Inference Providers

·

Metrics for top trending models

Qwen3.5-9B
$0.10$0.15262,1440.2358YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1441.6392YesNo
MiniMax-M2.5
-------
MiniMax-M2.5
---0.70155YesNo
Qwen3.5-27B
$0.30$2.40262,1440.7464YesNo
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1440.7846YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1441.4450YesNo
GLM-5
novita
cheapest
$1.00$3.20202,8001.3732YesNo
GLM-5
together
fastest
$1.00$3.20202,7520.9882YesYes
GLM-5
--202,7521.1174YesNo
GLM-5
---3.2938YesNo
Kimi-K2.5
$0.60$3.00262,1441.0726NoNo
Kimi-K2.5
together
cheapest fastest
$0.50$2.80262,1440.44131YesYes
Kimi-K2.5
--262,1440.52108YesNo
Qwen3-Coder-Next
$0.20$1.50262,1440.69122YesNo
gpt-oss-120b
$0.15$0.75131,0720.08435YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.3677YesYes
gpt-oss-120b
sambanova
fastest
$0.22$0.59131,0720.39636YesYes
gpt-oss-120b
$0.10$0.40131,0720.7886YesYes
gpt-oss-120b
$0.30$0.30131,0720.4785YesNo
gpt-oss-120b
$0.15$0.60131,0720.3367YesYes
gpt-oss-120b
$0.15$0.60131,0721.86103YesNo
gpt-oss-120b
---0.46156YesYes
gpt-oss-120b
$0.09$0.47131,0720.3178YesYes
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.5930YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8401.8148YesNo
Qwen3.5-122B-A10B
$0.40$3.20262,1440.65115YesNo
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.13782YesNo
gpt-oss-20b
$0.04$0.15131,0720.3374NoYes
gpt-oss-20b
$0.05$0.20131,0720.81111YesYes
gpt-oss-20b
hyperbolic
cheapest
$0.10$0.10131,0720.5999YesNo
gpt-oss-20b
$0.05$0.20131,0720.27122YesYes
gpt-oss-20b
$0.05$0.20131,0721.6180YesNo
gpt-oss-20b
$0.05$0.18131,0720.3671YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.6481NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.211,128NoNo
Llama-3.1-8B-Instruct
$0.10$0.2016,3841.06434YesYes
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.9159NoYes
Llama-3.1-8B-Instruct
---0.30121YesYes
Llama-3.1-8B-Instruct
$0.11$0.11131,0720.3544YesNo
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.4493NoNo
DeepSeek-R1
$0.70$2.5064,0001.5428YesNo
DeepSeek-R1
sambanova
fastest
---0.43207YesYes
DeepSeek-R1
hyperbolic
cheapest
$2.00$2.00163,8400.7496NoNo
DeepSeek-R1
$3.00$7.00163,8400.4697NoYes
MiMo-V2-Flash
$0.10$0.30262,1441.2695YesNo
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.17153YesYes
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9600.8454YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.45138YesNo
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.9959YesNo
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.18126NoYes
GLM-4.7-Flash
novita
cheapest fastest
$0.07$0.40200,0001.6952NoNo
GLM-4.7-Flash
---2.6146NoNo
Llama-3.3-70B-Instruct
$0.59$0.79131,0720.25253YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.7540YesNo
Llama-3.3-70B-Instruct
sambanova
fastest
$0.60$1.20131,0720.41283YesYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.9116NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.68122YesNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.33108YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.43119NoNo
Llama-3.3-70B-Instruct
---0.3780YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.3939YesYes
gemma-3-27b-it
---0.4547YesYes
tiny-aya-global
---0.31120NoNo
Llama-3.2-1B-Instruct
--131,0000.68188NoNo
Qwen3-Coder-30B-A3B-Instruct
---0.3467YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest fastest
$0.07$0.26262,1440.3576YesYes
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30$1.30262,1441.1226YesYes
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.8368YesNo
Qwen3-Coder-480B-A35B-Instruct
together
fastest
$2.00$2.00262,1440.3874YesYes
Kimi-K2-Instruct-0905
groq
fastest
--262,1440.17182YesNo
Kimi-K2-Instruct-0905
novita
cheapest
$0.60$2.50262,1441.4434YesYes
Kimi-K2-Instruct-0905
-------
Kimi-K2-Instruct-0905
--262,1440.7633YesNo
