Inference Providers

·

Metrics for top trending models

Kimi-K3
together
cheapest fastest
$3.00$15.001,000,0001.0642YesYes
Kimi-K3
$3.00$15.001,048,5762.3241NoNo
GLM-5.2
$1.40$4.401,048,5761.2035YesNo
GLM-5.2
together
fastest
$1.40$4.40512,0001.63110YesYes
GLM-5.2
$1.40$4.401,048,5762.1329YesNo
GLM-5.2
---3.8240NoNo
GLM-5.2
$2.05$6.27-1.0255YesYes
GLM-5.2
deepinfra
cheapest
$0.93$3.001,048,5760.8127YesYes
Inkling
together
cheapest
$1.00$4.05524,2881.0429YesYes
Inkling
fireworks-ai
fastest
--1,048,5760.45106YesNo
Inkling
$1.00$4.05524,2880.906NoNo
Ternary-Bonsai-27B-gguf
$0.00$0.00262,1440.3297YesNo
Kimi-K2.7-Code
$0.95$4.00262,1442.3229YesYes
Kimi-K2.7-Code
together
fastest
$0.95$4.00262,1440.57140YesYes
Kimi-K2.7-Code
$0.95$4.00262,1442.2840NoNo
Kimi-K2.7-Code
deepinfra
cheapest
$0.74$3.50262,1440.8654YesNo
Qwen3.6-35B-A3B
scaleway
fastest
$0.29$1.71-1.1235YesYes
Qwen3.6-35B-A3B
deepinfra
cheapest
$0.10$0.95262,1440.3917YesYes
DeepSeek-V4-Flash
$0.14$0.281,048,5761.5971YesNo
DeepSeek-V4-Flash
fireworks-ai
fastest
$0.14$0.281,048,5761.4398YesNo
DeepSeek-V4-Flash
deepinfra
cheapest
$0.09$0.181,048,5760.7323YesYes
Qwen3.6-27B
ovhcloud
cheapest fastest
$0.47$3.19262,1440.4474YesYes
Qwen3.6-27B
$0.32$3.20262,1441.0524YesYes
gemma-4-31B-it
$0.14$0.40262,1441.793YesYes
gemma-4-31B-it
cerebras
fastest
---0.19748YesNo
gemma-4-31B-it
$0.39$0.97262,1440.3821YesNo
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1441.703YesYes
Apertus-v1.5-70B
$0.82$2.92-0.5767YesYes
DeepSeek-V4-Pro
$1.60$3.201,048,5760.5440YesNo
DeepSeek-V4-Pro
$1.74$3.48512,0000.9647YesYes
DeepSeek-V4-Pro
fireworks-ai
fastest
$1.74$3.481,048,5761.0450YesNo
DeepSeek-V4-Pro
deepinfra
cheapest
$1.30$2.601,048,5760.9037YesYes
Apertus-v1.5-8B
$0.10$0.20-0.64151YesYes
MiniMax-M3
novita
cheapest
$0.30$1.201,000,0001.6154NoNo
MiniMax-M3
$0.30$1.20524,2880.5756YesYes
MiniMax-M3
fireworks-ai
fastest
$0.30$1.20512,0001.8189YesNo
MiniMax-M3
$0.30$1.20524,2880.9710YesNo
Qwen3-8B
$0.07$0.1840,9600.77130YesNo
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.3595YesYes
Qwen3.5-9B
$0.12$0.18262,1440.6638YesYes
Qwen3.5-9B
deepinfra
cheapest
$0.10$0.15262,1440.6639YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1442.1029YesNo
Kimi-K2.6
together
fastest
$1.20$4.50262,1440.62161YesYes
Kimi-K2.6
$0.95$4.00262,1440.4263YesNo
Kimi-K2.6
$0.75$3.50262,1440.8557YesYes
Ornith-1.0-35B
$0.10$0.75262,1440.6722YesYes
Hy3
$0.14$0.58262,1440.5338YesYes
gpt-oss-120b
$0.15$0.75131,0720.19448YesNo
gpt-oss-120b
$0.05$0.25131,0720.55110YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.211,199YesNo
gpt-oss-120b
$0.10$0.40131,0720.65106YesYes
gpt-oss-120b
$0.15$0.60131,0720.22134YesYes
gpt-oss-120b
$0.15$0.60131,0720.31142YesNo
gpt-oss-120b
$0.17$0.68-0.4698YesYes
gpt-oss-120b
$0.09$0.47131,0720.7842YesYes
gpt-oss-120b
deepinfra
cheapest
$0.04$0.17131,0720.8124YesYes
gemma-4-26B-A4B-it
$0.13$0.40262,1442.0426YesNo
gemma-4-26B-A4B-it
