Inference Providers

·

Metrics for top trending models

NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
$0.60$3.60512,2880.29129YesNo
DeepSeek-V4-Pro
novita
cheapest
$1.60$3.381,048,5760.5930YesNo
DeepSeek-V4-Pro
together
fastest
$1.74$3.48512,0000.7161YesYes
DeepSeek-V4-Pro
--1,048,5760.9560YesNo
DeepSeek-V4-Pro
$1.74$3.4865,5360.6321YesYes
gemma-4-31B-it
novita
fastest
$0.14$0.40262,1440.7048YesYes
gemma-4-31B-it
$0.39$0.97262,1440.5510YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.4114YesYes
DeepSeek-V4-Flash
novita
cheapest
$0.14$0.281,048,5760.8669YesNo
DeepSeek-V4-Flash
fireworks-ai
fastest
---0.6474YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5760.7236YesYes
Qwen3.6-27B
---0.2568YesYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.26142YesYes
gemma-4-26B-A4B-it
$0.13$0.40262,1441.3427NoNo
gemma-4-26B-A4B-it
deepinfra
cheapest fastest
$0.07$0.34262,1440.5949YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.3030YesNo
Kimi-K2.6
$1.20$4.50262,1440.4980YesYes
Kimi-K2.6
fireworks-ai
fastest
--262,1440.3187YesNo
Kimi-K2.6
$0.75$3.50262,1440.7073YesNo
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.71141NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
nscale
fastest
$0.06$0.06131,0720.58147NoYes
Llama-3.1-8B-Instruct
---0.32146YesYes
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.2576YesYes
Qwen3.5-9B
ovhcloud
cheapest
$0.12$0.18262,1440.4042YesYes
gpt-oss-120b
$0.15$0.75131,0720.27435YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.4195YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.161,065YesNo
gpt-oss-120b
-------
gpt-oss-120b
$0.10$0.40131,0720.47101YesYes
gpt-oss-120b
$0.15$0.60131,0720.3081YesYes
gpt-oss-120b
$0.15$0.60131,0720.49155YesNo
gpt-oss-120b
---0.39155YesYes
gpt-oss-120b
$0.09$0.47131,0720.26131YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.24701YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.50180NoYes
gpt-oss-20b
$0.05$0.20131,0720.60162YesYes
gpt-oss-20b
$0.05$0.20131,0720.2678NoNo
gpt-oss-20b
$0.05$0.20131,0720.52181YesNo
gpt-oss-20b
$0.05$0.18131,0720.1885YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8002.1838YesNo
MiniMax-M2.7
$0.30$1.20196,6080.3165YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.42168YesNo
GLM-5.1
$1.40$4.40202,7520.5572YesYes
GLM-5.1
--202,7520.8557YesNo
GLM-5.1
---4.1527YesNo
GLM-5.1
deepinfra
cheapest fastest
$1.05$3.50202,7520.8384YesYes
Meta-Llama-3-8B-Instruct
-------
Meta-Llama-3-8B-Instruct
$0.14$0.148,1920.21185NoYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.17121YesYes
Qwen3-Coder-Next
$0.20$1.50262,1441.26121YesNo
Qwen3-VL-8B-Instruct
$0.08$0.50131,0720.7752YesNo
DeepSeek-R1
$0.70$2.5064,0002.3926YesYes
DeepSeek-R1
-------
DeepSeek-R1
-------
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.61151YesYes
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.5747NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.32149YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.54129NoYes
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.40126YesYes
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.4026YesYes
Kimi-K2.5
novita
cheapest
$0.60$3.00262,1441.6234NoNo
Kimi-K2.5
fireworks-ai
fastest
--262,1440.3168YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.86106YesNo
Qwen3.5-122B-A10B
$0.40$3.20262,1440.7783YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest fastest
$0.29$2.40262,1440.4289YesYes
GLM-4.7-Flash
novita
cheapest fastest
$0.07$0.40200,0001.9468NoNo
GLM-4.7-Flash
---2.6556NoNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.22325NoNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4928YesNo
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.5238NoNo
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.3368NoNo
Llama-3.3-70B-Instruct
$1.04$1.04131,0720.3393YesYes
Llama-3.3-70B-Instruct
---0.3886YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.4332NoNo
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.51332NoYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1441.2951YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.5793YesYes
Qwen3.5-397B-A17B
---0.4183YesYes
Qwen3.5-397B-A17B
$0.71$4.25262,1442.2983YesYes
Qwen3.5-397B-A17B
$0.49$3.60262,1440.4372YesYes
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.9539YesNo
GLM-4.5-Air
---3.4538NoNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.48159YesYes
DeepSeek-OCR
$0.03$0.038,1920.66191NoNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.52184NoYes
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8001.0368YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.57114YesNo
Qwen3-14B
$0.07$0.2040,9600.5395YesNo
gpt-oss-safeguard-20b
--131,0720.65608YesNo
Qwen3-8B
$0.07$0.1840,9600.55135YesNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8001.6740YesNo
GLM-4.7
cerebras
fastest
---0.19350YesNo
GLM-4.7
---2.2121YesNo
tiny-aya-global
---0.19123NoNo
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1441.1456YesYes
Qwen3-Coder-480B-A35B-Instruct
-------
