Inference Providers

·

Metrics for top trending models

Kimi-K3
together
cheapest
$3.00$15.001,000,0001.8225YesYes
Kimi-K3
fireworks-ai
fastest
$3.00$15.001,048,5762.8938YesNo
GLM-5.2
$1.40$4.401,048,5761.2828YesNo
GLM-5.2
$1.40$4.40512,0000.4537YesYes
GLM-5.2
$1.40$4.401,048,5760.6741YesNo
GLM-5.2
zai-org
fastest
---2.9354YesNo
GLM-5.2
$2.05$6.27-0.6921YesNo
GLM-5.2
deepinfra
cheapest
$0.75$2.401,048,5760.7236YesYes
Inkling
together
cheapest fastest
$1.00$4.05524,2880.1984YesYes
Inkling
--1,048,5760.5282YesYes
Inkling
$1.00$4.05524,2881.046YesNo
Ternary-Bonsai-27B-gguf
$0.00$0.00262,1440.3395YesNo
Qwen3.6-35B-A3B
scaleway
fastest
$0.29$1.71-0.36183YesYes
Qwen3.6-35B-A3B
deepinfra
cheapest
$0.10$0.95262,1440.3723YesYes
Kimi-K2.7-Code
$0.95$4.00262,1441.1361YesYes
Kimi-K2.7-Code
together
fastest
$0.95$4.00262,1440.38134YesYes
Kimi-K2.7-Code
$0.95$4.00262,1440.6683YesNo
Kimi-K2.7-Code
deepinfra
cheapest
$0.74$3.50262,1440.8666YesYes
DeepSeek-V4-Flash
$0.14$0.281,048,5761.3981YesNo
DeepSeek-V4-Flash
fireworks-ai
fastest
$0.14$0.281,048,5760.65114YesNo
DeepSeek-V4-Flash
deepinfra
cheapest
$0.09$0.181,048,5760.6714YesYes
Qwen3.6-27B
ovhcloud
cheapest fastest
$0.47$3.19262,1440.4776YesYes
Qwen3.6-27B
$0.32$3.20262,1440.3763YesYes
gemma-4-31B-it
$0.14$0.40262,1440.7977YesNo
gemma-4-31B-it
-------
gemma-4-31B-it
together
fastest
$0.39$0.97262,1440.1683YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.5918YesYes
Apertus-v1.5-70B
$0.82$2.92-0.8266YesNo
DeepSeek-V4-Pro
$1.60$3.201,048,5760.5049YesNo
DeepSeek-V4-Pro
$1.74$3.48512,0000.6042YesYes
DeepSeek-V4-Pro
fireworks-ai
fastest
$1.74$3.481,048,5761.2658YesNo
DeepSeek-V4-Pro
deepinfra
cheapest
$1.30$2.601,048,5760.4948YesYes
Apertus-v1.5-8B
$0.10$0.20-0.66152YesYes
Qwen3-8B
$0.07$0.1840,9600.63133YesYes
MiniMax-M3
novita
cheapest
$0.30$1.201,000,0000.9878YesNo
MiniMax-M3
$0.30$1.20524,2880.5481YesYes
MiniMax-M3
fireworks-ai
fastest
$0.30$1.20512,0000.92123YesNo
MiniMax-M3
$0.30$1.20524,2880.4721YesNo
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.53126NoNo
Llama-3.1-8B-Instruct
nscale
fastest
$0.06$0.06131,0720.49150NoYes
Llama-3.1-8B-Instruct
$0.02$0.05131,0720.4819YesNo
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.4523YesNo
Kimi-K2.6
together
fastest
$1.20$4.50262,1440.4889YesYes
Kimi-K2.6
$0.95$4.00262,1441.4072YesNo
Kimi-K2.6
$0.75$3.50262,1440.7850YesYes
Hy3
$0.14$0.58262,1440.3542YesYes
gpt-oss-120b
$0.15$0.75131,0720.29428YesNo
gpt-oss-120b
$0.05$0.25131,0720.4872YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.231,113YesNo
gpt-oss-120b
$0.10$0.40131,0720.57114YesYes
gpt-oss-120b
$0.15$0.60131,0720.84101YesYes
gpt-oss-120b
$0.15$0.60131,0721.02130YesNo
gpt-oss-120b
$0.17$0.68-0.39164YesYes
gpt-oss-120b
$0.09$0.47131,0720.30138YesYes
gpt-oss-120b
deepinfra
cheapest
$0.04$0.17131,0720.4933NoYes
gemma-4-26B-A4B-it
$0.13$0.40262,1441.5315NoNo
gemma-4-26B-A4B-it
scaleway
fastest
$0.29$0.57-0.41127YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.8311YesYes
