Inference Providers

·

Metrics for top trending models

Qwen3.8-2.4T-A95B
together
cheapest
$2.50$6.251,010,0000.7377YesNo
Qwen3.8-2.4T-A95B
fireworks-ai
fastest
--262,1441.04100YesYes
Muse-Glimmer-30B
together
cheapest fastest
$0.35$1.50131,0720.2184YesNo
Muse-Glimmer-30B
--131,0720.1658YesNo
DeepSeek-V4-Pro-0813
novita
cheapest
$1.32$3.961,048,5760.7736YesNo
DeepSeek-V4-Pro-0813
$1.32$3.961,048,5760.8554YesNo
DeepSeek-V4-Pro-0813
--1,048,5760.6941YesYes
DeepSeek-V4-Pro-0813
baseten
fastest
$1.32$3.961,048,5760.55111YesYes
DeepSeek-V4-Flash-0731
$0.14$0.281,048,5760.6667YesNo
DeepSeek-V4-Flash-0731
$0.14$0.281,048,5761.0583YesYes
DeepSeek-V4-Flash-0731
--1,048,5760.6185YesYes
DeepSeek-V4-Flash-0731
baseten
fastest
$0.13$0.261,048,5760.45144YesYes
DeepSeek-V4-Flash-0731
deepinfra
cheapest
$0.08$0.181,048,5761.2221YesYes
Kimi-K3
$3.00$15.001,000,0000.8646YesNo
Kimi-K3
$3.00$15.001,048,5761.1157YesYes
Kimi-K3
baseten
fastest
$3.00$15.001,048,5760.6687YesYes
Kimi-K3
deepinfra
cheapest
$2.85$14.251,048,5761.1015YesYes
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
--262,1440.46270YesYes
GLM-5.2
$1.40$4.401,048,5761.5355YesNo
GLM-5.2
$1.40$4.40512,0001.638YesYes
GLM-5.2
$1.40$4.401,048,5761.4650YesYes
GLM-5.2
---4.1333YesNo
GLM-5.2
scaleway
fastest
$2.05$6.27-0.6987YesNo
GLM-5.2
$1.40$4.401,048,5760.8286YesYes
GLM-5.2
deepinfra
cheapest
$0.75$2.401,048,5760.9764YesYes
gemma-4-31B-it
$0.14$0.40262,1442.3456YesNo
gemma-4-31B-it
cerebras
fastest
$0.99$1.49131,0720.18774YesYes
gemma-4-31B-it
$0.39$0.97262,1440.2080YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.6532YesYes
DeepSeek-V4-Pro
-------
DeepSeek-V4-Pro
$1.74$3.48512,0000.5165YesYes
DeepSeek-V4-Pro
$1.74$3.481,048,5760.6454YesYes
DeepSeek-V4-Pro
baseten
fastest
$1.74$3.481,048,5760.55109YesNo
DeepSeek-V4-Pro
deepinfra
cheapest
$1.30$2.601,048,5760.5434YesNo
Qwen3.6-35B-A3B
scaleway
fastest
$0.29$1.71-0.40186YesYes
Qwen3.6-35B-A3B
deepinfra
cheapest
$0.10$0.95262,1440.3229YesYes
Qwen3.6-27B
ovhcloud
cheapest fastest
$0.47$3.19262,1440.3676YesYes
Qwen3.6-27B
$0.32$3.20262,1440.3056YesYes
DeepSeek-V4-Flash
novita
fastest
$0.14$0.281,048,5760.8395YesNo
DeepSeek-V4-Flash
deepinfra
cheapest
$0.09$0.181,048,5760.7635YesYes
Ternary-Bonsai-27B-gguf
$0.00$0.00262,1440.3990YesNo
gemma-4-26B-A4B-it
$0.13$0.40262,1440.5424YesNo
gemma-4-26B-A4B-it
scaleway
fastest
$0.29$0.57-0.39170YesNo
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.4026YesYes
MiniMax-M3
$0.30$1.201,000,0000.9487YesNo
MiniMax-M3
$0.30$1.20524,2880.3395YesNo
MiniMax-M3
fireworks-ai
fastest
$0.30$1.20512,0000.67108YesYes
MiniMax-M3
deepinfra
cheapest
$0.28$1.10524,2880.7039YesYes
Llama-3.1-8B-Instruct
novita
cheapest fastest
$0.02$0.0516,3840.48157NoNo
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.65148NoYes
Llama-3.1-8B-Instruct
$0.02$0.05131,0720.5222YesNo
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.3382YesYes
Qwen3.5-9B
$0.12$0.18262,1440.3936YesYes
Qwen3.5-9B
deepinfra
cheapest
$0.10$0.15262,1440.3736YesYes
Qwen3-Coder-Next
$0.20$1.50262,1440.98123YesNo
Inkling
together
cheapest
$1.00$4.05524,2881.0444YesYes
Inkling
--1,048,5760.4688YesYes
Inkling
baseten
fastest
$1.00$4.051,048,5760.21105YesYes
Inkling
$0.95$4.05524,2880.8517YesNo
DeepSeek-R1
$0.70$2.5064,0000.9116NoYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.13805YesYes
gpt-oss-20b
