Inference Providers

·

Metrics for top trending models

GLM-5.2
novita
cheapest fastest
$1.40$4.401,048,5760.9744YesYes
GLM-5.2
-------
GLM-5.2
-------
GLM-5.2
---3.4941NoNo
GLM-5.2
-------
Ornith-1.0-35B
$0.14$1.00262,1440.27107YesYes
Qwen3.6-27B
ovhcloud
cheapest fastest
$0.47$3.19262,1440.4668YesYes
Qwen3.6-27B
$0.32$3.20262,1440.6546YesYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.4025NoYes
gemma-4-31B-it
$0.14$0.40262,1440.9651YesYes
gemma-4-31B-it
cerebras
fastest
---0.32843YesNo
gemma-4-31B-it
$0.39$0.97262,1440.2566YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.5412YesYes
Kimi-K2.7-Code
$0.95$4.00262,1441.2447YesYes
Kimi-K2.7-Code
together
fastest
$0.95$4.00262,1441.88132YesYes
Kimi-K2.7-Code
$0.95$4.00262,1441.0065YesNo
Kimi-K2.7-Code
deepinfra
cheapest
$0.74$3.50262,1440.6872YesYes
DeepSeek-V4-Pro
$1.60$3.201,048,5761.2335YesNo
DeepSeek-V4-Pro
together
fastest
$1.74$3.48512,0000.7573YesYes
DeepSeek-V4-Pro
$1.74$3.481,048,5762.0738YesNo
DeepSeek-V4-Pro
deepinfra
cheapest
$1.30$2.601,048,5760.8127YesYes
DeepSeek-V4-Flash
novita
fastest
$0.14$0.281,048,5761.4480YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5760.4973YesNo
DeepSeek-V4-Flash
deepinfra
cheapest
$0.09$0.181,048,5760.8918YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.73130NoNo
Llama-3.1-8B-Instruct
nscale
fastest
$0.06$0.06131,0720.57152NoNo
Llama-3.1-8B-Instruct
---0.30150YesYes
Llama-3.1-8B-Instruct
$0.02$0.05131,0720.3325NoYes
MiniMax-M3
novita
cheapest
$0.30$1.201,000,0001.0649YesNo
MiniMax-M3
$0.30$1.20524,2880.6762YesYes
MiniMax-M3
fireworks-ai
fastest
$0.30$1.20512,0000.69118YesNo
MiniMax-M3
$0.30$1.20524,2880.4514YesNo
Qwen3.5-9B
$0.17$0.25262,1440.3261YesYes
Qwen3.5-9B
$0.12$0.18262,1441.2136NoYes
Qwen3.5-9B
deepinfra
cheapest fastest
$0.10$0.15262,1440.5868YesYes
gemma-4-26B-A4B-it
novita
fastest
$0.13$0.40262,1441.3227YesNo
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.4425YesYes
Ornith-1.0-35B-FP8
$0.14$1.00262,1440.31109YesYes
Qwen3-Coder-Next
$0.20$1.50262,1440.99114YesNo
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.34611YesNo
gpt-oss-20b
$0.04$0.15131,0720.29136NoYes
gpt-oss-20b
$0.05$0.20131,0720.50168YesYes
gpt-oss-20b
$0.05$0.20131,0720.25120YesYes
gpt-oss-20b
$0.07$0.30131,0721.4847YesNo
gpt-oss-20b
$0.05$0.18131,0720.2676YesYes
gpt-oss-20b
deepinfra
cheapest
$0.03$0.14131,0721.20117YesYes
DeepSeek-R1
$0.70$2.5064,0000.7620NoYes
Qwen3-8B
$0.07$0.1840,9600.54135YesNo
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.29110YesYes
gpt-oss-120b
$0.15$0.75131,0720.30421YesNo
gpt-oss-120b
$0.05$0.25131,0720.7596YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.201,086NoNo
gpt-oss-120b
$0.10$0.40131,0720.54105YesYes
gpt-oss-120b
$0.15$0.60131,0720.9386YesYes
gpt-oss-120b
$0.15$0.60131,0720.51149YesNo
gpt-oss-120b
---0.40132YesYes
gpt-oss-120b
$0.09$0.47131,0720.3083YesYes
gpt-oss-120b
deepinfra
cheapest
$0.04$0.17131,0720.5337YesYes
Meta-Llama-3-8B-Instruct
-------
Meta-Llama-3-8B-Instruct
$0.14$0.148,1921.5494NoYes
MiMo-V2.5-Pro
$1.00$3.001,048,5760.4070YesNo
Step-3.7-Flash
$0.20$1.15262,1440.3660YesNo
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
$0.60$3.60512,2881.1858YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
fireworks-ai
cheapest fastest
$0.60$2.40262,1440.44119YesNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.6240NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.4393YesNo
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.1741YesNo
Kimi-K2.6
together
fastest
$1.20$4.50262,1440.8995YesYes
Kimi-K2.6
$0.95$4.00262,1440.6176YesNo
Kimi-K2.6
$0.75$3.50262,1440.9825YesNo
GLM-5.2-FP8
---3.7137YesNo
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
$1.00$5.00262,1441.0856YesYes
DeepSeek-OCR
$0.03$0.038,1921.15230NoNo
GLM-4.7-Flash
novita
cheapest
$0.07$0.40200,0000.8073YesNo
GLM-4.7-Flash
zai-org
fastest
---1.8278YesNo
GLM-4.7-Flash
$0.06$0.40202,7520.4755YesNo
phi-4
