Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.69$3.381,048,5761.4534YesNo
DeepSeek-V4-Pro
-------
DeepSeek-V4-Pro
--1,048,5761.5719YesYes
DeepSeek-V4-Pro
deepinfra
fastest
$1.74$3.4865,5360.5238YesYes
DeepSeek-V4-Flash
novita
cheapest fastest
$0.14$0.281,048,5761.2355YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5763.8114YesNo
Qwen3.6-35B-A3B
$0.15$0.95262,1440.17142YesYes
gemma-4-31B-it
-------
gemma-4-31B-it
$0.20$0.50262,1440.5312YesNo
gemma-4-31B-it
deepinfra
cheapest fastest
$0.13$0.38262,1440.8129YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1442.0931YesNo
Kimi-K2.6
$1.20$4.50262,1440.6417YesYes
Kimi-K2.6
fireworks-ai
fastest
--262,1440.5784YesNo
Kimi-K2.6
$0.75$3.50262,1440.6837YesNo
gemma-4-26B-A4B-it
novita
fastest
$0.13$0.40262,1441.5732YesNo
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.3230YesYes
Ling-2.6-1T
$0.30$2.50262,1441.3079YesYes
GLM-5.1
$1.40$4.40202,7520.6031YesYes
GLM-5.1
--202,7521.8725YesNo
GLM-5.1
---3.8526NoNo
GLM-5.1
deepinfra
cheapest fastest
$1.05$3.50202,7520.7140YesYes
Qwen3.5-9B
together
cheapest fastest
$0.10$0.15262,1440.3973YesYes
Qwen3.5-9B
$0.12$0.18262,1440.3938YesYes
gpt-oss-120b
$0.15$0.75131,0720.16441YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.4437YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.131,063YesNo
gpt-oss-120b
$0.22$0.59131,0720.90540YesYes
gpt-oss-120b
$0.10$0.40131,0720.81113YesYes
gpt-oss-120b
$0.15$0.60131,0720.2677YesNo
gpt-oss-120b
$0.15$0.60131,0720.3379YesNo
gpt-oss-120b
---0.46146YesYes
gpt-oss-120b
$0.09$0.47131,0720.3031YesYes
Qwen3-Coder-Next
$0.20$1.50262,1441.02115YesNo
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.3848NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.161,748NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.8460NoYes
Llama-3.1-8B-Instruct
---0.39126YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8001.3032YesNo
MiniMax-M2.7
$0.30$1.20196,6080.6921YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.72131YesNo
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.4455YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.4830YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.32694YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.4781NoYes
gpt-oss-20b
$0.05$0.20131,0720.87153YesYes
gpt-oss-20b
$0.05$0.20131,0720.27109YesYes
gpt-oss-20b
$0.05$0.20131,0720.4961YesNo
gpt-oss-20b
$0.05$0.18131,0720.3635YesYes
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9600.9056YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.30117YesNo
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.6660YesYes
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.24137YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.26122YesYes
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.3874NoYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.7359YesNo
Llama-3.2-1B-Instruct
--131,0000.39195NoNo
DeepSeek-R1
$0.70$2.5064,0001.8620YesYes
DeepSeek-R1
-------
DeepSeek-R1
hyperbolic
cheapest fastest
$2.00$2.00163,8400.7598NoNo
DeepSeek-R1
$3.00$7.00163,8400.5783NoYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1441.0453YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1441.10103YesYes
Qwen3.5-397B-A17B
---0.5348YesYes
Qwen3.5-397B-A17B
$0.49$3.60262,1441.1222YesYes
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.7829YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8401.5950YesNo
Step-3.5-Flash
$0.10$0.30262,1440.4662YesNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.7174YesNo
Llama-3.3-70B-Instruct
$0.59$0.79131,0720.24231YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4349YesNo
Llama-3.3-70B-Instruct
sambanova
fastest
$0.60$1.20131,0721.03255YesYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.9217NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.4071NoNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.6735YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.60127NoNo
Llama-3.3-70B-Instruct
---0.2982YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.4532YesYes
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1440.7670YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.2664YesYes
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8001.0568YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.63142YesNo
DeepSeek-OCR
$0.03$0.038,1921.07168NoNo
GLM-5
novita
cheapest
$1.00$3.20202,8001.7039YesNo
GLM-5
$1.00$3.20202,7520.4257YesNo
GLM-5
fireworks-ai
fastest
--202,7521.1170YesNo
GLM-5
---3.8533YesNo
Kimi-K2.5
novita
fastest
$0.60$3.00262,1441.1838YesYes
Kimi-K2.5
together
cheapest
$0.50$2.80262,1440.7622YesYes
Kimi-K2.5
--262,1440.5033YesNo
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8000.7659YesNo
GLM-4.6
---2.1929YesNo
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30$1.30262,1441.1454YesYes
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
fastest
$2.00$2.00262,1440.4776NoNo
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.2654YesYes
Qwen3.5-27B
$0.30$2.40262,1440.7856YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1441.26101YesNo
Arch-Router-1.5B
---0.1180NoYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.9438NoYes
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.9528NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.4756YesNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.7561NoYes
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.75142NoNo
Qwen3-14B
$0.07$0.2040,9600.8251YesNo
GLM-5.1-FP8
--202,7521.4324YesNo
GLM-5.1-FP8
zai-org
fastest
---3.5730YesNo
MiMo-V2-Flash
$0.10$0.30262,1441.21106YesNo
tiny-aya-global
---0.19122NoNo
Qwen3-VL-30B-A3B-Instruct
novita
cheapest fastest
$0.20$0.70131,0720.80104YesYes
Qwen3-VL-30B-A3B-Instruct
--262,1440.21103YesNo
DeepSeek-V3
$0.40$1.3064,0001.2133YesNo
DeepSeek-V3
