Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.69$3.381,048,5760.8036YesNo
DeepSeek-V4-Pro
together
fastest
$2.10$4.40512,0000.6656NoNo
DeepSeek-V4-Pro
--1,048,5761.5910YesNo
DeepSeek-V4-Pro
$1.74$3.4865,5360.4851YesYes
DeepSeek-V4-Flash
novita
cheapest fastest
$0.14$0.281,048,5761.1179YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5761.7721YesYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.2093YesYes
gemma-4-31B-it
$0.14$0.40262,1440.3714NoNo
gemma-4-31B-it
$0.20$0.50262,1440.4114YesYes
gemma-4-31B-it
deepinfra
cheapest fastest
$0.13$0.38262,1441.6221NoYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1442.4329NoNo
Kimi-K2.6
$1.20$4.50262,1440.4918YesYes
Kimi-K2.6
fireworks-ai
fastest
--262,1440.4861YesNo
Kimi-K2.6
$0.75$3.50262,1440.9025YesNo
gemma-4-26B-A4B-it
$0.13$0.40262,1441.2036YesNo
gemma-4-26B-A4B-it
deepinfra
cheapest fastest
$0.07$0.34262,1440.3164YesYes
GLM-5.1
$1.40$4.40202,7520.6326YesYes
GLM-5.1
--202,7521.4528YesNo
GLM-5.1
zai-org
fastest
---3.0835YesNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7520.7726YesYes
Qwen3.5-9B
together
cheapest fastest
$0.10$0.15262,1440.3853YesYes
Qwen3.5-9B
$0.12$0.18262,1440.5339YesYes
Ling-2.6-1T
$0.30$2.50262,1441.5973YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.4453NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.151,436NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0721.9318NoYes
Llama-3.1-8B-Instruct
---0.30150YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8000.9151YesNo
MiniMax-M2.7
$0.30$1.20196,6080.6324YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.89130YesNo
gpt-oss-120b
$0.15$0.75131,0720.26429YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0721.3919YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.141,228YesNo
gpt-oss-120b
$0.22$0.59131,0720.69557YesYes
gpt-oss-120b
$0.10$0.40131,0720.87107YesYes
gpt-oss-120b
$0.15$0.60131,0720.3341YesNo
gpt-oss-120b
$0.15$0.60131,0720.26109YesNo
gpt-oss-120b
---0.30182YesYes
gpt-oss-120b
$0.09$0.47131,0720.39125YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.21121YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.38725YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.5296NoYes
gpt-oss-20b
$0.05$0.20131,0720.96155YesYes
gpt-oss-20b
$0.05$0.20131,0720.34132YesYes
gpt-oss-20b
$0.05$0.20131,0720.5457YesNo
gpt-oss-20b
$0.05$0.18131,0720.4163YesYes
Qwen3-Coder-Next
$0.20$1.50262,1441.29123YesNo
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.4378YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.4667YesYes
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.4283NoNo
DeepSeek-OCR
$0.03$0.038,1921.0795NoNo
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9600.9054YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.2792YesNo
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.6557YesNo
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.24137YesYes
DeepSeek-R1
$0.70$2.5064,0001.9324YesYes
DeepSeek-R1
-------
DeepSeek-R1
-------
DeepSeek-R1
-------
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1441.1856YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.99106YesYes
Qwen3.5-397B-A17B
---0.47100YesYes
Qwen3.5-397B-A17B
$0.49$3.60262,1440.2472YesYes
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.1735YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8401.0548YesNo
Qwen3-14B
$0.07$0.2040,9600.9450YesNo
Step-3.5-Flash
$0.10$0.30262,1440.3032YesNo
Kimi-K2.5
$0.60$3.00262,1441.2138YesYes
Kimi-K2.5
together
cheapest fastest
$0.50$2.80262,1440.4042YesYes
Kimi-K2.5
--262,1440.5133YesNo
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8000.9371YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.36150YesNo
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.94140NoNo
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.8338NoYes
GLM-5
novita
cheapest
$1.00$3.20202,8001.5627YesNo
GLM-5
together
fastest
$1.00$3.20202,7520.7393YesYes
GLM-5
--202,7522.0359YesNo
GLM-5
---2.9645YesNo
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.38$1.55262,1441.1057YesYes
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
fastest
$2.00$2.00262,1440.5176NoNo
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.2672YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.8259NoYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.8088YesNo
Llama-3.2-1B-Instruct
--131,0000.39199NoNo
GLM-4.7-Flash
novita
cheapest fastest
$0.07$0.40200,0000.5563NoNo
GLM-4.7-Flash
---2.4161YesNo
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1440.69106YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.2795YesYes
Kimi-K2-Instruct-0905
$0.60$2.50262,1440.8053NoNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8001.3046YesNo
GLM-4.7
cerebras
fastest
---0.14373NoNo
GLM-4.7
--202,7521.04107YesNo
GLM-4.7
---2.6034NoNo
Llama-3.1-70B-Instruct
---0.3384YesYes
Kimi-K2-Instruct
$0.57$2.30131,0722.6024YesNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0721.0228NoYes
Arch-Router-1.5B
---0.1179NoYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.6960YesNo
DeepSeek-V3
$0.40$1.3064,0001.1035YesNo
DeepSeek-V3
-------
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.3235NoYes
GLM-5.1-FP8
--202,7521.4724YesNo
GLM-5.1-FP8
zai-org
fastest
---3.6033YesNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.9028NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.39122YesNo
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0721.89303YesYes
Qwen3.5-27B
$0.30$2.40262,1440.7358YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.73105YesNo