$0.07$0.1416,3840.3678NoYes
Qwen3-Coder-30B-A3B-Instruct
---0.4286YesYes
GLM-4.6V-Flash
novita
cheapest fastest
$0.30$0.90131,0721.4758YesNo
GLM-4.6V-Flash
---4.0446NoNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.55149NoYes
gemma-3-4b-it
$0.05$0.10131,0720.5266YesYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.58127YesYes
Qwen3.5-35B-A3B
$0.25$2.00262,1440.89106YesNo
Qwen3.5-35B-A3B
deepinfra
cheapest fastest
$0.14$1.00262,1440.35130YesYes
Step-3.5-Flash
$0.10$0.30262,1440.26125YesNo
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.6177YesNo
GLM-4.5-Air
---1.7566YesNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.27286YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.406,0000.7737YesNo
Llama-3.3-70B-Instruct
$1.04$1.04131,0720.8076YesYes
Llama-3.3-70B-Instruct
---0.3484YesNo
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.3233YesYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.5729NoYes
Qwen3.5-397B-A17B
$0.60$3.60262,1441.1051YesNo
Qwen3.5-397B-A17B
-------
Qwen3.5-397B-A17B
---4.1619YesYes
Qwen3.5-397B-A17B
ovhcloud
fastest
$0.71$4.25262,1440.43110YesNo
Qwen3.5-397B-A17B
deepinfra
cheapest
$0.45$3.00262,1440.5214YesYes
GLM-5
$1.00$3.20202,8002.3035NoNo
GLM-5
-------
GLM-5
zai-org
fastest
---3.2938YesNo
GLM-5
deepinfra
cheapest
$0.60$2.08202,7523.0716YesNo
Qwen3-235B-A22B-Instruct-2507
$0.09$0.58131,0720.6335YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.6018YesYes
Qwen3-235B-A22B-Instruct-2507
together
fastest
$0.20$0.60262,1440.2853YesYes
Qwen3-235B-A22B-Instruct-2507
---0.6135YesYes
Qwen3-235B-A22B-Instruct-2507
deepinfra
cheapest
$0.09$0.10262,1440.4724YesYes
Qwen3.5-27B
novita
cheapest fastest
$0.30$2.40262,1440.9159YesNo
Qwen3.5-27B
$0.26$2.60262,1440.2754YesYes
MiniMax-M2.5
$0.30$1.20204,8001.1552YesNo
MiniMax-M2.5
deepinfra
cheapest fastest
$0.15$1.15196,6080.62105YesNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.5539NoYes
Apertus-8B-Instruct-2509
$0.10$0.20-1.29109NoYes
DeepSeek-R1-Distill-Llama-70B
novita
cheapest
$0.80$0.808,1920.5929NoNo
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3976YesYes
gemma-3-12b-it
$0.05$0.15131,0720.2732YesYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
GLM-4.7
$0.60$2.20204,8002.1233YesNo
GLM-4.7
cerebras
fastest
---0.27104YesNo
GLM-4.7
-------
GLM-4.7
deepinfra
cheapest
$0.40$1.75202,7520.5938YesNo
gemma-3-27b-it
scaleway
fastest
---0.6346YesYes
gemma-3-27b-it
deepinfra
cheapest
$0.08$0.16131,0720.4018YesNo
MiniMax-M2
$0.30$1.20204,8001.1651YesNo
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.58166NoYes
MiniMax-M2.1
$0.30$1.20204,8001.4846YesNo
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0721.00288YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3450NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.6660YesYes
Llama-4-Scout-17B-16E-Instruct
$0.10$0.30327,6800.3331YesYes
Bielik-11B-v3.0-Instruct
$0.10$0.20-1.7644YesYes
GLM-5.1
together
fastest
$1.40$4.40202,7521.3445YesYes
GLM-5.1
$1.40$4.40202,7521.8542YesNo
GLM-5.1
---3.3537NoNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7520.7319YesYes
Qwen3.5-122B-A10B
$0.40$3.20262,1440.6687YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest fastest
$0.29$2.40262,1440.59105YesNo
aya-expanse-32b
---0.2342NoNo
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1441.2150YesYes
c4ai-command-r7b-12-2024
---0.4476YesNo
Kimi-K2.5
$0.60$3.00262,1441.0537YesYes
Kimi-K2.5
-------
Kimi-K2.5
deepinfra
cheapest fastest
$0.45$2.25262,1440.7657YesNo
Llama-3.1-70B-Instruct
---0.4183YesYes
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.26257YesNo
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.5642YesYes
Qwen3-32B
$0.08$0.2840,9600.39104YesNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.4666NoNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6787NoNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.53162YesYes
WizardLM-2-8x22B
$0.62$0.6265,5350.8817NoNo