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.3476YesYes
Qwen3.5-9B
$0.12$0.18262,1440.7237YesYes
Qwen3.5-9B
deepinfra
cheapest
$0.10$0.15262,1440.4259YesYes
Ornith-1.0-35B
$0.10$0.75262,1440.2724YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.32723YesNo
gpt-oss-20b
$0.04$0.15131,0720.3960NoYes
gpt-oss-20b
$0.05$0.20131,0720.55164YesYes
gpt-oss-20b
$0.05$0.20131,0720.27120YesYes
gpt-oss-20b
$0.07$0.30131,0720.3797YesNo
gpt-oss-20b
$0.05$0.18131,0720.3085YesYes
gpt-oss-20b
deepinfra
cheapest
$0.03$0.14131,0720.34104YesYes
DeepSeek-R1
$0.70$2.5064,0000.8118YesYes
Qwen3-Coder-Next
$0.20$1.50262,1440.85127YesNo
Qwen3-Coder-30B-A3B-Instruct
$0.23$0.91-0.30125YesNo
MiMo-V2.5
$0.40$2.00262,1442.1013YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
$0.60$3.60512,2880.3388YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
fireworks-ai
cheapest fastest
$0.60$2.40262,1440.48148YesNo
gemma-3-4b-it
$0.05$0.10131,0720.4324YesYes
GLM-5.2-FP8
---3.0751YesNo
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1440.7593YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.7388YesNo
Kimi-K2.5
novita
fastest
$0.60$3.00262,1440.5938YesYes
Kimi-K2.5
deepinfra
cheapest
$0.45$2.25262,1442.6116YesNo
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
$1.00$5.00262,1440.7248YesYes
Step-3.7-Flash
$0.20$1.15262,1440.22151YesNo
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.21130YesYes
Kimi-K2-Instruct-0905
$0.60$2.50262,1440.6141YesYes
Qwen3.5-397B-A17B
$0.60$3.60262,1441.7257YesNo
Qwen3.5-397B-A17B
$0.68$4.10-0.5393YesYes
Qwen3.5-397B-A17B
ovhcloud
fastest
$0.71$4.25262,1440.45124YesNo
Qwen3.5-397B-A17B
deepinfra
cheapest
$0.45$3.00262,1440.3532YesYes
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0720.6678YesNo
GLM-4.5-Air
zai-org
fastest
---1.8483YesNo
Qwen3.5-27B
novita
cheapest fastest
$0.30$2.40262,1440.8653YesNo
Qwen3.5-27B
$0.26$2.60262,1440.2640YesYes
GLM-4.7-Flash
novita
cheapest fastest
$0.07$0.40200,0000.7082YesNo
GLM-4.7-Flash
---2.0476NoNo
GLM-4.7-Flash
$0.06$0.40202,7520.4741YesNo
GLM-4.7
$0.60$2.20204,8001.4544YesNo
GLM-4.7
cerebras
fastest
---0.16329YesNo
GLM-4.7
---2.1657YesNo
GLM-4.7
deepinfra
cheapest
$0.40$1.75202,7520.4742YesNo
MiMo-V2.5-Pro
$1.00$3.001,048,5760.3379YesYes
Qwen3-32B
-------
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.5548YesNo
Qwen3-32B
deepinfra
fastest
$0.08$0.2840,9600.23100YesNo
Ling-2.6-1T
$0.30$2.50262,1440.7988YesNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.80142YesNo
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0720.68110YesYes
DeepSeek-OCR
$0.03$0.038,1920.69262NoNo
DeepSeek-V3
novita
fastest
$0.40$1.3064,0001.1634YesNo
DeepSeek-V3
deepinfra
cheapest
$0.32$0.89163,8400.5331YesYes
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.31253YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.406,0000.4739YesNo
Llama-3.3-70B-Instruct
$1.04$1.04131,0720.30111YesYes
Llama-3.3-70B-Instruct