scaleway
fastest
$0.29$0.57-0.45114YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.7617YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.47121NoNo
Llama-3.1-8B-Instruct
nscale
fastest
$0.06$0.06131,0720.63148NoYes
Llama-3.1-8B-Instruct
$0.02$0.05131,0720.4824YesNo
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.23734YesNo
gpt-oss-20b
$0.04$0.15131,0720.35132NoYes
gpt-oss-20b
$0.05$0.20131,0720.66160YesYes
gpt-oss-20b
$0.05$0.20131,0720.28157YesYes
gpt-oss-20b
$0.07$0.30131,0720.5798YesNo
gpt-oss-20b
$0.05$0.18131,0720.3285YesYes
gpt-oss-20b
deepinfra
cheapest
$0.03$0.14131,0720.4582YesYes
DeepSeek-R1
$0.70$2.5064,0001.0327YesYes
MiMo-V2.5
$0.40$2.00262,1440.4531YesYes
Qwen3-Coder-Next
$0.20$1.50262,1441.82102YesNo
Qwen3-Coder-30B-A3B-Instruct
$0.23$0.91-0.29136YesYes
GLM-5.2-FP8
---3.8546NoNo
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
$0.60$3.60512,2880.3353YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
fireworks-ai
cheapest fastest
$0.60$2.40262,1440.44154YesNo
gemma-3-4b-it
$0.05$0.10131,0720.4124YesYes
Qwen3.5-122B-A10B
$0.40$3.20262,1440.7988YesNo
Qwen3.5-122B-A10B
-------
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
$1.00$5.00262,1440.9679YesYes
Step-3.7-Flash
$0.20$1.15262,1440.45124YesNo
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.32119YesYes
Kimi-K2.5
$0.60$3.00262,1440.8636YesYes
Kimi-K2.5
deepinfra
cheapest fastest
$0.45$2.25262,1440.7542YesYes
Kimi-K2-Instruct-0905
$0.60$2.50262,1440.7635YesYes
GLM-4.7-Flash
novita
cheapest
$0.07$0.40200,0000.8663YesNo
GLM-4.7-Flash
zai-org
fastest
---2.0782YesNo
GLM-4.7-Flash
$0.06$0.40202,7521.3018YesNo
Qwen3.5-27B
novita
cheapest fastest
$0.30$2.40262,1442.1045YesNo
Qwen3.5-27B
$0.26$2.60262,1440.7528YesYes
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.8835YesNo
GLM-4.5-Air
---3.6130YesNo
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.7296YesYes
GLM-4.7
$0.60$2.20204,8001.6923YesNo
GLM-4.7
cerebras
fastest
---0.20404YesNo
GLM-4.7
---2.5457NoNo
GLM-4.7
deepinfra
cheapest
$0.40$1.75202,7520.6956YesNo
Ling-2.6-1T
$0.30$2.50262,1441.9082NoNo
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1442.3658YesNo
Qwen3.5-397B-A17B
$0.68$4.10-0.5661YesYes
Qwen3.5-397B-A17B
ovhcloud
fastest
$0.71$4.25262,1440.8397YesNo
Qwen3.5-397B-A17B
-------
MiMo-V2.5-Pro
$1.00$3.001,048,5760.4481YesYes
DeepSeek-V3
novita
fastest
$0.40$1.3064,0001.2333YesNo
DeepSeek-V3
deepinfra
cheapest
$0.32$0.89163,8402.7713YesYes
Qwen3.5-35B-A3B
novita
fastest
$0.25$2.00262,1440.81111YesNo
Qwen3.5-35B-A3B
deepinfra
cheapest
$0.14$1.00262,1440.3069YesYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.81107YesNo
Qwen3-14B
nscale
cheapest fastest
$0.07$0.2040,9600.7692YesNo
Qwen3-14B
$0.12$0.2440,9600.4445YesNo
Qwen3-32B
-------
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.6647YesYes
Qwen3-32B
deepinfra
fastest
$0.08$0.2840,9600.2866YesNo
Apertus-8B-Instruct-2509