$0.04$0.15131,0720.35108NoYes
gpt-oss-20b
$0.05$0.20131,0720.54162YesYes
gpt-oss-20b
$0.05$0.20131,0720.29107YesYes
gpt-oss-20b
$0.07$0.30131,0720.5695YesYes
gpt-oss-20b
$0.05$0.18131,0720.3180YesYes
gpt-oss-20b
deepinfra
cheapest
$0.03$0.14131,0720.2887YesYes
GLM-4.7-Flash
novita
cheapest
$0.07$0.40200,0000.6153YesNo
GLM-4.7-Flash
---1.9375YesNo
GLM-4.7-Flash
deepinfra
fastest
$0.06$0.40202,7520.50126YesNo
Inkling-Small
together
cheapest fastest
$0.50$1.20524,2880.21190YesNo
Inkling-Small
$0.50$1.201,048,5760.21178YesYes
Inkling-Small
$0.45$1.20524,2880.38138YesYes
Qwen3-Coder-30B-A3B-Instruct
$0.23$0.91-0.40147YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
$1.00$5.00262,1441.02123YesYes
gpt-oss-120b
$0.15$0.75131,0720.18442YesYes
gpt-oss-120b
$0.05$0.25131,0720.4376YesYes
gpt-oss-120b
cerebras
fastest
$0.35$0.75131,0720.29855YesYes
gpt-oss-120b
$0.10$0.40131,0720.55112YesYes
gpt-oss-120b
$0.15$0.60131,0720.23167YesYes
gpt-oss-120b
$0.15$0.60131,0720.4779YesYes
gpt-oss-120b
$0.17$0.68-0.46140YesYes
gpt-oss-120b
$0.10$0.50128,0720.19315YesYes
gpt-oss-120b
$0.09$0.47131,0720.26144YesYes
gpt-oss-120b
deepinfra
cheapest
$0.04$0.17131,0720.3511YesYes
Kimi-K2.7-Code
$0.95$4.00262,1441.0462YesYes
Kimi-K2.7-Code
$0.95$4.00262,1440.25121YesYes
Kimi-K2.7-Code
$0.95$4.00262,1440.3795YesYes
Kimi-K2.7-Code
baseten
fastest
$0.95$4.00262,0000.40147YesYes
Kimi-K2.7-Code
deepinfra
cheapest
$0.68$3.40262,1440.6987YesNo
Qwen3-8B
$0.07$0.1840,9600.58134YesNo
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
$0.60$3.60512,2880.23105YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
fireworks-ai
cheapest fastest
$0.60$2.40262,1440.51115YesYes
Hy3
$0.14$0.58262,1440.2459YesYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.6361YesYes
MiMo-V2.5-Pro
$1.00$3.001,048,5760.3386YesYes
DeepSeek-OCR
$0.03$0.038,1921.04192NoNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.7498YesNo
Qwen3.5-35B-A3B
deepinfra
cheapest fastest
$0.14$1.00262,1440.20139YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.58149NoYes
MiniMax-M2.7
$0.30$1.20204,8001.5839YesNo
MiniMax-M2.7
fireworks-ai
fastest
$0.30$1.20196,6080.74128YesYes
MiniMax-M2.7
deepinfra
cheapest
$0.25$1.00196,6080.8358YesNo
MiMo-V2.5
$0.40$2.00262,1440.2864YesYes
Qwen2.5-Coder-32B-Instruct
$0.06$0.20131,0720.5746NoYes
Qwen3.5-122B-A10B
$0.40$3.20262,1441.0882YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest fastest
$0.29$2.40262,1440.33122YesNo
Step-3.7-Flash
$0.20$1.15262,1440.3292YesNo
GLM-5.2-FP8
---3.4343YesNo
gemma-3-12b-it
$0.05$0.15131,0720.8423YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.1358YesYes
Kimi-K2.6
together
fastest
$1.20$4.50262,1440.36189YesYes
Kimi-K2.6
$0.95$4.00262,1442.6073YesYes
Kimi-K2.6
$0.95$4.00262,0000.38148YesYes
Kimi-K2.6
$0.75$3.50262,1440.5445YesYes
Step-3.5-Flash
$0.10$0.30262,1440.4293YesNo
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0720.6261YesNo
GLM-4.5-Air
zai-org
fastest
---1.9076YesNo
GLM-5
$1.00$3.20202,8001.1236YesNo
GLM-5
zai-org
fastest
---3.2938YesNo
GLM-5
deepinfra
cheapest
$0.60$2.08202,7520.7837YesYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.7190NoYes
Qwen3-30B-A3B
-------
Qwen3-30B-A3B
$0.12$0.5040,9600.2573YesYes
Bielik-11B-v3.0-Instruct
$0.40$0.40-0.9956YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.23133YesNo
gemma-3-27b-it