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.44352YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.8065NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.9032YesYes
MiniMax-M2.1
-------
MiniMax-M2.1
--204,8001.45105YesNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8003.0814YesNo
GLM-4.7
fireworks-ai
fastest
--202,7521.5461YesNo
GLM-4.7
-------
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.90139NoNo
Qwen2.5-VL-7B-Instruct
$0.20$0.2032,7680.57113NoNo
DeepSeek-OCR
$0.03$0.038,1921.56200NoNo
GLM-4.6V
---4.3219NoNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.8627YesNo
Qwen3-30B-A3B
$0.09$0.4540,9601.43111YesNo
gemma-3n-E4B-it
$0.02$0.0432,7680.2052NoYes
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.9628NoNo
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.7687YesNo
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.7247NoNo
DeepSeek-R1-Distill-Llama-70B
sambanova
fastest
$0.70$1.40131,0720.87191NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.8117NoYes
DeepSeek-R1-Distill-Llama-70B
---0.5338NoYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.7566NoNo
Apertus-8B-Instruct-2509
$0.10$0.20-0.89118NoYes
Kimi-K2-Instruct
$0.57$2.30131,0721.4631YesNo
Kimi-K2-Instruct
-------
gpt-oss-safeguard-20b
--131,0720.12849YesNo
Kimi-K2-Thinking
novita
cheapest
$0.60$2.50262,1440.9434YesNo
Kimi-K2-Thinking
-------
Kimi-K2-Thinking
fireworks-ai
fastest
---0.5370YesNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0720.9519YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.9317YesYes
Qwen3-235B-A22B-Instruct-2507
$2.00$2.00262,1440.8125YesNo
Qwen3-235B-A22B-Instruct-2507
together
fastest
$0.20$0.60262,1440.3545YesYes
Qwen3-235B-A22B-Instruct-2507
---0.3943YesYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.9334YesYes
L3-8B-Lunaris-v1
$0.05$0.058,1920.7234NoNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.9849YesNo
Apriel-1.6-15b-Thinker
$0.00$0.00131,0720.16150NoNo
DeepSeek-V3
$0.40$1.3064,0001.3130YesNo
DeepSeek-V3
together
cheapest fastest
$1.25$1.25131,0720.7832YesYes
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8401.8023YesNo
DeepSeek-R1-0528
sambanova
fastest
$5.00$7.00131,0721.69121NoNo
DeepSeek-R1-0528
$3.00$3.00163,8400.7796NoNo
DeepSeek-R1-0528
$3.00$7.00163,8400.74103NoYes
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20$0.70131,0720.90116YesYes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
--262,1440.33148YesNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.9194YesNo
Llama-3.1-70B-Instruct
---0.2782YesYes
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0720.9737NoNo
GLM-4.5-Air
zai-org
fastest
---2.0366YesNo
Olmo-3.1-32B-Think
$0.15$0.50-1.6674NoNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Llama-4-Maverick-17B-128E-Instruct
-------
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0721.43318YesYes
c4ai-command-a-03-2025
---0.2453YesNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5360.8642YesNo
GLM-4.5V
zai-org
fastest
---2.1254YesNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.8362NoYes
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.7123NoYes
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.69104NoNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.8654YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.6067NoNo
GLM-4-32B-0414
$0.55$1.6632,0001.0642NoNo
Llama-4-Maverick-17B-128E-Instruct-FP8
novita
cheapest fastest
$0.27$0.851,048,5760.4358NoNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.3252YesYes
Qwen3-235B-A22B
$0.20$0.8040,9600.794NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0000.9623YesNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.16239YesNo
Qwen3-32B
$0.10$0.4540,9600.3982NoNo
Qwen3-32B
$0.40$0.8032,7682.75191YesYes
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.8627YesYes
Qwen3-32B