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.41377YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3057NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.4861YesYes
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.5748NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.5237NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.4185YesYes
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0721.4752YesYes
c4ai-command-a-03-2025
---0.2562YesNo
tiny-aya-fire
---0.32122NoNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.2112NoNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6480NoNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.8838YesNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.5924NoYes
DeepSeek-V3.2
$0.27$0.40163,8401.3035YesYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.5829NoYes
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.7533YesYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0721.0862YesNo
GLM-5
novita
cheapest
$1.00$3.20202,8003.2135NoNo
GLM-5
together
fastest
$1.00$3.20202,7520.53147YesYes
GLM-5
---4.5234NoNo
GLM-5.1-FP8
fireworks-ai
fastest
--202,7522.4929YesNo
GLM-5.1-FP8
---4.1727NoNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0720.9753YesNo
GLM-4.6V-Flash
zai-org
fastest
---4.7160NoNo
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.4977NoYes
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8001.5052YesNo
GLM-4.6
---3.7520NoNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.3148YesYes
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.6513YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.1944YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
---0.3991YesYes
gemma-3n-E4B-it
$0.06$0.1232,7680.4643NoYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
gemma-3-27b-it
---0.4646YesYes
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.4620YesNo
Kimi-K2-Instruct
$0.57$2.30131,0721.4220YesNo
MiniMax-M1-80k
$0.55$2.201,000,0001.0061YesNo
DeepSeek-R1-0528
$0.70$2.50163,8401.7524YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.5519NoYes
Qwen3.5-27B
$0.30$2.40262,1441.2039YesNo
Arch-Router-1.5B
---0.2373NoYes
Step-3.5-Flash
$0.10$0.30262,1440.4143YesNo
tiny-aya-water
---0.33121NoNo
DeepSeek-V3-0324
$0.27$1.12163,8401.3329YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
QwQ-32B
$0.18$0.20131,0720.6340YesYes
command-a-vision-07-2025
---0.1547NoNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2858NoNo
cogito-671b-v2.1
$1.25$1.25163,8400.4556NoNo
cogito-671b-v2.1
-------
rnj-1-instruct
$0.15$0.1532,7680.18115YesYes
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.22255YesNo
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.5948YesYes
Qwen3-32B
$0.09$0.2532,7680.1843YesYes
Ling-2.6-1T
$0.30$2.50262,1442.0277YesNo
Qwen3-235B-A22B
$0.20$0.8040,9601.858NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.0316YesNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.5450NoYes
tiny-aya-earth
---0.35120NoNo
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.58168NoNo
command-a-translate-08-2025
---0.3268YesNo
Gemma-4-31B-it-pearl
$0.28$0.86262,1440.9325YesNo
command-a-reasoning-08-2025
---0.2886YesNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.8146YesNo
GLM-4.5
---2.3344NoNo
c4ai-command-r7b-arabic-02-2025
---0.26106YesNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5360.9413YesNo
GLM-4.5V
zai-org
fastest
---4.1916NoNo
aya-vision-32b
---0.2236NoNo
GLM-4.6-FP8
---3.4615YesNo
GLM-4.5V-FP8
---4.1037NoNo
GLM-4.6V
---2.6946YesNo
aya-expanse-32b
---0.2438NoNo
GLM-4.6V-FP8
---2.1755YesNo
c4ai-command-r-08-2024
---0.3629YesNo
GLM-4.7-FP8
---1.63102YesNo
c4ai-command-r7b-12-2024
---0.2567YesNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.4455NoYes
MiniMax-M2
$0.30$1.20204,8001.0667YesNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0721.55104YesNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.3741YesNo
Apertus-8B-Instruct-2509
$0.10$0.20-0.6897NoYes
Apertus-70B-Instruct-2509
$0.82$2.92-0.9760NoYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.4650NoYes
DeepSeek-V3.1
$0.27$1.00131,0721.7023YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.6348YesYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.2266YesYes
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.7733YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.4621YesYes
Qwen3-VL-30B-A3B-Thinking
$0.20$1.00131,0720.99113YesNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.2442NoNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.8422YesYes
Kimi-K2-Thinking
$0.60$2.50262,1441.1657NoNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.4732NoNo
GLM-4-32B-0414
$0.55$1.6632,0001.2436NoNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.85102NoNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.62142NoYes
DeepSeek-V3
$0.40$1.3064,0001.3232YesNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.4574NoNo
Llama-3.1-70B-Instruct
---0.3286YesYes
WizardLM-2-8x22B
$0.62$0.6265,5351.0411NoNo
MiniMax-M2.1
$0.30$1.20204,8001.5061YesNo