$1.03$1.03-0.3777YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.4431YesYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.8591NoYes
Kimi-K2-Instruct
$0.57$2.30131,0720.6944YesNo
Qwen3.5-35B-A3B
novita
fastest
$0.25$2.00262,1440.75126YesNo
Qwen3.5-35B-A3B
deepinfra
cheapest
$0.14$1.00262,1440.2886YesYes
DeepSeek-V3.2
novita
fastest
$0.27$0.40163,8401.6528YesYes
DeepSeek-V3.2
deepinfra
cheapest
$0.26$0.38163,8400.6119YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.54140NoYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.6973YesYes
phi-4
$0.07$0.1416,3840.2874NoYes
GLM-5.1
-------
GLM-5.1
---3.7135YesNo
GLM-5.1
deepinfra
cheapest fastest
$1.05$3.50202,7520.8974YesYes
MiniMax-M2.7
$0.30$1.20204,8001.1630YesNo
MiniMax-M2.7
fireworks-ai
fastest
$0.30$1.20196,6080.63173YesNo
MiniMax-M2.7
deepinfra
cheapest
$0.25$1.00196,6082.0761NoNo
Qwen3-14B
nscale
cheapest fastest
$0.07$0.2040,9602.5681YesNo
Qwen3-14B
$0.12$0.2440,9600.2734YesNo
Llama-Guard-4-12B
together
fastest
$0.20$0.201,048,5760.1413NoNo
Llama-Guard-4-12B
deepinfra
cheapest
$0.18$0.18163,8400.328NoNo
Llama-4-Scout-17B-16E-Instruct
-------
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3851NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest fastest
$0.09$0.29890,0000.5673YesYes
Llama-4-Scout-17B-16E-Instruct
$0.10$0.30327,6800.4447YesYes
gemma-3-12b-it
$0.05$0.15131,0720.2452YesYes
aya-expanse-32b
---0.2743NoNo
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.60166NoNo
c4ai-command-r7b-12-2024
---0.2772YesNo
c4ai-command-r7b-arabic-02-2025
---0.3097YesNo
c4ai-command-a-03-2025
---1.9727YesNo
Apertus-70B-Instruct-2509
$0.82$2.92-0.8657NoYes
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.5494NoNo
gpt-oss-safeguard-20b
--131,0720.41656YesNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.7340YesYes
gemma-3-27b-it
scaleway
fastest
$0.29$0.57-0.3948YesYes
gemma-3-27b-it
deepinfra
cheapest
$0.08$0.16131,0720.3418YesYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.4436NoYes
Qwen2.5-72B-Instruct
novita
cheapest
$0.38$0.4032,0000.6325YesNo
Qwen2.5-72B-Instruct
deepinfra
fastest
$0.36$0.4032,7680.4525YesYes
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.7621NoNo
MiniMax-M2.1
$0.30$1.20204,8001.1954YesNo
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Bielik-11B-v3.0-Instruct
$0.40$0.40-0.9955YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.6034NoYes
Qwen3-235B-A22B
novita
fastest
$0.20$0.8040,9602.4421NoNo
Qwen3-235B-A22B
nscale
cheapest
$0.20$0.6032,0003.3915YesYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
tiny-aya-water
---0.26122NoNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.4195NoNo
tiny-aya-global
---0.25133NoNo
command-a-reasoning-08-2025
---0.18105YesNo
Step-3.5-Flash
$0.10$0.30262,1440.26148YesNo
Ternary-Bonsai-27B-AWQ-4bit
$0.00$0.00262,1440.3594YesNo
GLM-4.5
---2.4153YesNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0721.4749YesNo
GLM-4.6V-Flash
zai-org
fastest
---3.9250NoNo
GLM-5
