Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.69$3.381,048,5760.8130YesNo
DeepSeek-V4-Pro
together
fastest
$2.10$4.40512,0000.5141YesYes
DeepSeek-V4-Pro
$1.74$3.4865,5360.5722YesYes
DeepSeek-V4-Flash
novita
cheapest fastest
$0.14$0.281,048,5760.9790YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5760.5726YesYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.4078YesYes
gemma-4-31B-it
$0.14$0.40262,1440.8013YesNo
gemma-4-31B-it
$0.20$0.50262,1440.4010YesYes
gemma-4-31B-it
deepinfra
cheapest fastest
$0.13$0.38262,1440.5417YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.3851YesNo
Kimi-K2.6
together
fastest
$1.20$4.50262,1440.9789YesYes
Kimi-K2.6
--262,1440.4088YesNo
Kimi-K2.6
$0.75$3.50262,1440.6258YesNo
gemma-4-26B-A4B-it
$0.13$0.40262,1444.1131YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest fastest
$0.07$0.34262,1440.3064YesYes
GLM-5.1
together
fastest
$1.40$4.40202,7520.4748YesYes
GLM-5.1
--202,7521.4729YesNo
GLM-5.1
---3.4331NoNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7520.9025YesYes
Ling-2.6-1T
$0.30$2.50262,1441.0377YesYes
Qwen3.5-9B
together
cheapest fastest
$0.10$0.15262,1440.5167YesYes
Qwen3.5-9B
$0.12$0.18262,1440.5441YesNo
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.4253NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.131,736NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0721.9718NoYes
Llama-3.1-8B-Instruct
---0.28151YesYes
gpt-oss-120b
$0.15$0.75131,0720.16445YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.5914YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.151,168YesNo
gpt-oss-120b
$0.22$0.59131,0720.95494YesYes
gpt-oss-120b
$0.10$0.40131,0720.81114YesYes
gpt-oss-120b
$0.15$0.60131,0720.27195YesYes
gpt-oss-120b
$0.15$0.60131,0720.31129YesNo
gpt-oss-120b
---0.30164YesYes
gpt-oss-120b
$0.09$0.47131,0720.49121YesYes
Qwen3-Coder-Next
$0.20$1.50262,1440.85128YesNo
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8000.9432YesNo
MiniMax-M2.7
$0.30$1.20196,6080.5627YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.30132YesNo
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.26110YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.4467YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.10761YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.6387NoYes
gpt-oss-20b
$0.05$0.20131,0720.87162YesYes
gpt-oss-20b
$0.05$0.20131,0720.3870YesYes
gpt-oss-20b
$0.05$0.20131,0720.5755YesNo
gpt-oss-20b
$0.05$0.18131,0720.4063YesYes
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.5777NoNo
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9600.7559YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.25100YesNo
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.8155YesNo
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.24137YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.39100YesYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1440.9554YesNo
Qwen3.5-397B-A17B
$0.60$3.60262,1440.5685YesYes
Qwen3.5-397B-A17B
scaleway
fastest
---0.37100YesYes
Qwen3.5-397B-A17B
$0.49$3.60262,1440.2992YesYes
DeepSeek-OCR
$0.03$0.038,1920.8497NoNo
DeepSeek-R1
$0.70$2.5064,0001.7922YesYes
DeepSeek-R1
-------
DeepSeek-R1
hyperbolic
cheapest fastest
$2.00$2.00163,8400.9098NoNo
DeepSeek-R1
$3.00$7.00163,8400.5866NoYes
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.2328YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8401.0045YesNo
Step-3.5-Flash
$0.10$0.30262,1440.3067YesNo
Qwen3-14B
$0.07$0.2040,9600.8947YesYes
Kimi-K2.5
$0.60$3.00262,1440.8234YesNo
Kimi-K2.5
together
cheapest
$0.50$2.80262,1440.5931YesYes
Kimi-K2.5
fireworks-ai
fastest
--262,1440.3386YesNo
Llama-3.2-1B-Instruct
--131,0000.52195NoNo
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8000.9760YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.64150YesNo
GLM-5
novita
cheapest
$1.00$3.20202,8002.0841YesNo
GLM-5
together
fastest
$1.00$3.20202,7520.6087YesYes
GLM-5
--202,7520.9180YesNo
GLM-5
-------
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.38$1.55262,1441.1053YesYes
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
fastest
$2.00$2.00262,1440.4776NoNo
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.1847YesYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.8035NoYes
Qwen3.5-27B
$0.30$2.40262,1440.6263YesNo
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.9459YesNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.8482YesNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.3639YesNo
MiMo-V2-Flash
$0.10$0.30262,1442.0096YesNo
GLM-4.7-Flash
novita
cheapest
$0.07$0.40200,0001.2965NoNo
GLM-4.7-Flash
zai-org
fastest
---1.8874YesNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8000.8658YesNo
GLM-4.7
cerebras
fastest
---0.13519YesNo
GLM-4.7
--202,7520.99102YesNo
GLM-4.7
---1.9959YesNo
Qwen3.5-122B-A10B
$0.40$3.20262,1440.7363YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest fastest
$0.29$2.40262,1440.2768YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.7361NoYes
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.83141NoNo
Kimi-K2-Instruct
$0.57$2.30131,0721.3922YesNo
Arch-Router-1.5B
---0.1275NoYes
DeepSeek-V3
$0.40$1.3064,0001.0935YesNo
DeepSeek-V3
together
cheapest fastest
$1.25$1.25131,0720.4758YesYes
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.9228NoYes
MiniMax-M2.1
$0.30$1.20204,8001.5657YesNo
Llama-3.1-70B-Instruct
---0.3384YesYes
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20$0.70131,0720.65115YesYes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
--262,1440.33118YesNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.8127NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.35122YesNo
Apertus-8B-Instruct-2509
$0.10$0.20-1.0628NoYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.5933NoYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.8565NoNo
