Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.64$3.381,048,5760.9342YesNo
DeepSeek-V4-Pro
$2.10$4.40512,0000.7238YesYes
DeepSeek-V4-Pro
fireworks-ai
fastest
--1,048,5761.4149YesNo
DeepSeek-V4-Pro
$1.74$3.4865,5360.4919YesYes
DeepSeek-V4-Flash
novita
cheapest fastest
$0.14$0.281,048,5760.8177YesNo
DeepSeek-V4-Flash
---0.7256YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5760.4552YesYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.26137YesYes
gemma-4-31B-it
$0.14$0.40262,1443.3211YesYes
gemma-4-31B-it
together
fastest
$0.39$0.97262,1440.6826YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.5819YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.9533YesNo
Kimi-K2.6
together
fastest
$1.20$4.50262,1440.2737YesYes
Kimi-K2.6
--262,1442.7227YesNo
Kimi-K2.6
$0.75$3.50262,1440.5531YesNo
GLM-5.1
$1.40$4.40202,7520.6144YesYes
GLM-5.1
--202,7521.5540YesNo
GLM-5.1
---4.1029YesNo
GLM-5.1
deepinfra
cheapest fastest
$1.05$3.50202,7520.7866YesYes
gemma-4-26B-A4B-it
novita
fastest
$0.13$0.40262,1440.7752YesNo
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.2447YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.4350NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.231,620NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.8059NoYes
Llama-3.1-8B-Instruct
---0.34147YesYes
Qwen3.5-9B
together
cheapest fastest
$0.10$0.15262,1440.4887YesYes
Qwen3.5-9B
$0.12$0.18262,1440.4240YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.39656YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.48103NoYes
gpt-oss-20b
$0.05$0.20131,0720.89154YesYes
gpt-oss-20b
$0.05$0.20131,0720.3486YesNo
gpt-oss-20b
$0.05$0.20131,0720.6467YesNo
gpt-oss-20b
$0.05$0.18131,0720.2987YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.18130YesYes
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.35105YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.596YesYes
gpt-oss-120b
$0.15$0.75131,0720.28440YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.45192YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.221,082YesNo
gpt-oss-120b
-------
gpt-oss-120b
$0.10$0.40131,0720.81110YesYes
gpt-oss-120b
$0.15$0.60131,0720.23114YesYes
gpt-oss-120b
$0.15$0.60131,0720.48179YesNo
gpt-oss-120b
---0.35176YesYes
gpt-oss-120b
$0.09$0.47131,0720.29101YesYes
Llama-3.2-1B-Instruct
--131,0000.5491NoNo
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8000.9835YesNo
MiniMax-M2.7
$0.30$1.20196,6080.4135NoNo
MiniMax-M2.7
fireworks-ai
fastest
--196,6081.5485YesNo
Qwen3-Coder-Next
$0.20$1.50262,1441.09120YesNo
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.5684NoYes
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.31273YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.5427YesNo
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.0417NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.8758NoNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.4650YesYes
Llama-3.3-70B-Instruct
---0.4174YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.3330YesYes
Kimi-K2.5
novita
cheapest
$0.60$3.00262,1441.0635YesYes
Kimi-K2.5
-------
Kimi-K2.5
fireworks-ai
fastest
--262,1440.3468YesNo
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.7284YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.79101YesNo
Step-3.5-Flash
$0.10$0.30262,1440.5040YesNo
GLM-4.7-Flash
$0.07$0.40200,0000.9474NoNo
GLM-4.7-Flash
-------
Qwen3-8B
$0.07$0.1840,9600.8456YesNo
QwQ-32B
$0.18$0.20131,0721.0128NoYes
DeepSeek-R1
$0.70$2.5064,0001.7722NoYes
DeepSeek-R1
-------
DeepSeek-R1
-------
DeepSeek-R1
-------
DeepSeek-OCR
$0.03$0.038,1921.04205NoNo
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1440.77115YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.2874YesYes
Qwen3.5-27B
$0.30$2.40262,1440.7971YesNo
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1441.1751YesNo
Qwen3.5-397B-A17B
$0.60$3.60262,1440.5292YesYes
Qwen3.5-397B-A17B
---0.79100YesYes
Qwen3.5-397B-A17B
ovhcloud
fastest
$0.71$4.25262,1440.35113YesYes
Qwen3.5-397B-A17B
$0.49$3.60262,1440.5324YesYes
Ling-2.6-1T
$0.30$2.50262,1440.9784YesNo
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.7563YesNo
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.24137YesYes
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8001.0263YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.64132YesNo
gpt-oss-safeguard-20b
--131,0720.28708YesNo
gemma-3-27b-it
---4.8037YesNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.8895YesNo
GLM-5
novita
cheapest
$1.00$3.20202,8001.2032YesNo
GLM-5
together
fastest
$1.00$3.20202,7520.6065YesYes
GLM-5
---3.7835YesNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Qwen3-30B-A3B
$0.09$0.4540,9600.7460YesNo
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.45344YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3533NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.7233YesYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.7737NoYes
DeepSeek-V3
$0.40$1.3064,0001.1236YesNo
DeepSeek-V3
-------
DeepSeek-V3-0324
$0.27$1.12163,8400.8537YesYes
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
GLM-4.7
novita
cheapest
$0.60$2.20204,8001.4059YesNo
GLM-4.7
cerebras
fastest
---0.29480YesNo
GLM-4.7
---2.2121YesNo
GLM-5.1-FP8
fireworks-ai
fastest
--202,7521.3445YesNo
GLM-5.1-FP8
---3.9430YesNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.24281YesNo
