Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Flash-0731
$0.14$0.281,048,5760.5066YesNo
DeepSeek-V4-Flash-0731
$0.14$0.281,048,5760.5545YesYes
DeepSeek-V4-Flash-0731
--1,048,5760.7970YesYes
DeepSeek-V4-Flash-0731
baseten
fastest
$0.13$0.261,048,5760.58105YesNo
DeepSeek-V4-Flash-0731
deepinfra
cheapest
$0.08$0.181,048,5760.3345YesYes
Kimi-K3
$3.00$15.001,000,0001.2942YesYes
Kimi-K3
$3.00$15.001,048,5760.9235YesYes
Kimi-K3
baseten
fastest
$3.00$15.001,048,5761.7065YesNo
Kimi-K3
deepinfra
cheapest
$2.85$14.251,048,5761.2814YesYes
GLM-5.2
$1.40$4.401,048,5762.7351NoNo
GLM-5.2
together
fastest
$1.40$4.40512,0000.71100YesYes
GLM-5.2
$1.40$4.401,048,5761.2857NoNo
GLM-5.2
---2.6754NoNo
GLM-5.2
$2.05$6.27-1.1828YesYes
GLM-5.2
$1.40$4.401,048,5760.7247YesYes
GLM-5.2
deepinfra
cheapest
$0.75$2.401,048,5761.4429YesNo
DeepSeek-V4-Flash
novita
fastest
$0.14$0.281,048,5760.82102YesNo
DeepSeek-V4-Flash
-------
DeepSeek-V4-Flash
deepinfra
cheapest
$0.09$0.181,048,5760.7741YesYes
Qwen3.6-27B
ovhcloud
cheapest fastest
$0.47$3.19262,1440.5370NoNo
Qwen3.6-27B
$0.32$3.20262,1440.3448YesYes
Inkling-Small
together
cheapest
$0.50$1.20524,2880.21181YesNo
Inkling-Small
baseten
fastest
$0.50$1.201,048,5760.26208YesYes
Inkling-Small
$0.45$1.20524,2880.6147YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.52135NoNo
Llama-3.1-8B-Instruct
nscale
fastest
$0.06$0.06131,0720.61148NoYes
Llama-3.1-8B-Instruct
$0.02$0.05131,0720.4918NoNo
gemma-4-31B-it
$0.14$0.40262,1441.304NoYes
gemma-4-31B-it
cerebras
fastest
$0.99$1.49131,0720.17745NoNo
gemma-4-31B-it
$0.39$0.97262,1440.2459YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.5621YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.24119YesYes
Qwen3.6-35B-A3B
scaleway
fastest
$0.29$1.71-1.5999YesYes
Qwen3.6-35B-A3B
deepinfra
cheapest
$0.10$0.95262,1442.4320YesYes
DeepSeek-V3
novita
fastest
$0.40$1.3064,0001.2933YesNo
DeepSeek-V3
deepinfra
cheapest
$0.32$0.89163,8400.4822YesYes
Ternary-Bonsai-27B-gguf
$0.00$0.00262,1440.2695YesNo
Inkling
together
cheapest
$1.00$4.05524,2880.1472YesYes
Inkling
--1,048,5760.6586YesYes
Inkling
$1.00$4.051,048,5760.2271YesYes
Inkling
deepinfra
fastest
$0.95$4.05524,2880.6594YesNo
MiniMax-M3
novita
fastest
$0.30$1.201,000,0001.0493YesNo
MiniMax-M3
$0.30$1.20524,2880.9843YesNo
MiniMax-M3
$0.30$1.20512,0000.9783NoYes
MiniMax-M3
deepinfra
cheapest
$0.28$1.10524,2880.3947YesYes
DeepSeek-V4-Pro
$1.60$3.201,048,5760.8048YesNo
DeepSeek-V4-Pro
$1.74$3.48512,0000.4182YesYes
DeepSeek-V4-Pro
$1.74$3.481,048,5761.6975NoNo
DeepSeek-V4-Pro
baseten
fastest
$1.74$3.48262,1440.48108YesNo
DeepSeek-V4-Pro
deepinfra
cheapest
$1.30$2.601,048,5761.1218YesYes
gemma-4-26B-A4B-it
$0.13$0.40262,1441.6737YesNo
gemma-4-26B-A4B-it
scaleway
fastest
$0.29$0.57-0.4988YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.4923YesYes
gpt-oss-120b
groq
fastest
$0.15$0.75131,0720.10448YesYes
gpt-oss-120b
$0.05$0.25131,0720.5359YesYes
gpt-oss-120b
-------
gpt-oss-120b
$0.10$0.40131,0720.6292YesYes
gpt-oss-120b
$0.15$0.60131,0720.2284YesYes
gpt-oss-120b
$0.15$0.60131,0720.51164YesYes
gpt-oss-120b
$0.17$0.68-0.48111YesYes
gpt-oss-120b
$0.10$0.50128,0721.31101YesYes