$0.08$0.16131,0721.0619YesYes
DeepSeek-V3.2
novita
fastest
$0.27$0.40163,8401.5428YesYes
DeepSeek-V3.2
deepinfra
cheapest
$0.26$0.38163,8400.7410YesYes
GLM-4.7
$0.60$2.20204,8001.2850YesNo
GLM-4.7
-------
GLM-4.7
-------
GLM-4.7
baseten
fastest
$0.60$2.20200,0000.47129YesYes
GLM-4.7
deepinfra
cheapest
$0.40$1.75202,7520.9618YesNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0720.5959YesNo
GLM-4.6V-Flash
zai-org
fastest
---1.6477YesNo
MiniMax-M2
$0.30$1.20204,8001.3957YesNo
Qwen3-VL-235B-A22B-Instruct
novita
fastest
$0.30$1.50131,0720.5435YesYes
Qwen3-VL-235B-A22B-Instruct
deepinfra
cheapest
$0.20$0.88262,1440.8022YesYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.81127NoYes
Qwen3.5-397B-A17B
$0.60$3.60262,1440.9958YesNo
Qwen3.5-397B-A17B
scaleway
fastest
$0.68$4.10-0.41115YesYes
Qwen3.5-397B-A17B
$0.71$4.25262,1440.35106YesNo
Qwen3.5-397B-A17B
deepinfra
cheapest
$0.45$3.00262,1440.6610YesYes
Ling-2.6-1T
$0.30$2.50262,1440.9842YesYes
Qwen3-32B
-------
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.6747YesYes
Qwen3-32B
deepinfra
fastest
$0.08$0.2840,9600.3289YesNo
Qwen3-14B
nscale
cheapest fastest
$0.07$0.2040,9600.5396YesNo
Qwen3-14B
$0.12$0.2440,9600.4143YesNo
Apertus-v1.5-70B
$0.82$2.92-0.8064YesYes
Apertus-v1.5-8B
$0.10$0.20-0.72147YesYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.3434NoYes
gpt-oss-safeguard-20b
--131,0720.30654YesYes
DeepSeek-V3.1
novita
fastest
$0.27$1.00131,0721.5627YesYes
DeepSeek-V3.1
deepinfra
cheapest
$0.25$0.95163,8400.787YesYes
phi-4
$0.07$0.1416,3840.294NoYes
gemma-3-4b-it
$0.05$0.10131,0721.5824YesYes
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1440.7358YesNo
command-a-plus-05-2026-w4a4
---0.14126YesYes
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.5255NoYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.70161NoNo
Qwen3-Next-80B-A3B-Instruct
novita
fastest
$0.15$1.50131,0720.92114YesNo
Qwen3-Next-80B-A3B-Instruct
deepinfra
cheapest
$0.09$1.10262,1440.6253YesYes
GLM-5.1
zai-org
fastest
---4.1141YesNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7524.419YesNo
Qwen3-235B-A22B
novita
fastest
$0.20$0.8040,9600.9032NoNo
Qwen3-235B-A22B
nscale
cheapest
$0.20$0.6032,0000.8016YesYes
Qwen3-235B-A22B-Instruct-2507
$0.09$0.58131,0720.8329YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.7214YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
$0.86$2.57-0.4893YesYes
Qwen3-235B-A22B-Instruct-2507
deepinfra
cheapest
$0.09$0.55262,1440.4332YesYes
GLM-4.6V
---2.1359YesNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.68157YesYes
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.4012,2880.5345YesNo
Llama-3.3-70B-Instruct
$1.04$1.04131,0720.4483YesYes
Llama-3.3-70B-Instruct
scaleway
fastest
$1.03$1.03-0.3886YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.2829YesYes
GLM-4.6
$0.55$2.20204,8001.5438YesNo
GLM-4.6
---4.8516YesNo
GLM-4.6
deepinfra
cheapest fastest
$0.50$2.00202,7520.5161YesYes
Llama-Guard-4-12B
together
fastest
$0.20$0.201,048,5760.1215NoNo
Llama-Guard-4-12B
deepinfra
cheapest
$0.18$0.18163,8400.457NoNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5361.0381YesNo
GLM-4.5V
zai-org
fastest
---1.5594YesNo
Qwen2.5-72B-Instruct
novita
cheapest fastest
$0.38$0.4032,0000.3839YesNo
Qwen2.5-72B-Instruct
$0.36$0.4032,7681.824YesYes
GLM-4.5
---2.4153YesNo
Qwen3.5-27B
novita
cheapest
$0.30$2.40262,1441.2636YesNo