together
cheapest fastest
$1.25$1.25131,0720.5138YesYes
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8401.0833YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
hyperbolic
fastest
$1.25$1.25163,8400.7859NoNo
DeepSeek-V3-0324
$1.25$1.25131,0720.5933YesYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.66113NoYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.8766NoYes
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0722.57257YesYes
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.9121NoYes
GLM-4.7
novita
cheapest
$0.60$2.20204,8000.8043YesNo
GLM-4.7
cerebras
fastest
---0.14479YesNo
GLM-4.7
--202,7521.4162YesNo
GLM-4.7
---2.4928YesNo
Kimi-K2-Instruct
$0.57$2.30131,0720.9629YesNo
GLM-4.7-Flash
novita
cheapest
$0.07$0.40200,0001.9450NoNo
GLM-4.7-Flash
zai-org
fastest
---2.2865NoNo
Qwen3-Coder-Next-FP8
$0.50$1.20262,1440.49133YesYes
MiniMax-M2.1
$0.30$1.20204,8001.3063YesNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.1513NoNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.0543YesNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.6539YesYes
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.1348YesYes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.13258YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7681.0220YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1441.3735YesNo
Qwen3-235B-A22B-Instruct-2507
---0.4941YesYes
c4ai-command-a-03-2025
---1.3330YesNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.5047NoYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.86100NoNo
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.5138NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.9116NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3672YesYes
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8402.3821YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
$3.00$3.00163,8400.6957NoNo
DeepSeek-R1-0528
together
fastest
$3.00$7.00163,8400.4786NoYes
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0721.0153YesNo
GLM-4.5
---2.5047YesNo
GLM-4.6V-FP8
---3.2742YesNo
c4ai-command-r7b-12-2024
---0.2172YesNo
gemma-3-27b-it
---0.4048YesYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.31374YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3044NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.9033YesYes
Llama-3.1-70B-Instruct
---0.3772YesYes
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.1326YesYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.8479NoYes
Qwen3-30B-A3B
$0.09$0.4540,9600.7453YesNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.8157NoYes
Qwen3-235B-A22B
$0.20$0.8040,9600.947NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0000.9532YesYes
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.8926NoYes
MiniMax-M2
$0.30$1.20204,8001.0064YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.5930NoNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.8395YesNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.2615YesNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.5934YesNo
gemma-3n-E4B-it
$0.06$0.1232,7680.9231NoYes
command-a-translate-08-2025
---0.3368YesNo
tiny-aya-water
---0.23121NoNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.3260NoNo
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.5324YesYes
DeepSeek-V3.1
$0.60$1.70131,0720.4438YesYes
DeepSeek-V3.1
fireworks-ai
fastest
--163,8400.3642NoNo
rnj-1-instruct
$0.15$0.1532,7680.19122YesYes
cogito-671b-v2.1
$1.25$1.25163,8400.2562NoNo
cogito-671b-v2.1
-------
command-a-reasoning-08-2025
---0.4048YesNo
command-a-vision-07-2025
---0.1846NoNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.79166YesNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.9338YesNo
c4ai-command-r7b-arabic-02-2025
---0.1799YesNo
aya-vision-32b
---0.2337NoNo
aya-expanse-32b
---0.1740NoNo
c4ai-command-r-08-2024
---0.1759YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.4926YesYes
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0720.6448YesNo
GLM-4.5-Air
zai-org
fastest
---2.2551YesNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5361.8442YesNo
GLM-4.5V
zai-org
fastest
---2.2544YesNo
GLM-4.6-FP8
---1.7075YesNo
GLM-4.5V-FP8
---2.2738YesNo
GLM-4.6V
---2.2650YesNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0721.1551YesNo
GLM-4.6V-Flash
zai-org
fastest
---4.5255NoNo
GLM-4.7-FP8
---3.1331YesNo
Kimi-K2-Thinking
$0.60$2.50262,1440.9944YesNo
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0720.86122YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.31138YesNo
QwQ-32B
$0.18$0.20131,0720.8728YesYes
L3-8B-Lunaris-v1
$0.05$0.058,1921.1538NoNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.5729NoNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.16258YesNo
Qwen3-32B
$0.10$0.4540,9600.5276NoNo
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9601.0326YesNo
Qwen3-32B
$0.09$0.2532,7680.3436YesYes
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.44109NoNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.4324NoYes
WizardLM-2-8x22B
$0.62$0.6265,5351.1312NoNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.4931NoYes
Apertus-70B-Instruct-2509
$0.82$2.92-0.6560NoYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.3040YesYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.2865YesYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5761.5914NoNo
GLM-4-32B-0414
$0.55$1.6632,0001.0738NoNo
gpt-oss-safeguard-20b
--131,0720.12854YesNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.7416NoNo
MiniMax-M1-80k
$0.55$2.201,000,0001.0856YesNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.5122NoNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0000.9443NoNo
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.9155YesYes
tiny-aya-fire
---0.20122NoNo
tiny-aya-earth
---0.23121NoNo