GLM-4.6
novita
cheapest
$0.55$2.20204,8001.149YesNo
GLM-4.6
zai-org
fastest
---3.4641YesNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.2441YesNo
Qwen3-Coder-Next-FP8
$0.50$1.20262,1440.96113YesYes
tiny-aya-global
---0.20122NoNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.20262YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4642YesNo
Llama-3.3-70B-Instruct
$0.60$1.20131,0721.73226YesYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.9017NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.7438NoNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0721.1741YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.35135NoNo
Llama-3.3-70B-Instruct
---0.3084YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.3436YesYes
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.9358YesNo
GLM-4.5
---2.2942YesNo
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8402.3421YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
$3.00$3.00163,8400.7857NoNo
DeepSeek-R1-0528
together
fastest
$3.00$7.00163,8400.48105NoYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.30381YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3360NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.8133YesYes
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.1340YesYes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.12617YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7681.0619YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.4119YesYes
Qwen3-235B-A22B-Instruct-2507
---0.3861YesYes
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.4245NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0721.0416NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3484YesYes
GLM-4.6V-FP8
---2.9631YesNo
Qwen3-235B-A22B
$0.20$0.8040,9600.6014NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.1028YesYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
c4ai-command-r7b-12-2024
---0.2388YesNo
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0722.15258YesYes
GLM-5.1-FP8
--202,7521.0126YesNo
GLM-5.1-FP8
-------
Llama-Guard-4-12B
$0.20$0.201,048,5760.1513NoNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.3825YesYes
Qwen3.5-35B-A3B
$0.25$2.00262,1440.7998YesNo
Qwen3-30B-A3B
$0.09$0.4540,9600.7467YesNo
WizardLM-2-8x22B
$0.62$0.6265,5350.8612NoNo
Kimi-K2-Thinking
$0.60$2.50262,1441.1331YesNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.8820NoYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.8621NoYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.5978NoNo
MiniMax-M2
$0.30$1.20204,8000.8456YesNo
gemma-3n-E4B-it
$0.06$0.1232,7680.2356NoYes
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.5833YesNo
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8400.9934YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
hyperbolic
fastest
$1.25$1.25163,8400.7859NoNo
DeepSeek-V3-0324
$1.25$1.25131,0720.4556YesYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.8689YesNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2458NoNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.8838YesYes
cogito-671b-v2.1
$1.25$1.25163,8400.2469NoNo
cogito-671b-v2.1
-------
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.1824YesYes
DeepSeek-V3.1
$0.60$1.70131,0720.5632YesYes
DeepSeek-V3.1
fireworks-ai
fastest
--163,8400.2974NoNo
rnj-1-instruct
$0.15$0.1532,7680.22119YesYes
tiny-aya-earth
---0.19122NoNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5361.5131YesNo
GLM-4.5V
zai-org
fastest
---2.6542YesNo
GLM-4.7-FP8
---3.5948YesNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0721.0453YesNo
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0720.93119YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.27127YesNo
c4ai-command-a-03-2025
---0.5049YesNo
tiny-aya-water
---0.22121NoNo
command-a-translate-08-2025
---0.3565YesNo
command-a-reasoning-08-2025
---0.4846YesNo
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.6569YesNo
GLM-4.5-Air
---2.0861YesNo
command-a-vision-07-2025
---0.1747NoNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.85121YesNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0720.8935YesNo
GLM-4.6V-Flash
zai-org
fastest
---3.0358NoNo
c4ai-command-r7b-arabic-02-2025
---0.19104YesNo
aya-vision-32b
---0.2537NoNo
aya-expanse-32b
---0.1742NoNo
GLM-4.6-FP8
---3.4615YesNo
c4ai-command-r-08-2024
---0.6432YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.4522YesYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.4344NoYes
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.29321YesNo
Qwen3-32B
$0.10$0.4540,9600.5647NoNo
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.9127YesYes
Qwen3-32B
$0.09$0.2532,7680.3637YesYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.9288NoYes
QwQ-32B
$0.18$0.20131,0720.8828YesYes
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.4823NoYes
gpt-oss-safeguard-20b
--131,0720.18785YesNo
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.46110NoNo
Apertus-70B-Instruct-2509
$0.82$2.92-0.5161NoYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.2148NoYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.1146YesYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.0367YesYes
L3-70B-Euryale-v2.1
$1.48$1.488,1920.5837NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.4441NoNo
GLM-4-32B-0414
$0.55$1.6632,0001.0844NoNo
gemma-3-27b-it
---0.4548YesYes
DeepSeek-Prover-V2-671B
$0.70$2.50160,0001.5515NoNo
MiniMax-M1-80k
$0.55$2.201,000,0001.1748YesNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.5419NoYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.0643NoNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.6732NoNo
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.1745YesYes
tiny-aya-fire
---0.19122NoNo