Qwen3.5-27B
deepinfra
fastest
$0.26$2.60262,1440.2478YesYes
MiniMax-M2.1
$0.30$1.20204,8001.7554YesNo
MiniMax-M2.5
$0.30$1.20204,8000.9757YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.0730YesYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.4389NoNo
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.7418NoNo
DeepSeek-V3
$0.40$1.3064,0001.7330YesNo
DeepSeek-V3
deepinfra
cheapest fastest
$0.32$0.89163,8400.4033YesYes
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.5982NoNo
tiny-aya-earth
---0.19133NoNo
tiny-aya-fire
---0.35132NoNo
command-a-plus-05-2026-bf16
---0.14154YesYes
command-a-vision-07-2025
---0.2447NoYes
Ternary-Bonsai-27B-AWQ-4bit
$0.00$0.00262,1440.3393YesNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.5134NoNo
Llama-4-Scout-17B-16E-Instruct
-------
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.6038NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest fastest
$0.09$0.29890,0000.6073YesNo
Llama-4-Scout-17B-16E-Instruct
$0.10$0.30327,6800.3063YesYes
Gemma-4-31B-it-pearl
$0.28$0.86262,1440.2942YesNo
Kimi-K2-Instruct
$0.57$2.30131,0720.8339YesNo
Qwen3-235B-A22B-Thinking-2507
novita
fastest
$0.30$3.00131,0720.7647YesNo
Qwen3-235B-A22B-Thinking-2507
deepinfra
cheapest
$0.23$2.30262,1440.4040YesNo
Qwen3-VL-30B-A3B-Instruct
novita
fastest
$0.20$0.70131,0720.5669YesYes
Qwen3-VL-30B-A3B-Instruct
deepinfra
cheapest
$0.15$0.60262,1440.3834YesYes
command-a-plus-05-2026-fp8
---0.13143YesYes
GLM-4.5V-FP8
---1.7382YesNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1440.7339YesYes
c4ai-command-a-03-2025
---0.2453YesYes
DeepSeek-V3.1-Terminus
novita
fastest
$0.27$1.00131,0721.6427YesYes
DeepSeek-V3.1-Terminus
deepinfra
cheapest
$0.27$0.95163,8400.7222YesYes
c4ai-command-r7b-12-2024
---0.2282YesYes
c4ai-command-r-08-2024
---0.2039YesYes
GLM-4.7-FP8
---2.3453YesNo
GLM-4.6V-FP8
---3.3352YesNo
aya-expanse-32b
---0.2744NoNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.9147YesNo
tiny-aya-global
---0.18134NoNo
GLM-4.6-FP8
---4.2626YesNo
aya-vision-32b
---0.2042NoNo
c4ai-command-r7b-arabic-02-2025
---0.2439YesNo
MiniMax-M1-80k
$0.55$2.201,000,0001.5747YesNo
command-a-reasoning-08-2025
---0.18103YesYes
command-a-translate-08-2025
---0.2471YesYes
tiny-aya-water
---0.36131NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.3373NoNo
WizardLM-2-8x22B
$0.62$0.6265,5350.5011NoNo
Hermes-3-Llama-3.1-70B
$0.70$0.70131,0720.1835NoYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.48148NoYes
DeepSeek-R1-0528
$0.70$2.50163,8401.4219YesYes
DeepSeek-R1-0528
deepinfra
cheapest fastest
$0.50$2.15163,8400.5633YesNo
gemma-3n-E4B-it
$0.06$0.1232,7680.2258NoYes
cogito-671b-v2.1
$1.25$1.25163,8400.3071NoNo
cogito-671b-v2.1
-------
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2370NoNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.58183NoYes
Kimi-K2.5
novita
fastest
$0.60$3.00262,1441.2738YesYes
Kimi-K2.5
deepinfra
cheapest
$0.45$2.25262,1440.9033YesYes
GLM-4-32B-0414
$0.55$1.6632,0000.7255NoNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.4768NoYes
DeepSeek-V3-0324
$0.27$1.12163,8401.2531YesNo
DeepSeek-V3-0324
deepinfra
cheapest fastest
$0.24$0.90163,8400.7584YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.3542YesYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.4951NoYes
Apertus-70B-Instruct-2509
$0.82$2.92-0.5958NoYes