gpt-oss-120b
$0.09$0.47131,0720.3658YesYes
gpt-oss-120b
deepinfra
cheapest
$0.04$0.17131,0724.0036YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.26679YesYes
gpt-oss-20b
$0.04$0.15131,0720.4865NoYes
gpt-oss-20b
$0.05$0.20131,0720.57143YesYes
gpt-oss-20b
$0.05$0.20131,0720.28117YesYes
gpt-oss-20b
$0.07$0.30131,0720.29222YesYes
gpt-oss-20b
$0.05$0.18131,0720.2677YesYes
gpt-oss-20b
deepinfra
cheapest
$0.03$0.14131,0720.45118YesYes
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.3557YesYes
Qwen3.5-9B
ovhcloud
cheapest
$0.12$0.18262,1440.5135YesYes
Qwen3.5-9B
-------
Qwen3-Coder-Next
$0.20$1.50262,1441.48115YesNo
DeepSeek-R1
$0.70$2.5064,0000.9123YesNo
Hy3
$0.14$0.58262,1440.5433YesYes
Kimi-K2.7-Code
novita
cheapest
$0.95$4.00262,1441.1645YesYes
Kimi-K2.7-Code
together
fastest
$0.95$4.00262,1440.49131YesYes
Kimi-K2.7-Code
$0.95$4.00262,1440.40113NoNo
Kimi-K2.7-Code
$0.95$4.00262,0000.47123YesYes
Kimi-K2.7-Code
-------
Qwen3-8B
$0.07$0.1840,9600.67114YesNo
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
$1.00$5.00262,1441.1058YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
together
fastest
$0.60$3.60512,2880.28117YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
fireworks-ai
cheapest
$0.60$2.40262,1440.5290YesYes
MiMo-V2.5
$0.40$2.00262,1440.5516YesYes
Qwen3-Coder-30B-A3B-Instruct
$0.23$0.91-0.34132YesYes
GLM-4.7-Flash
novita
cheapest fastest
$0.07$0.40200,0001.2778YesNo
GLM-4.7-Flash
---2.1172YesNo
GLM-4.7-Flash
$0.06$0.40202,7520.3651YesNo
gemma-3-4b-it
$0.05$0.10131,0720.2649YesYes
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.9418NoNo
Qwen3.5-397B-A17B
novita
fastest
$0.60$3.60262,1441.0967YesNo
Qwen3.5-397B-A17B
$0.68$4.10-1.3351YesYes
Qwen3.5-397B-A17B
$0.71$4.25262,1441.0058YesNo
Qwen3.5-397B-A17B
deepinfra
cheapest
$0.45$3.00262,1440.2752YesYes
DeepSeek-OCR
$0.03$0.038,1921.18115NoNo
Qwen2.5-Coder-32B-Instruct
$0.06$0.20131,0720.5748NoYes
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.23269YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.4012,2880.5436NoNo
Llama-3.3-70B-Instruct
$1.04$1.04131,0722.3771NoNo
Llama-3.3-70B-Instruct
$1.03$1.03-0.3980YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.3830YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.55150NoYes
Qwen3.5-35B-A3B
novita
fastest
$0.25$2.00262,1440.8393YesNo
Qwen3.5-35B-A3B
deepinfra
cheapest
$0.14$1.00262,1440.2071YesYes
GLM-5.2-FP8
---2.7056NoNo
Apertus-v1.5-8B
$0.10$0.20-0.92133YesYes
GLM-4.6V-Flash
$0.30$0.90131,0720.7939YesNo
GLM-4.6V-Flash
-------
MiniMax-M2.7
$0.30$1.20204,8001.3834YesNo
MiniMax-M2.7
fireworks-ai
fastest
$0.30$1.20196,6080.58145YesYes
MiniMax-M2.7
deepinfra
cheapest
$0.25$1.00196,6080.6177YesNo
Qwen3.5-27B
novita
cheapest
$0.30$2.40262,1441.2154YesNo
Qwen3.5-27B
deepinfra
fastest
$0.26$2.60262,1440.3556YesYes
Qwen3-14B
nscale
cheapest fastest
$0.07$0.2040,9600.6694YesNo
Qwen3-14B
$0.12$0.2440,9600.4231YesNo
Qwen3-30B-A3B
-------
Qwen3-30B-A3B
$0.12$0.5040,9600.4468YesYes
phi-4
$0.07$0.1416,3840.4277NoYes
MiMo-V2.5-Pro
$1.00$3.001,048,5760.4168YesYes
Step-3.7-Flash
$0.20$1.15262,1440.45119YesNo
gpt-oss-safeguard-20b