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8001.5145YesNo
GLM-4.6
---3.7520YesNo
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.8065NoNo
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.44366YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.5154NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.8233YesYes
MiniMax-M2.1
$0.30$1.20204,8000.7977YesNo
DeepSeek-V3-0324
$0.27$1.12163,8400.7837YesYes
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20$0.70131,0720.8390YesYes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
--262,1440.30136YesNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.0746YesNo
Llama-3.3-70B-Instruct
$0.59$0.79131,0720.18283YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.5724YesNo
Llama-3.3-70B-Instruct
sambanova
fastest
$0.60$1.20131,0720.37312YesYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.9116NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.2834NoNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0721.7240YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.62113NoNo
Llama-3.3-70B-Instruct
---0.3483YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.4635YesYes
WizardLM-2-8x22B
$0.62$0.6265,5350.7320NoNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6673NoNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1921.3744NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0721.1117NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3285YesYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.63102NoYes
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.2545YesYes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.20570YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7681.0824YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.2240YesYes
Qwen3-235B-A22B-Instruct-2507
---0.38100YesYes
gpt-oss-safeguard-20b
--131,0720.58666YesNo
tiny-aya-global
---1.54100NoNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.1513NoNo
GLM-4.6V-FP8
---2.5852YesNo
MiMo-V2-Flash
$0.10$0.30262,1441.11114YesNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5364.0423NoYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.7687NoYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0721.1114NoYes
QwQ-32B
$0.18$0.20131,0720.9428YesNo
DeepSeek-R1-0528
$0.70$2.50163,8401.6224NoNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
Qwen3-235B-A22B
$0.20$0.8040,9602.8816NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.2223YesYes
Kimi-K2-Thinking
$0.60$2.50262,1441.0753YesNo
MiniMax-M2
$0.30$1.20204,8000.8672YesNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.8134YesYes
Qwen3-30B-A3B
$0.09$0.4540,9600.6740YesNo
gemma-3n-E4B-it
$0.06$0.1232,7680.2144NoYes
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.6037YesNo
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.3930YesYes
DeepSeek-V3.1
-------
DeepSeek-V3.1
fireworks-ai
fastest
--163,8400.4145NoNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2556NoNo
command-a-reasoning-08-2025
---0.3353YesNo
cogito-671b-v2.1
$1.25$1.25163,8400.2962NoNo
cogito-671b-v2.1
-------
rnj-1-instruct
$0.15$0.1532,7680.18121YesYes
tiny-aya-water
---0.96110NoNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0720.8651YesNo
GLM-4.6V-Flash
zai-org
fastest
---1.5574NoNo
tiny-aya-earth
---0.99111NoNo
tiny-aya-fire
---0.62116NoNo
GLM-4.5V-FP8
---2.4740YesNo
c4ai-command-a-03-2025
---0.4951YesNo
c4ai-command-r7b-12-2024
---0.2477YesNo
GLM-4.7-FP8
---2.1457YesNo
c4ai-command-r-08-2024
---0.1959YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5361.7431NoNo
GLM-4.6V
---2.8650YesNo
command-a-vision-07-2025
---0.1647NoNo
GLM-4.6-FP8
---3.4615YesNo
aya-expanse-32b
---0.4841NoNo
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5361.5134YesNo
GLM-4.5V
---2.5733YesNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.5461YesNo
GLM-4.5
---2.2153YesNo
aya-vision-32b
---0.2337NoNo
c4ai-command-r7b-arabic-02-2025
---0.1897YesNo
MiniMax-M1-80k
$0.55$2.201,000,0000.9472YesNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.8390YesNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.4837NoYes
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.25276YesNo
Qwen3-32B
$0.10$0.4540,9600.6626NoNo
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.9526YesNo
Qwen3-32B
$0.09$0.2532,7680.4125YesYes
L3-8B-Lunaris-v1
$0.05$0.058,1922.2032NoNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.7034NoNo
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.40112NoNo
Apertus-70B-Instruct-2509
$0.82$2.92-0.7061NoYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.6351NoYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.2448YesYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.2764YesYes
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.4722NoYes
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.9214NoNo
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0720.92118YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.31138NoNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.3420NoYes
gemma-3-27b-it
---0.4244YesYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.1645NoNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.7440YesNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.8295YesNo
GLM-4-32B-0414
$0.55$1.6632,0000.8043NoNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.4631YesYes
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.1030YesYes
GLM-4.5-Air
$0.13$0.85131,0720.7077YesNo
GLM-4.5-Air
-------
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.2070YesYes