$1.00$3.20202,8001.1939YesNo
GLM-5
---3.2938YesNo
GLM-5
deepinfra
cheapest fastest
$0.60$2.08202,7521.2455YesNo
MiniMax-M2.5
$0.30$1.20204,8000.8949YesNo
MiniMax-M2.5
deepinfra
cheapest fastest
$0.15$1.15196,6081.2760NoNo
Ornith-1.0-35B-FP8
$0.10$0.75262,1440.6423YesYes
Kimi-K2-Thinking
$0.60$2.50262,144----
MiniMax-M2
$0.30$1.20204,8001.1650YesNo
Qwen2.5-Coder-32B-Instruct
$0.06$0.20131,0720.6124NoYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.54130NoYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.6291NoYes
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1441.2254YesYes
GLM-4.6-FP8
---4.8223YesNo
Gemma-4-31B-it-pearl
$0.28$0.86262,1440.2928YesNo
DeepSeek-V3.1
novita
fastest
$0.27$1.00131,0721.7825YesYes
DeepSeek-V3.1
deepinfra
cheapest
$0.25$0.95163,8400.8721YesYes
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.5531YesYes
DeepSeek-V3.1-Terminus
deepinfra
cheapest fastest
$0.27$0.95163,8400.4991NoYes
aya-vision-32b
---0.3641NoNo
GLM-4.6
$0.55$2.20204,8000.8735YesNo
GLM-4.6
zai-org
fastest
---2.9541YesNo
GLM-4.6
deepinfra
cheapest
$0.50$2.00202,7520.9730YesYes
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.2326YesYes
DeepSeek-R1-0528
$0.70$2.50163,8400.9519YesYes
DeepSeek-R1-0528
deepinfra
cheapest fastest
$0.50$2.15163,8400.6423YesNo
Qwen3-235B-A22B-Instruct-2507
$0.09$0.58131,0720.7647YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.6713YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
$0.86$2.57-0.3195YesYes
Qwen3-235B-A22B-Instruct-2507
deepinfra
cheapest
$0.09$0.55262,1440.4516YesYes
c4ai-command-r-08-2024
---0.3526YesNo
GLM-4.5V-FP8
---1.6693YesNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5361.1072YesNo
GLM-4.5V
zai-org
fastest
---1.6492YesNo
GLM-4.6V
---2.1958YesNo
GLM-4.6V-FP8
---2.0755YesNo
GLM-4.7-FP8
---2.2628YesNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.52158YesYes
GLM-5.1-FP8
-------
GLM-5.1-FP8
---3.7934YesNo
MiniMax-M1-80k
$0.55$2.201,000,0001.2350YesNo
tiny-aya-fire
---0.36113NoNo
DeepSeek-V3-0324
novita
fastest
$0.27$1.12163,8401.1734YesNo
DeepSeek-V3-0324
deepinfra
cheapest
$0.24$0.90163,8401.1526YesYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.3346NoYes
Qwen3-235B-A22B-Thinking-2507
novita
fastest
$0.30$3.00131,0720.7071YesNo
Qwen3-235B-A22B-Thinking-2507
deepinfra
cheapest
$0.23$2.30262,1440.4335YesNo
GLM-4-32B-0414
$0.55$1.6632,0001.0138NoNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.69145NoYes
L3-8B-Lunaris-v1
$0.05$0.058,1920.3949NoNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.5654NoYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.3832NoYes
tiny-aya-earth
---0.22133NoNo
WizardLM-2-8x22B
$0.62$0.6265,5350.9118NoNo
gemma-3n-E4B-it
$0.06$0.1232,7680.3246NoYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.1437NoNo
cogito-671b-v2.1
$1.25$1.25163,8400.3078NoNo
cogito-671b-v2.1
-------
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.3974NoNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.8851YesNo