$0.10$0.20-1.0687NoYes
DeepSeek-OCR
$0.03$0.038,1920.43239NoNo
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0720.7289YesYes
gemma-3-12b-it
$0.05$0.15131,0720.3048YesYes
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.27261YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.406,0000.5235YesNo
Llama-3.3-70B-Instruct
$1.04$1.04131,0722.9834YesYes
Llama-3.3-70B-Instruct
$1.03$1.03-0.4665YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.3032YesYes
DeepSeek-V3.2
novita
fastest
$0.27$0.40163,8401.2932YesYes
DeepSeek-V3.2
deepinfra
cheapest
$0.26$0.38163,8400.8315YesYes
GLM-5
$1.00$3.20202,8001.5339YesNo
GLM-5
-------
GLM-5
deepinfra
cheapest fastest
$0.60$2.08202,7521.0357YesNo
Kimi-K2-Instruct
$0.57$2.30131,0721.0135YesNo
phi-4
$0.07$0.1416,3840.2777NoYes
GLM-5.1
-------
GLM-5.1
---3.7135YesNo
GLM-5.1
deepinfra
cheapest fastest
$1.05$3.50202,7520.8845YesYes
MiniMax-M2.7
$0.30$1.20204,8001.8029YesNo
MiniMax-M2.7
fireworks-ai
fastest
$0.30$1.20196,6081.0087YesNo
MiniMax-M2.7
deepinfra
cheapest
$0.25$1.00196,6080.9230NoNo
Llama-Guard-4-12B
together
fastest
$0.20$0.201,048,5760.1711NoNo
Llama-Guard-4-12B
deepinfra
cheapest
$0.18$0.18163,8401.073NoNo
Llama-4-Scout-17B-16E-Instruct
-------
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3358NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest fastest
$0.09$0.29890,0000.7372YesNo
Llama-4-Scout-17B-16E-Instruct
$0.10$0.30327,6800.3664YesYes
c4ai-command-r7b-12-2024
---0.4175YesNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.70144NoYes
c4ai-command-r7b-arabic-02-2025
---0.2997YesNo
Qwen2.5-Coder-32B-Instruct
$0.06$0.20131,0720.5948NoYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.73145NoNo
c4ai-command-a-03-2025
---0.2849YesNo
Apertus-70B-Instruct-2509
$0.82$2.92-0.6859NoYes
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.5398NoNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.8533YesYes
Qwen3-235B-A22B-Instruct-2507
$0.09$0.58131,0720.8544YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.7413YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
$0.86$2.57-0.3671YesYes
Qwen3-235B-A22B-Instruct-2507
deepinfra
cheapest
$0.09$0.55262,1440.3922YesYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.70155YesYes
MiniMax-M2.1
$0.30$1.20204,8001.4943YesNo
Qwen2.5-72B-Instruct
novita
cheapest fastest
$0.38$0.4032,0000.4943YesNo
Qwen2.5-72B-Instruct
$0.36$0.4032,7680.3939YesYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Bielik-11B-v3.0-Instruct
$0.40$0.40-1.1156YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.5443NoYes
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.8519NoNo
Qwen3-235B-A22B
$0.20$0.8040,9600.7514NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0000.9814YesYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.4736NoYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.54100NoNo
gpt-oss-safeguard-20b
--131,0720.19791YesNo
tiny-aya-water