Qwen3-32B
$0.10$0.4540,9600.6658NoNo
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.9728YesYes
Qwen3-32B
$0.09$0.2532,7680.2244YesYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.87115NoYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.3936NoYes
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.9941YesYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6285NoNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.7560YesNo
tiny-aya-earth
---0.36119NoNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.8992YesNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.5320NoYes
WizardLM-2-8x22B
$0.62$0.6265,5350.7710NoNo
Apertus-70B-Instruct-2509
$0.82$2.92-0.7960NoYes
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.2948YesYes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.24614NoNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.9924YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.2321YesYes
Qwen3-235B-A22B-Instruct-2507
---0.4354YesYes
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.6037YesNo
Kimi-K2-Instruct
$0.57$2.30131,0721.3324YesNo
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.38$1.55262,1441.2455YesYes
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
fastest
$2.00$2.00262,1440.5476NoNo
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.2459YesYes
tiny-aya-fire
---0.18122NoNo
gemma-3n-E4B-it
$0.06$0.1232,7680.4655NoYes
tiny-aya-global
---0.17122NoNo
tiny-aya-water
---0.22122NoNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.415NoNo
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.6065YesNo
GLM-4.5-Air
---2.2359YesNo
GLM-4.6V-Flash
novita
cheapest fastest
$0.30$0.90131,0721.0343YesNo
GLM-4.6V-Flash
---2.1436NoNo
GLM-4.7-FP8
---1.63102YesNo
c4ai-command-a-03-2025
---1.0550YesNo
MiniMax-M2.1
$0.30$1.20204,8001.5766YesNo
MiMo-V2-Flash
$0.10$0.30262,1441.39101NoNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.9825NoYes
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0720.69117YesYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.7964NoNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.79164YesNo
MiniMax-M2
$0.30$1.20204,8001.2181YesNo
Kimi-K2-Thinking
$0.60$2.50262,1441.0059YesNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1440.8317YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.6447NoNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.9528NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.38109YesNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.9328NoYes
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.88139NoNo
DeepSeek-V3.2
$0.27$0.40163,8401.5130YesYes
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.0625YesYes
Qwen3-VL-30B-A3B-Thinking
$0.20$1.00131,0720.96107YesNo
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8001.4560YesNo
GLM-4.6
---3.7520YesNo
command-a-translate-08-2025
---0.3368YesNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.8061NoYes
rnj-1-instruct
$0.15$0.1532,7680.15122YesYes
cogito-671b-v2.1
$1.25$1.25163,8400.2666NoNo
cogito-671b-v2.1
-------
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2578NoNo
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.2681YesYes
command-a-reasoning-08-2025
---0.9259YesNo
command-a-vision-07-2025
---0.1847NoNo
c4ai-command-r7b-arabic-02-2025
---0.2993YesNo
aya-vision-32b
---0.2723NoNo
Gemma-4-31B-it-pearl
$0.28$0.8632,0000.2945NoNo
aya-expanse-32b
---0.2241NoNo
c4ai-command-r-08-2024
---0.1858YesNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.7959YesNo
GLM-4.5
---2.1656YesNo
c4ai-command-r7b-12-2024
---0.2691YesNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5360.9730YesNo
GLM-4.5V
zai-org
fastest
---2.9032YesNo
GLM-4.6-FP8
---3.4615YesNo
GLM-4.6V-FP8
---2.5238YesNo
GLM-4.5V-FP8
---2.8639YesNo
GLM-4.6V
---2.5351YesNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0001.3012NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.6139NoNo
Qwen3-235B-A22B
$0.20$0.8040,9600.578NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.1023YesYes
GLM-4-32B-0414
$0.55$1.6632,0001.1044NoNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.4065YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.4347YesYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.8250NoYes
DeepSeek-R1-0528
$0.70$2.50163,8401.3322YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
MiniMax-M1-80k
$0.55$2.201,000,0001.1460YesNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0002.0420NoYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.1943NoNo
Qwen3-14B
$0.07$0.2040,9600.9650YesYes
DeepSeek-V3.1
$0.27$1.00131,0721.0132NoNo
DeepSeek-V3.1
-------
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.8334YesNo
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.3548NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.9117NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3584YesYes
Arch-Router-1.5B
---0.1075NoYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.8257NoYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.9771NoYes
Llama-3.1-70B-Instruct
---0.3983YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.1025YesYes
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.4719NoYes
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.37113NoNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.5329NoNo