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0720.8598YesYes
gpt-oss-safeguard-20b
--131,0720.32698YesNo
MiniMax-M2.7
$0.30$1.20204,8001.8040YesNo
MiniMax-M2.7
together
fastest
$0.30$1.20196,6080.33124YesYes
MiniMax-M2.7
$0.30$1.20196,6080.87105YesNo
MiniMax-M2.7
deepinfra
cheapest
$0.25$1.00196,6080.7933YesNo
GLM-4.7-FP8
---1.63102NoNo
Apertus-70B-Instruct-2509
$0.82$2.92-1.3352NoYes
GLM-4.6V
---1.9860YesNo
GLM-4.5
---2.2852YesNo
tiny-aya-global
---0.19134NoNo
DeepSeek-R1-0528
$0.70$2.50163,8400.8522NoYes
DeepSeek-R1-0528
deepinfra
cheapest fastest
$0.50$2.15163,8400.5834YesNo
Llama-Guard-4-12B
together
fastest
$0.20$0.201,048,5760.1811NoNo
Llama-Guard-4-12B
deepinfra
cheapest
$0.18$0.18163,8400.328NoNo
Ling-2.6-1T
$0.30$2.50262,1440.8483YesNo
Kimi-K2-Instruct
$0.57$2.30131,0720.9137YesNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.5547YesYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.54147NoYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.58179NoYes
DeepSeek-V3
novita
fastest
$0.40$1.3064,0001.3132YesNo
DeepSeek-V3
deepinfra
cheapest
$0.32$0.89163,8401.4719YesYes
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.8344YesNo
Qwen2.5-72B-Instruct
novita
cheapest
$0.38$0.4032,0000.7223YesNo
Qwen2.5-72B-Instruct
deepinfra
fastest
$0.36$0.4032,7680.5030YesYes
Gemma-4-31B-it-pearl
$0.28$0.86262,1441.5320NoNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.72142YesNo
tiny-aya-fire
---0.21134NoNo
tiny-aya-earth
---0.21132NoNo
tiny-aya-water
---0.30133NoNo
DeepSeek-V3-0324
$0.27$1.12163,8401.3132YesNo
DeepSeek-V3-0324
deepinfra
cheapest fastest
$0.24$0.90163,8400.6342YesYes
c4ai-command-r-08-2024
---0.2957YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.4226YesYes
DeepSeek-V3.1-Terminus
deepinfra
cheapest fastest
$0.27$0.95163,8400.7158NoYes
command-a-vision-07-2025
---0.1448NoNo
Qwen3-14B
nscale
cheapest fastest
$0.07$0.2040,9600.5695YesYes
Qwen3-14B
$0.12$0.2440,9600.2676YesNo
GLM-5.1-FP8
fireworks-ai
cheapest fastest
$1.40$4.40202,7521.5341YesNo
GLM-5.1-FP8
---3.5335NoNo
DeepSeek-V3.2
novita
fastest
$0.27$0.40163,8401.3729YesYes
DeepSeek-V3.2
deepinfra
cheapest
$0.26$0.38163,8400.6819YesYes
c4ai-command-r7b-arabic-02-2025
---0.2583YesNo
aya-vision-32b
---0.2042NoNo
c4ai-command-a-03-2025
---0.3226YesNo
GLM-4.6
novita
fastest
$0.55$2.20204,8001.9234YesNo
GLM-4.6
-------
GLM-4.6
deepinfra
cheapest
$0.43$1.74202,7520.7226YesYes
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.1026NoYes
GLM-4.6V-FP8
---2.5558YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.67106NoNo
command-a-reasoning-08-2025
---0.4039YesNo
GLM-4.6-FP8
---3.4615NoNo
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5360.8944YesNo
GLM-4.5V
---2.5635YesNo
GLM-4.5V-FP8
---2.2168YesNo
command-a-translate-08-2025
---0.3768YesNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Qwen3-235B-A22B
novita
fastest
$0.20$0.8040,9600.5118NoNo
Qwen3-235B-A22B
nscale
cheapest
$0.20$0.6032,0000.6616YesYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.5477NoYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.5257NoYes
GLM-4-32B-0414
$0.55$1.6632,0000.8643NoNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-3.5047NoYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-2.0446YesYes
MiniMax-M1-80k
$0.55$2.201,000,0001.6843YesNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.6564YesYes
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.3170NoNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.3041NoNo
DeepSeek-V3.1
novita
fastest
$0.27$1.00131,0721.6626YesYes
DeepSeek-V3.1
deepinfra
cheapest
$0.21$0.79163,8400.917YesYes
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0721.3036YesNo
Qwen3-235B-A22B-Thinking-2507
deepinfra
cheapest fastest
$0.23$2.30262,1440.3650YesNo
gemma-3n-E4B-it
$0.06$0.1232,7680.2958NoYes
Kimi-K2-Instruct-0905
$0.60$2.50262,1440.7137YesYes
cogito-671b-v2.1
$1.25$1.25163,8400.2672NoNo
cogito-671b-v2.1
-------