Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.74$3.481,048,5761.0927YesNo
DeepSeek-V4-Pro
$2.10$4.40512,0000.5319YesYes
DeepSeek-V4-Pro
fireworks-ai
fastest
--1,048,5760.9255YesYes
DeepSeek-V4-Pro
---0.5129NoNo
DeepSeek-V4-Flash
novita
cheapest fastest
$0.14$0.281,048,5761.0479YesNo
DeepSeek-V4-Flash
---1.5512YesNo
Qwen3.6-35B-A3B
---0.2597YesYes
Kimi-K2.6
novita
cheapest
$0.95$4.00262,1441.6440YesNo
Kimi-K2.6
$1.20$4.50262,1441.1872YesYes
Kimi-K2.6
fireworks-ai
fastest
--262,1440.3975YesNo
Kimi-K2.6
---0.9124YesYes
gemma-4-31B-it
novita
cheapest fastest
$0.14$0.40262,1441.0239YesNo
gemma-4-31B-it
$0.20$0.50262,1440.4813YesYes
gemma-4-31B-it
---0.4526YesYes
Ling-2.6-1T
$0.00$0.00262,1440.7482YesYes
GLM-5.1
together
cheapest
$1.40$4.40202,7520.6040YesYes
GLM-5.1
--202,7521.7128YesNo
GLM-5.1
---3.8131YesNo
GLM-5.1
deepinfra
fastest
---0.8849YesYes
gemma-4-26B-A4B-it
novita
cheapest
$0.13$0.40262,1440.4939YesYes
gemma-4-26B-A4B-it
deepinfra
fastest
---0.3969YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8001.5333YesNo
MiniMax-M2.7
$0.30$1.20196,6080.4523YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6081.5996YesNo
Qwen3.5-9B
together
cheapest fastest
$0.10$0.15262,1440.3975YesYes
Qwen3.5-9B
$0.12$0.18262,1440.4541YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.3861NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.221,406NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.7359NoYes
Llama-3.1-8B-Instruct
---0.27151YesYes
gpt-oss-120b
$0.15$0.75131,0720.18438YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.4443YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.151,142YesNo
gpt-oss-120b
$0.22$0.59131,0720.55586YesYes
gpt-oss-120b
$0.10$0.40131,0720.88106YesYes
gpt-oss-120b
$0.15$0.60131,0720.4838YesYes
gpt-oss-120b
$0.15$0.60131,0720.41144YesNo
gpt-oss-120b
---0.38177YesYes
gpt-oss-120b
$0.09$0.47131,0720.35130YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.10842YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.53134NoNo
gpt-oss-20b
$0.05$0.20131,0720.91154YesYes
gpt-oss-20b
$0.05$0.20131,0720.26112YesYes
gpt-oss-20b
$0.05$0.20131,0720.6858YesNo
gpt-oss-20b
$0.05$0.18131,0720.2989YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.22118YesYes
Qwen3-Coder-Next
$0.20$1.50262,1441.10108YesNo
Qwen3-Coder-30B-A3B-Instruct
---0.3570YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest fastest
$0.07$0.26262,1440.4077YesYes
Kimi-K2.5
novita
fastest
$0.60$3.00262,1441.0845YesYes
Kimi-K2.5
together
cheapest
$0.50$2.80262,1440.3839YesYes
Kimi-K2.5
--262,1440.3243YesNo
Llama-3.3-70B-Instruct
$0.59$0.79131,0720.20243YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4843YesNo
Llama-3.3-70B-Instruct
sambanova
fastest
$0.60$1.20131,0720.34290NoNo
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.0316NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.1449NoNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.6276YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.53125NoNo
Llama-3.3-70B-Instruct
---0.2885YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.5038YesYes
Qwen3.5-35B-A3B
$0.25$2.00262,1440.72102YesNo
Llama-3.2-1B-Instruct
--131,0000.47199NoNo
Arch-Router-1.5B
---0.1072NoYes
GLM-4.7-Flash
$0.07$0.40200,0003.3851NoNo
GLM-4.7-Flash
-------
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.7961YesNo
Qwen3.5-27B
$0.30$2.40262,1440.7257YesNo
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.4178NoYes
GLM-5
novita
cheapest
$1.00$3.20202,8001.6837YesNo
GLM-5
$1.00$3.20202,7520.5853YesYes
GLM-5
fireworks-ai
fastest
--202,7521.7358YesNo
GLM-5
---3.5531NoNo
DeepSeek-R1
$0.70$2.5064,0001.9324YesYes
DeepSeek-R1
-------
DeepSeek-R1
hyperbolic
cheapest fastest
$2.00$2.00163,8400.7698NoNo
DeepSeek-R1
$3.00$7.00163,8400.4987NoYes
MiMo-V2-Flash
$0.10$0.30262,1441.3296YesNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0721.0828NoYes
Qwen3.5-122B-A10B
novita
cheapest
$0.40$3.20262,1440.7695YesNo
Qwen3.5-122B-A10B
deepinfra
fastest
---0.2898YesYes
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9600.9254YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.26105YesNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.7761NoYes
c4ai-command-r7b-12-2024
---0.2777YesNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.9026YesNo
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.3227YesNo
DeepSeek-V3.2
fireworks-ai
fastest
--163,8402.7645YesNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.9128NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.38103YesNo
gpt-oss-safeguard-20b
--131,0720.38680YesNo
GLM-4.6
novita
cheapest
$0.55$2.20204,8000.6835YesNo
GLM-4.6
zai-org
fastest
---2.6149YesNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8000.7549YesNo
GLM-4.7
cerebras
fastest
---0.18444YesNo
GLM-4.7
--202,7522.56106YesNo
GLM-4.7
---3.2544YesNo
DeepSeek-V3
$0.40$1.3064,0001.1933YesNo
DeepSeek-V3
together
cheapest fastest
$1.25$1.25131,0720.4242YesYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.82334YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3147NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.8633YesYes
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8000.9064YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.7897YesNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0004.7513NoNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.7888NoYes
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.84140NoNo
Qwen3-Coder-Next-FP8
$0.50$1.20262,1440.49138YesYes
Qwen3-14B
$0.07$0.2040,9600.8550YesYes
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.27266YesNo
Qwen3-32B
$0.10$0.4540,9600.5432NoNo