$0.09$0.2532,7680.3838YesYes
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.2321NoYes
ERNIE-4.5-21B-A3B-PT
$0.07$0.28120,0000.9681NoNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.7927NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.3566YesNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.6353YesNo
GLM-4.5
---2.9045YesNo
Mixtral-8x22B-Instruct-v0.1
nscale
cheapest
$1.20$1.2065,5360.9526NoYes
Mixtral-8x22B-Instruct-v0.1
fireworks-ai
fastest
$1.20$1.2065,5360.2368NoNo
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.6224YesYes
DeepSeek-V3.1
$0.60$1.70131,0720.4241YesYes
DeepSeek-V3.1
fireworks-ai
fastest
--163,8400.2977YesNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.9568YesNo
Qwen3-Next-80B-A3B-Instruct
hyperbolic
cheapest fastest
$0.30$0.30262,1440.49179YesNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50262,1440.36120YesYes
tiny-aya-water
---0.30120NoNo
command-a-reasoning-08-2025
---0.2378YesNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.3272NoNo
rnj-1-instruct
$0.15$0.1532,7680.18124YesYes
Qwen3-Coder-Next-FP8
$0.50$1.20262,1440.9258YesYes
GLM-4.7-FP8
together
cheapest fastest
$0.45$2.00202,7520.6671YesNo
GLM-4.7-FP8
---2.1657YesNo
WizardLM-2-8x22B
$0.62$0.6265,5351.1315NoNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.7056NoNo
c4ai-command-r7b-12-2024
---0.2082YesNo
MiniMax-M2
$0.30$1.20204,8003.3622YesNo
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0720.8663YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.60132YesNo
Apertus-70B-Instruct-2509
$0.82$2.92-1.0158NoYes
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.1625YesYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.7557NoYes
Molmo2-8B
---1.6944NoYes
Qwen2.5-VL-72B-Instruct
hyperbolic
cheapest fastest
$0.60$0.6032,7681.5433NoNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.3831NoYes
QwQ-32B
$0.18$0.20131,0721.0028NoYes
command-a-vision-07-2025
---0.2235NoNo
GLM-4.6
novita
cheapest
$0.55$2.20204,8002.0115YesNo
GLM-4.6
together
fastest
$0.60$2.20202,7520.6169YesYes
GLM-4.6
---4.1215NoNo
Qwen3-14B
$0.07$0.2040,9600.8645YesNo
c4ai-command-r-08-2024
---0.1664YesNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.7036NoNo
cogito-671b-v2.1
together
cheapest fastest
$1.25$1.25163,8400.3074NoNo
cogito-671b-v2.1
--163,8400.3439YesNo
c4ai-command-r7b-arabic-02-2025
---0.1892YesNo
aya-vision-32b
---0.2437NoNo
aya-expanse-32b
---0.1942NoNo
command-a-translate-08-2025
---0.3366YesNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.99137YesNo
Qwen3-Next-80B-A3B-Thinking
hyperbolic
cheapest fastest
$0.30$0.30262,1440.52197YesNo
GLM-4.5V-FP8
---1.9652YesNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0721.0521YesNo
GLM-4.6V-Flash
zai-org
fastest
---2.0550YesNo
GLM-4.6V-FP8
---4.3423NoNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.6689NoYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.2345YesYes
Llama-3.3-Swallow-70B-Instruct-v0.4
$0.60$1.20131,0723.82117NoYes
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.5724YesYes
Olmo-3.1-32B-Instruct
$0.20$0.60-1.4744YesYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.2133NoNo
tiny-aya-fire
---0.24123NoNo
ERNIE-4.5-VL-28B-A3B-PT
$0.14$0.5630,0001.0060NoNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.4756YesYes
tiny-aya-earth
---0.32120NoNo
MiniMax-M1-80k
$0.55$2.201,000,0002.0434YesNo
Arch-Router-1.5B
---0.1179NoYes
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.9214NoNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.6747NoYes
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8401.0030YesNo
DeepSeek-V3-0324
sambanova
fastest
$3.00$4.50131,0720.61148YesYes
DeepSeek-V3-0324
$1.25$1.25163,8400.7537YesNo
DeepSeek-V3-0324
$1.25$1.25131,0720.5735YesYes
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.2078YesYes
GLM-4.5-Air-FP8
$0.20$1.10131,0720.86130YesNo