--131,0720.33712YesYes
GLM-4.7
$0.60$2.20204,8001.9337YesNo
GLM-4.7
cerebras
fastest
$2.25$2.75131,0720.15423YesYes
GLM-4.7
-------
GLM-4.7
$0.60$2.20200,0000.6052YesYes
GLM-4.7
deepinfra
cheapest
$0.40$1.75202,7520.6220YesNo
Apertus-v1.5-70B
$0.82$2.92-0.5665YesYes
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.6167YesNo
GLM-4.5-Air
---2.2449YesNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.3635NoYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.6482YesYes
GLM-4.6V
---2.3844YesNo
Ternary-Bonsai-27B-AWQ-4bit
$0.00$0.00262,1440.3096YesNo
Llama-4-Scout-17B-16E-Instruct
-------
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.4737NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest fastest
$0.09$0.29890,0000.6872YesYes
Llama-4-Scout-17B-16E-Instruct
$0.10$0.30327,6800.5222YesYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.4492NoNo
gemma-3-12b-it
$0.05$0.15131,0720.7930YesYes
Kimi-K2-Instruct
$0.57$2.30131,0720.7237YesNo
Llama-Guard-4-12B
together
fastest
$0.20$0.201,048,5760.1513NoNo
Llama-Guard-4-12B
deepinfra
cheapest
$0.18$0.18163,8400.536NoNo
DeepSeek-R1-0528
$0.70$2.50163,8401.1617YesYes
DeepSeek-R1-0528
deepinfra
cheapest fastest
$0.50$2.15163,8400.5925NoNo
Hermes-3-Llama-3.1-70B
$0.70$0.70131,0720.3027NoYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.8874NoNo
Kimi-K2.6
together
fastest
$1.20$4.50262,1440.38132YesYes
Kimi-K2.6
$0.95$4.00262,1440.5045YesYes
Kimi-K2.6
$0.95$4.00262,0000.7546YesYes
Kimi-K2.6
$0.75$3.50262,1440.8413YesYes
Qwen3-32B
-------
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.6048YesYes
Qwen3-32B
deepinfra
fastest
$0.08$0.2840,9600.3595YesNo
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.6592NoYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.63165NoNo
Qwen2.5-72B-Instruct
novita
cheapest
$0.38$0.4032,0000.8535YesNo
Qwen2.5-72B-Instruct
deepinfra
fastest
$0.36$0.4032,7680.4337YesYes
Bielik-11B-v3.0-Instruct
$0.40$0.40-3.0929YesYes
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1440.6661YesNo
Kimi-K2.5
$0.60$3.00262,1440.6639YesYes
Kimi-K2.5
deepinfra
cheapest fastest
$0.45$2.25262,1440.6697NoNo
DeepSeek-V3.2
novita
fastest
$0.27$0.40163,8401.8832YesYes
DeepSeek-V3.2
deepinfra
cheapest
$0.26$0.38163,8401.2914YesYes
GLM-5
novita
fastest
$1.00$3.20202,8001.2639YesNo
GLM-5
---3.2938YesNo
GLM-5
deepinfra
cheapest
$0.60$2.08202,7520.7130YesNo
cogito-671b-v2.1
$1.25$1.25163,8400.3258NoNo
cogito-671b-v2.1
-------
GLM-4.7-FP8
---2.0461YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.3125YesYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.6432NoNo
MiniMax-M2.5
$0.30$1.20204,8000.9562YesNo
GLM-4-32B-0414
$0.55$1.6632,0000.8641NoNo
Qwen3-VL-235B-A22B-Instruct
novita
fastest
$0.30$1.50131,0720.5535YesYes
Qwen3-VL-235B-A22B-Instruct
deepinfra
cheapest
$0.20$0.88262,1440.2819YesYes
command-a-translate-08-2025
---0.2571YesYes
tiny-aya-water
---0.30134NoNo
tiny-aya-global
---0.30135NoNo
tiny-aya-earth
---0.36133NoNo
tiny-aya-fire
---0.36133NoNo
GLM-5.1
-------
GLM-5.1
$1.05$3.50202,7520.7915YesYes
Gemma-4-31B-it-pearl
$0.28$0.86262,1440.2753YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.4231YesYes
