ai
fastest
$0.30$1.20512,0000.55124YesYes
MiniMax-M3
deepinfra
cheapest
$0.28$1.10524,2880.7749YesNo
Qwen3.5-27B
novita
cheapest fastest
$0.30$2.40262,1441.0666YesNo
Qwen3.5-27B
$0.26$2.60262,1440.3258YesYes
Bielik-11B-v3.0-Instruct
$0.40$0.40-1.2654YesYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.42179NoYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
$0.60$2.40262,1440.5292YesNo
Ternary-Bonsai-27B-gguf
$0.00$0.00262,1440.3958YesNo
Llama-4-Scout-17B-16E-Instruct
-------
Llama-4-Scout-17B-16E-Instruct
-------
Llama-4-Scout-17B-16E-Instruct
$0.09$0.29890,0000.4570YesYes
Llama-4-Scout-17B-16E-Instruct
-------
L3-8B-Stheno-v3.2
$0.05$0.058,1920.45115NoNo
Qwen3.6-27B
ovhcloud
cheapest fastest
$0.47$3.19262,1440.4667YesNo
Qwen3.6-27B
$0.32$3.20262,1440.2553YesYes
Apertus-v1.5-70B
$0.82$2.92-0.8057YesYes
Kimi-K2.7-Code
$0.95$4.00262,1441.4735YesYes
Kimi-K2.7-Code
-------
Kimi-K2.7-Code
deepinfra
cheapest fastest
$0.68$3.40262,1440.4651YesYes
GLM-5.3-BF16
---1.2347YesYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.3841NoYes
GLM-4.7
novita
fastest
$0.60$2.20204,8003.2427YesNo
GLM-4.7
---3.9727YesNo
GLM-4.7
-------
GLM-4.7
deepinfra
cheapest
$0.40$1.75202,7521.1122YesYes
Kimi-K2.6
novita
cheapest fastest
$0.80$3.40262,1441.6033YesNo
Kimi-K2.6
-------
Kimi-K2.6
$0.75$3.50262,1440.5713YesNo
GLM-5
$1.00$3.20202,8001.8231YesNo
GLM-5
---1.3334YesNo
GLM-5
deepinfra
cheapest fastest
$0.60$2.08202,7520.7342YesYes
GLM-4.6V-Flash
$0.30$0.90131,0721.1327YesNo
GLM-4.6V-Flash
-------
Kimi-K2.5
novita
fastest
$0.60$3.00262,1441.2170YesNo
Kimi-K2.5
deepinfra
cheapest
$0.45$2.25262,1440.7518YesYes
GLM-5.3-Flash-BF16
---1.1732YesYes
Inkling-Small
-------
Inkling-Small
$0.45$1.20524,2880.27148YesYes
MiMo-V2.5
-------
MiMo-V2.5
$0.14$0.28262,1440.4123YesYes
granite-4.2-8b
$0.06$0.25131,0720.7315YesNo
gpt-oss-safeguard-20b
--131,0720.24761YesYes
DeepSeek-V3
-------
DeepSeek-V3
$0.32$0.89163,8400.4515YesYes
Qwen3.5-397B-A17B
$0.60$3.60262,1441.3260YesNo
Qwen3.5-397B-A17B
$0.68$4.10-1.3311YesYes
Qwen3.5-397B-A17B
ovhcloud
fastest
$0.71$4.25262,1440.6179YesYes
Qwen3.5-397B-A17B
deepinfra
cheapest
$0.45$3.00262,1440.2338YesYes
MiniMax-M2.5
$0.30$1.20204,8000.8434YesNo
GLM-4.7-Flash
novita
cheapest
$0.07$0.40200,0001.1078YesNo
GLM-4.7-Flash
---0.7171YesNo
GLM-4.7-Flash
deepinfra
fastest
$0.06$0.40202,7520.4482YesYes
Qwen3.5-35B-A3B
$0.25$2.00262,1441.1467YesNo
Qwen3.5-35B-A3B
deepinfra
cheapest fastest
$0.14$1.00262,1440.2194YesNo
GLM-5.2-FP8
---1.0146YesNo
Tev1-4B-experimental
$0.04$0.0032,7680.1638YesNo
Beam-1.0-501B-A23B-NVFP4
$0.40$1.201,048,5760.27161YesNo
Qwen3-235B-A22B
-------
Qwen3-235B-A22B
$0.20$0.6032,0000.5819YesYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.34137NoYes
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.4554YesYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.49144NoYes
Ling-3.0-flash
novita
cheapest fastest
$0.06$0.18262,1440.75277YesNo
Ling-3.0-flash
$0.06$0.18131,0720.6172YesYes
Qwen3-VL-235B-A22B-Instruct
-------
Qwen3-VL-235B-A22B-Instruct
$0.20$0.88262,1441.786YesYes
Qwen3-VL-30B-A3B-Instruct
novita
fastest
$0.20$0.70131,0720.7445YesYes
Qwen3-VL-30B-A3B-Instruct
deepinfra
cheapest
$0.15$0.60262,1440.3336YesYes
Hy3
$0.13$0.53262,1440.7835YesYes
tiny-aya-earth
---0.17134NoNo
Ling-3.0-flash-Fin
novita
fastest
$0.08$0.22262,1440.95116YesNo
