Inference Providers

·

Metrics for top trending models

NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
$0.60$3.60512,2880.41132YesNo
DeepSeek-V4-Pro
novita
cheapest
$1.60$3.381,048,5760.5533YesNo
DeepSeek-V4-Pro
$1.74$3.48512,0000.7018YesYes
DeepSeek-V4-Pro
fireworks-ai
fastest
--1,048,5760.9873YesNo
DeepSeek-V4-Pro
$1.74$3.4865,5360.8722YesYes
gemma-4-31B-it
novita
fastest
$0.14$0.40262,1440.6496YesYes
gemma-4-31B-it
$0.39$0.97262,1440.4411YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.4335YesYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.24139YesYes
DeepSeek-V4-Flash
novita
cheapest
$0.14$0.281,048,5761.3063YesNo
DeepSeek-V4-Flash
fireworks-ai
fastest
---0.7890YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5760.5422YesYes
Qwen3.6-27B
---1.4953YesYes
gemma-4-26B-A4B-it
novita
fastest
$0.13$0.40262,1441.8239YesNo
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.3539YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.2625YesNo
Kimi-K2.6
$1.20$4.50262,1440.3058YesYes
Kimi-K2.6
fireworks-ai
fastest
--262,1440.2892NoNo
Kimi-K2.6
$0.75$3.50262,1440.7253YesNo
Llama-3.1-8B-Instruct
novita
cheapest fastest
$0.02$0.0516,3840.66174NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.51151NoYes
Llama-3.1-8B-Instruct
---0.44143YesYes
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.2774YesYes
Qwen3.5-9B
ovhcloud
cheapest
$0.12$0.18262,1440.6741YesYes
gpt-oss-120b
$0.15$0.75131,0720.39420YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.4387YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.221,082YesNo
gpt-oss-120b
$0.22$0.59131,0721.32430YesYes
gpt-oss-120b
$0.10$0.40131,0720.45112YesYes
gpt-oss-120b
$0.15$0.60131,0720.2741YesYes
gpt-oss-120b
$0.15$0.60131,0720.44187YesNo
gpt-oss-120b
---0.36163YesYes
gpt-oss-120b
$0.09$0.47131,0720.3893YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.22712YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0723.6783NoYes
gpt-oss-20b
$0.05$0.20131,0720.55161YesYes
gpt-oss-20b
$0.05$0.20131,0720.2694NoNo
gpt-oss-20b
$0.05$0.20131,0720.5472YesNo
gpt-oss-20b
$0.05$0.18131,0720.3184YesYes
GLM-5.1
together
fastest
$1.40$4.40202,7520.4073YesYes
GLM-5.1
--202,7521.2147YesNo
GLM-5.1
---4.1928NoNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7521.1822YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.21134YesYes
Meta-Llama-3-8B-Instruct
-------
Meta-Llama-3-8B-Instruct
$0.14$0.148,1920.17194NoYes
Qwen3-Coder-Next
$0.20$1.50262,1441.07122YesNo
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8001.6640YesNo
MiniMax-M2.7
$0.30$1.20196,6080.3577YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.63189YesNo
DeepSeek-R1
$0.70$2.5064,0001.6525YesYes
DeepSeek-R1
-------
DeepSeek-R1
-------
Qwen3-VL-8B-Instruct
$0.08$0.50131,0721.0363YesNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.50130NoYes
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.36129YesYes
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.508YesYes
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.5945NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.42131YesYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.58152YesYes
Qwen3-8B
$0.07$0.1840,9600.50136YesNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.13322YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.5135YesNo
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.5537NoNo
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.7489NoNo
Llama-3.3-70B-Instruct
$1.04$1.04131,0721.0330YesYes
Llama-3.3-70B-Instruct
---0.4383YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.3833YesYes
Kimi-K2.5
novita
cheapest
$0.60$3.00262,1441.4633YesYes
Kimi-K2.5
fireworks-ai
fastest
--262,1440.2760YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.8499YesNo
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1441.2252YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.43234YesYes
Qwen3.5-397B-A17B
---0.54102YesYes
Qwen3.5-397B-A17B
$0.71$4.25262,1441.4738YesNo
Qwen3.5-397B-A17B
$0.49$3.60262,1440.4474YesYes
GLM-4.7
novita
cheapest
$0.60$2.20204,8001.8637YesNo
GLM-4.7
cerebras
fastest
---0.27381YesNo
GLM-4.7
---2.2121YesNo
tiny-aya-global
---0.44121NoNo
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1440.8384YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.4483YesYes
gpt-oss-safeguard-20b
--131,0720.39688YesNo
DeepSeek-OCR
$0.03$0.038,1920.85192NoNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.53153NoYes
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8001.3367YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.8785YesNo
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.53321NoNo
GLM-4.7-Flash
-------
GLM-4.7-Flash
---3.6552YesNo
Qwen3-14B
$0.07$0.2040,9600.5095YesNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.47160YesYes
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1441.2056YesYes
Qwen3-Coder-480B-A35B-Instruct
-------
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.5830NoYes
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0720.8336YesNo
GLM-4.5-Air