---0.32133NoNo
tiny-aya-global
---0.29132NoNo
command-a-reasoning-08-2025
---0.23104YesNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.6324YesNo
Qwen3-235B-A22B-Thinking-2507
deepinfra
cheapest fastest
$0.23$2.30262,1440.4635YesNo
aya-expanse-32b
---0.5042NoNo
GLM-4.5
---2.4153NoNo
Step-3.5-Flash
$0.10$0.30262,1440.22127YesNo
Ornith-1.0-35B-FP8
$0.10$0.75262,1440.4222YesYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.3840NoNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.71142NoYes
GLM-4.6V-Flash
$0.30$0.90131,0720.8148YesNo
GLM-4.6V-Flash
-------
MiniMax-M2
$0.30$1.20204,8001.9948YesNo
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1441.0760YesYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.8091NoYes
Ternary-Bonsai-27B-AWQ-4bit
$0.00$0.00262,1440.3397YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.1125YesYes
c4ai-command-r-08-2024
---0.2061YesNo
GLM-4.6
$0.55$2.20204,8001.0135YesNo
GLM-4.6
zai-org
fastest
---2.9738YesNo
GLM-4.6
deepinfra
cheapest
$0.50$2.00202,7520.5633YesYes
GLM-4.6V-FP8
---3.4343YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.7523YesYes
DeepSeek-V3.1-Terminus
deepinfra
cheapest fastest
$0.27$0.95163,8400.5355NoYes
aya-vision-32b
---0.2842NoNo
DeepSeek-V3.1
novita
fastest
$0.27$1.00131,0721.6723YesYes
DeepSeek-V3.1
deepinfra
cheapest
$0.25$0.95163,8400.6218YesYes
Gemma-4-31B-it-pearl
$0.28$0.86262,1440.9127YesNo
GLM-4.5V-FP8
---2.2265YesNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5361.5836YesNo
GLM-4.5V
zai-org
fastest
---1.9246YesNo
GLM-4.6-FP8
---3.1029YesNo
GLM-4.6V
---3.0139NoNo
cogito-671b-v2.1
$1.25$1.25163,8400.3082NoNo
cogito-671b-v2.1
-------
GLM-4.7-FP8
---2.3937NoNo
GLM-5.1-FP8
-------
GLM-5.1-FP8
---3.7934YesNo
MiniMax-M2.5
novita
fastest
$0.30$1.20204,8001.1343YesNo
MiniMax-M2.5
deepinfra
cheapest
$0.15$1.15196,6080.8431NoNo
DeepSeek-R1-0528
novita
fastest
$0.70$2.50163,8401.2731NoNo
DeepSeek-R1-0528
deepinfra
cheapest
$0.50$2.15163,8400.6728NoNo
GLM-4-32B-0414
$0.55$1.6632,0000.9741NoNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.5428NoYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.7347NoYes
DeepSeek-V3-0324
novita
fastest
$0.27$1.12163,8401.3733YesNo
DeepSeek-V3-0324
deepinfra
cheapest
$0.24$0.90163,8401.4227YesNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.5972NoNo
gemma-3-27b-it
scaleway
fastest
$0.29$0.57-0.5548YesNo
gemma-3-27b-it
deepinfra
cheapest
$0.08$0.16131,0721.1818YesYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.85148NoYes
tiny-aya-fire
---0.28132NoNo
tiny-aya-earth
---0.23124NoNo
WizardLM-2-8x22B
$0.62$0.6265,5350.6915NoNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.6653NoYes
gemma-3n-E4B-it
$0.06$0.1232,7680.6343NoYes
MiniMax-M1-80k
$0.55$2.201,000,0002.0736NoNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.4084NoNo
command-a-translate-08-2025
---0.2772YesNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.0649YesNo