DeepSeek-V3.1-Terminus
deepinfra
cheapest fastest
$0.27$0.95163,8400.7659NoYes
Qwen3-235B-A22B-Instruct-2507
novita
fastest
$0.09$0.58131,0720.5651YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.7319YesYes
Qwen3-235B-A22B-Instruct-2507
$0.86$2.57-0.4238YesYes
Qwen3-235B-A22B-Instruct-2507
deepinfra
cheapest
$0.09$0.55262,1440.2837YesYes
Qwen3.5-122B-A10B
$0.40$3.20262,1440.89105YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest fastest
$0.29$2.40262,1440.45139YesYes
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.1741YesNo
Step-3.5-Flash
$0.10$0.30262,1440.48118YesNo
gemma-3n-E4B-it
$0.06$0.1232,7680.2551NoYes
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.3459NoNo
GLM-4.6
novita
fastest
$0.55$2.20204,8000.7353YesNo
GLM-4.6
---4.4229YesNo
GLM-4.6
deepinfra
cheapest
$0.50$2.00202,7520.4423YesYes
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5360.8197YesNo
GLM-4.5V
---2.1062YesNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0721.2341YesNo
Qwen3-235B-A22B-Thinking-2507
deepinfra
cheapest fastest
$0.23$2.30262,1440.3567YesNo
DeepSeek-V3.1
novita
fastest
$0.27$1.00131,0721.5827YesYes
DeepSeek-V3.1
deepinfra
cheapest
$0.25$0.95163,8400.7619YesYes
Kimi-K2-Instruct-0905
$0.60$2.50262,1440.5737YesYes
GLM-4.6V-FP8
---3.6034YesNo
GLM-4.5V-FP8
---1.9577YesNo
GLM-4.6-FP8
---3.3644YesNo
command-a-reasoning-08-2025
---0.17107YesYes
GLM-4.5
---2.4153NoNo
Qwen3-Next-80B-A3B-Instruct
novita
fastest
$0.15$1.50131,0720.86142YesNo
Qwen3-Next-80B-A3B-Instruct
deepinfra
cheapest
$0.09$1.10262,1440.4848YesYes
c4ai-command-a-03-2025
---2.2627YesYes
c4ai-command-r7b-12-2024
---0.47103YesYes
c4ai-command-r-08-2024
---0.2543YesYes
aya-expanse-32b
---0.2046NoNo
aya-vision-32b
---0.2342NoNo
c4ai-command-r7b-arabic-02-2025
---0.2538NoYes
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.8052NoYes
Qwen3-235B-A22B
novita
fastest
$0.20$0.8040,9601.5226NoNo
Qwen3-235B-A22B
nscale
cheapest
$0.20$0.6032,0000.7216YesYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.73155YesYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.3459NoYes
DeepSeek-V3-0324
novita
fastest
$0.27$1.12163,8401.0734YesNo
DeepSeek-V3-0324
deepinfra
cheapest
$0.24$0.90163,8400.6233YesYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.57130NoYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.60185NoYes
L3-8B-Lunaris-v1
$0.05$0.058,1920.4880NoNo
WizardLM-2-8x22B
$0.62$0.6265,5352.1411NoNo
Ling-2.6-1T
$0.30$2.50262,1440.8285YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.5947YesYes
MiniMax-M2
$0.30$1.20204,8000.9159YesNo
Kimi-K2-Thinking
$0.60$2.50262,144----
gemma-3-27b-it
$0.08$0.16131,0720.8014YesYes
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.5599NoNo
MiniMax-M1-80k
$0.55$2.201,000,0001.1056YesNo
Qwen3-VL-30B-A3B-Instruct
novita
fastest
$0.20$0.70131,0721.0865YesYes
Qwen3-VL-30B-A3B-Instruct
deepinfra
cheapest
$0.15$0.60262,1440.2242YesYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.5351NoYes
Apertus-70B-Instruct-2509
$0.82$2.92-0.7557NoYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.52149NoYes
MiniMax-M2.1
$0.30$1.20204,8001.2862YesNo