zai-org
fastest
---2.2361YesNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.9372YesNo
tiny-aya-fire
---0.22120NoNo
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.15418YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3052NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.6373YesNo
GLM-5.1-FP8
fireworks-ai
fastest
--202,7521.8740YesNo
GLM-5.1-FP8
---3.8129YesNo
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.4948NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.5438NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3785YesYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
DeepSeek-V3.2
$0.27$0.40163,8401.6031YesYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.8095NoNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.5434YesNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1921.6120NoNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.1811NoNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.7645YesYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.5177NoYes
Arch-Router-1.5B
---0.1079NoYes
GLM-5
novita
cheapest
$1.00$3.20202,8002.8931YesNo
GLM-5
together
fastest
$1.00$3.20202,7520.5498YesYes
GLM-5
---3.6836YesNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.5620NoYes
DeepSeek-R1-0528
$0.70$2.50163,8401.6525YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
MiniMax-M1-80k
$0.55$2.201,000,0002.4159YesNo
Kimi-K2-Instruct
$0.57$2.30131,0721.4222YesNo
gemma-3n-E4B-it
$0.06$0.1232,7680.3143NoYes
tiny-aya-water
---0.25121NoNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.5421YesNo
GLM-4.6V-Flash
novita
cheapest fastest
$0.30$0.90131,0721.0667YesNo
GLM-4.6V-Flash
---4.3061YesNo
c4ai-command-a-03-2025
---0.3062YesNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.0043YesNo
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0720.75108YesYes
DeepSeek-V3-0324
$0.27$1.12163,8401.3930YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
QwQ-32B
$0.18$0.20131,0720.5848YesYes
GLM-4.5V-FP8
---2.4649NoNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.6874NoNo
Llama-3.1-70B-Instruct
---0.3687YesYes
GLM-4.7-FP8
---1.63102YesNo
GLM-4.6V-FP8
---1.9571YesNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.3247YesYes
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.5914YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.2353YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
---0.36101YesYes
GLM-4.6V
---2.0061YesNo
Gemma-4-31B-it-pearl
$0.28$0.86262,1440.3931YesNo
GLM-4.6-FP8
---3.4615YesNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2835NoNo
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8001.9351YesNo
GLM-4.6
---3.7520YesNo
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5360.9756YesNo
GLM-4.5V
---2.5943YesNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0721.3552YesNo
GLM-4.5
---2.6249YesNo
cogito-671b-v2.1
$1.25$1.25163,8400.2742NoNo
cogito-671b-v2.1
-------
rnj-1-instruct
$0.15$0.1532,7680.23119YesYes
gemma-3-27b-it
---0.6147YesNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.3641NoNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.5379NoNo
Qwen3-235B-A22B
$0.20$0.8040,9600.749NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0000.6516YesYes
GLM-4-32B-0414
$0.55$1.6632,0001.0135NoNo
DeepSeek-V3
$0.40$1.3064,0001.5329YesNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.2676NoNo
WizardLM-2-8x22B
$0.62$0.6265,5350.6111NoNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.31224YesNo
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.6446YesNo
Qwen3-32B
$0.09$0.2532,7680.3534YesYes
Step-3.5-Flash
$0.10$0.30262,1440.3537YesNo
tiny-aya-earth
---0.35123NoNo
command-a-translate-08-2025
---0.3667YesNo
command-a-reasoning-08-2025
---0.7929YesNo
c4ai-command-r7b-arabic-02-2025
---0.22126YesNo
aya-vision-32b
---0.2936NoNo
aya-expanse-32b
---0.3339NoNo
c4ai-command-r-08-2024
---0.1959YesNo
c4ai-command-r7b-12-2024
---0.3171YesNo
Qwen3.5-27B
$0.30$2.40262,1440.9321YesNo
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.1548YesYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-2.2445NoNo
Apertus-70B-Instruct-2509
$0.82$2.92-0.7060NoYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.76107NoYes
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.5649NoYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.62147NoNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.53142NoYes
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.5853NoYes
Ling-2.6-1T
$0.30$2.50262,1441.1086YesNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.6266YesYes
MiniMax-M2.1
$0.30$1.20204,8001.4271YesNo
Kimi-K2-Thinking
$0.60$2.50262,1441.0859NoNo
MiniMax-M2
$0.30$1.20204,8001.2576YesNo
Qwen3-VL-30B-A3B-Thinking
$0.20$1.00131,0721.10117YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.8729YesYes
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.9429YesYes
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.92122YesNo
DeepSeek-V3.1
$0.27$1.00131,0721.8426YesYes
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.8243YesNo