Ling-3.0-flash-Fin
deepinfra
cheapest
$0.06$0.18262,1440.6443YesYes
Step-3.5-Flash
$0.10$0.30262,1440.5220YesYes
GLM-4.5
---3.6725YesNo
DeepSeek-V3.2
-------
DeepSeek-V3.2
$0.26$0.38163,8400.4618YesYes
Qwen3-32B
-------
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest fastest
$0.08$0.2540,9600.4645YesNo
Qwen3-32B
$0.08$0.2840,9600.2529YesYes
DeepSeek-R1-0528
novita
fastest
$0.70$2.50163,8400.8522YesYes
DeepSeek-R1-0528
deepinfra
cheapest
$0.50$2.15163,8400.3818YesYes
DeepSeek-V3.1-Terminus
-------
DeepSeek-V3.1-Terminus
$0.27$0.95163,8400.2956YesYes
Hermes-3-Llama-3.1-70B
$0.70$0.70131,0720.3753YesYes
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.4714YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
$0.86$2.57-0.4367YesYes
Qwen3-235B-A22B-Instruct-2507
deepinfra
cheapest
$0.09$0.55262,1440.3117YesNo
DeepSeek-V3.1
-------
DeepSeek-V3.1
$0.25$0.95163,8400.4030YesYes
Qwen3-Next-80B-A3B-Instruct
-------
Qwen3-Next-80B-A3B-Instruct
$0.09$1.10262,1440.40124YesYes
GLM-4.6
$0.55$2.20204,8002.9027YesNo
GLM-4.6
zai-org
fastest
---4.1027YesNo
GLM-4.6
deepinfra
cheapest
$0.50$2.00202,7520.4520YesYes
Ling-3.0-flash-VL
novita
fastest
$0.08$0.22262,1441.03237YesNo
Ling-3.0-flash-VL
deepinfra
cheapest
$0.06$0.18131,0720.6344YesNo
Qwen3-235B-A22B-Thinking-2507
-------
Qwen3-235B-A22B-Thinking-2507
$0.23$2.30262,1440.22196YesNo
Step-3.7-Flash
$0.20$1.15262,1440.6428YesYes
MiniMax-M2.7
$0.30$1.20204,8000.7537YesNo
MiniMax-M2.7
deepinfra
cheapest fastest
$0.25$1.00196,6080.4845YesYes
tiny-aya-water
---0.16134NoNo
Ternary-Bonsai-27B-AWQ-4bit
$0.00$0.00262,1440.4454YesNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5361.2157YesNo
GLM-4.5V
zai-org
fastest
---0.7659YesNo
GLM-5.1-FP8
---2.5029YesNo
GLM-5.1
zai-org
fastest
---2.5731YesNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7520.3723YesYes
GLM-4.7-FP8
---3.7629YesNo
GLM-4.6V-FP8
---1.3946YesNo
GLM-4.6V
---0.7335YesNo
GLM-4.5V-FP8
---0.7960YesNo
GLM-4.6-FP8
---3.5227YesNo
tiny-aya-fire
---0.17130NoNo
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.8792YesNo
GLM-4.5-Air
---0.6083YesNo
aya-expanse-32b
---0.2047NoNo
c4ai-command-r7b-12-2024
---0.4475YesYes
aya-vision-32b
---0.1942NoNo
c4ai-command-r-08-2024
---0.1935YesYes
c4ai-command-a-03-2025
---0.6528YesYes
c4ai-command-r7b-arabic-02-2025
---0.2178YesNo
command-a-reasoning-08-2025
---0.21103YesYes
command-a-translate-08-2025
---0.2571YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.5032,0001.3448YesYes
WizardLM-2-8x22B
$0.62$0.6265,5350.5821NoNo
MiniMax-M1-80k
$0.55$2.201,000,0000.8969YesNo
Kimi-K2-Instruct
$0.57$2.30131,0721.3594YesNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1440.7240YesYes
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.5190NoNo
Llama-Guard-4-12B
$0.18$0.18163,8400.3010NoNo
ALIA-40b-instruct-2606
$0.30$0.6065,5361.1626YesYes
Nemotron-SEA-LION-v4.8-120B-A12B
$0.50$2.00262,1441.5562YesYes
Qwen-SEA-LION-v4.5-27B-IT
$0.20$0.40262,1441.5922YesYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40131,0722.0442NoYes
Apertus-70B-Instruct-2509
$0.82$2.92-1.3215YesYes
Apertus-8B-Instruct-2509
$0.10$0.20-1.0643NoYes
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
$0.24$0.90163,8400.3987YesYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.4433NoYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.47140YesYes