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.9526YesYes
Qwen3-32B
$0.09$0.2532,7680.4027YesYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.4434NoYes
gemma-3n-E4B-it
$0.06$0.1232,7680.2723NoYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1441.2957YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.43101YesYes
Qwen3.5-397B-A17B
---0.4493YesYes
Qwen3.5-397B-A17B
---0.3495YesYes
GLM-5.1-FP8
--202,7520.9032YesNo
GLM-5.1-FP8
zai-org
fastest
---3.4233YesNo
QwQ-32B
$0.18$0.20131,0721.0228YesNo
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0721.08360YesYes
Qwen3-30B-A3B
$0.09$0.4540,9600.7146YesNo
Qwen3-VL-30B-A3B-Instruct
novita
cheapest fastest
$0.20$0.70131,0720.6646YesYes
Qwen3-VL-30B-A3B-Instruct
--262,1440.3341YesNo
Step-3.5-Flash
---0.2845YesNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.8546YesNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.1349YesYes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.30586NoNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7681.0220YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.3344YesYes
Qwen3-235B-A22B-Instruct-2507
---0.4292YesYes
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8402.2122NoNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
$3.00$3.00163,8400.6557NoNo
DeepSeek-R1-0528
together
fastest
$3.00$7.00163,8400.5290NoYes
gemma-3-27b-it
---0.6547YesYes
L3-8B-Lunaris-v1
$0.05$0.058,1920.5636NoNo
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8400.9734YesYes
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
hyperbolic
fastest
$1.25$1.25163,8400.6759NoNo
DeepSeek-V3-0324
$1.25$1.25131,0723.5820NoYes
Apertus-70B-Instruct-2509
$0.82$2.92-0.6755NoYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.7676NoYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.4426NoYes
Qwen3-235B-A22B
$0.20$0.8040,9600.7111NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0000.8532YesYes
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.5222NoYes
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.2437YesYes
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0720.94121YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.21123YesNo
rnj-1-instruct
$0.15$0.1532,7680.20117YesYes
Llama-Guard-4-12B
$0.20$0.201,048,5760.1711NoNo
command-a-reasoning-08-2025
---0.3278YesNo
aya-expanse-32b
---0.5640NoNo
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.9166NoNo
Kimi-K2-Thinking
$0.60$2.50262,1440.8944YesNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.7257NoYes
DeepSeek-OCR
$0.03$0.038,1920.64164NoNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.2223YesYes
GLM-4.6V-Flash
$0.30$0.90131,0720.9038YesNo
GLM-4.6V-Flash
-------
Kimi-K2-Instruct
$0.57$2.30131,0721.0929YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.5023YesYes
Qwen3-VL-8B-Instruct
$0.08$0.50131,0720.7068YesYes
Qwen3-VL-8B-Instruct
-------
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.3523YesYes
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30$1.30262,1440.9758YesYes
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
fastest
$2.00$2.00262,1440.9976NoNo
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.1927YesYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.75107YesNo
tiny-aya-global
---0.29120NoNo
tiny-aya-earth
---0.26121NoNo
command-a-vision-07-2025
---0.2446NoNo
tiny-aya-fire
---0.23121NoNo
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.7787YesNo
GLM-4.5-Air
---1.6876YesNo
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.5223YesYes
DeepSeek-V3.1
$0.60$1.70131,0720.8236YesYes
DeepSeek-V3.1
fireworks-ai
fastest
--163,8400.3851YesNo
cogito-671b-v2.1
$1.25$1.25163,8400.3672NoNo
cogito-671b-v2.1
-------
aya-vision-32b
---0.2537NoNo
MiniMax-M1-80k
$0.55$2.201,000,0001.1757YesNo
c4ai-command-a-03-2025
---0.6725YesNo
c4ai-command-r-08-2024
---0.1830YesNo
GLM-4.7-FP8
---2.8136YesNo
GLM-4.6V-FP8
---3.3939YesNo
GLM-4.6V
---4.1235NoNo
GLM-4.5V-FP8
---2.9229YesNo
GLM-4.6-FP8
---2.4730YesNo
tiny-aya-water
---0.27121NoNo
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5360.8240YesNo
GLM-4.5V
---3.5928YesNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.8152NoNo
GLM-4.5
---2.7346NoNo
c4ai-command-r7b-arabic-02-2025
---0.2478YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5361.9828NoNo
MiniMax-M2
$0.30$1.20204,8000.7963YesNo
command-a-translate-08-2025
---0.4868YesNo
WizardLM-2-8x22B
$0.62$0.6265,5351.169NoNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.3419NoYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.8294NoNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.1139NoNo
GLM-4-32B-0414
$0.55$1.6632,0001.2736NoNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.2448NoYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.3044YesYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-2.2962YesYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.8039YesNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.6027NoNo
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.43111NoNo
MiniMax-M2.1
$0.30$1.20204,8001.1666YesNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2482NoNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.7082NoNo
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.9637NoYes
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.4848NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0721.1616NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.4183YesYes
Llama-3.1-70B-Instruct
---0.3184YesYes
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5361.2922NoYes
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.87168YesNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.6435YesYes