Inference Providers

·

Metrics for top trending models

GLM-5.2
---1.5734NoNo
GLM-5.2
together
cheapest
$1.40$4.40262,1440.9257YesYes
GLM-5.2
---1.3341YesNo
GLM-5.2
---4.3827NoNo
GLM-5.2
deepinfra
fastest
---0.69108YesYes
MiniMax-M3
---1.5035YesNo
MiniMax-M3
together
cheapest fastest
$0.30$1.20524,2880.4481YesYes
MiniMax-M3
---1.9356YesNo
Kimi-K2.7-Code
---1.0754YesNo
Kimi-K2.7-Code
together
cheapest fastest
$0.95$4.00262,1440.4282YesYes
Kimi-K2.7-Code
---2.7142YesNo
Kimi-K2.7-Code
---0.8133YesNo
GLM-5.2-FP8
---3.4943NoNo
DeepSeek-V4-Pro
novita
cheapest fastest
$1.60$3.381,048,5760.6969YesNo
DeepSeek-V4-Pro
$1.74$3.48512,0000.5633YesYes
DeepSeek-V4-Pro
--1,048,5760.7059YesNo
DeepSeek-V4-Pro
$1.74$3.4865,5360.6732YesYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.24148YesYes
Qwen3.6-27B
ovhcloud
fastest
---0.7173YesYes
Qwen3.6-27B
---0.3172YesYes
DeepSeek-V4-Flash
novita
cheapest
$0.14$0.281,048,5762.0358YesNo
DeepSeek-V4-Flash
fireworks-ai
fastest
---0.51123YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5760.619YesYes
gemma-4-31B-it
$0.14$0.40262,1440.7674YesNo
gemma-4-31B-it
together
fastest
$0.39$0.97262,1440.2397YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.6723YesYes
gemma-4-26B-A4B-it
novita
fastest
$0.13$0.40262,1440.9349YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.3929YesYes
MiMo-V2.5-Pro
---0.3258NoNo
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.26112YesYes
Qwen3.5-9B
ovhcloud
cheapest
$0.12$0.18262,1440.5441YesNo
Qwen3.5-9B
---0.3479YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
---1.16110YesYes
GLM-5.1
$1.40$4.40202,7520.6372YesYes
GLM-5.1
--202,7520.9850YesNo
GLM-5.1
---3.3934YesNo
GLM-5.1
deepinfra
cheapest fastest
$1.05$3.50202,7520.9474YesYes
Llama-3.1-8B-Instruct
novita
cheapest fastest
$0.02$0.0516,3840.79160NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.55150NoYes
Llama-3.1-8B-Instruct
---0.43137YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
together
cheapest
$0.60$3.60512,2880.70125YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
fireworks-ai
fastest
---0.38163YesNo
Qwen3-Coder-Next
$0.20$1.50262,1441.23117YesNo
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1440.6466YesYes
Kimi-K2.6
together
fastest
$1.20$4.50262,1440.41105YesNo
Kimi-K2.6
--262,1440.4573YesNo
Kimi-K2.6
$0.75$3.50262,1440.8226YesNo
gpt-oss-120b
$0.15$0.75131,0720.36420YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.58223YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.211,021YesNo
gpt-oss-120b
-------
gpt-oss-120b
$0.10$0.40131,0720.54112YesYes
gpt-oss-120b
$0.15$0.60131,0720.33111YesYes
gpt-oss-120b
$0.15$0.60131,0720.41170YesNo
gpt-oss-120b
---0.36179YesYes
gpt-oss-120b
$0.09$0.47131,0720.3292YesYes
gpt-oss-120b
---0.5641YesYes
Meta-Llama-3-8B-Instruct
-------
Meta-Llama-3-8B-Instruct
$0.14$0.148,1920.50112NoYes
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.52267YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.5445YesNo
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.8649NoNo
Llama-3.3-70B-Instruct
$1.04$1.04131,0720.4094YesYes
Llama-3.3-70B-Instruct
---0.3488YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.4435YesYes
Qwen3-8B
$0.07$0.1840,9600.57133YesNo
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1440.6785YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.3649YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.29129YesNo
GLM-5
novita
cheapest
$1.00$3.20202,8002.5918NoNo
GLM-5
-------
GLM-5
zai-org
fastest
---3.5042YesNo
GLM-5
---1.3524YesNo
GLM-4.7-Flash
novita
cheapest fastest
$0.07$0.40200,0001.7668YesNo
GLM-4.7-Flash
-------
GLM-4.7-Flash
---0.6919YesNo
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.41147YesYes
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.5237YesYes
DeepSeek-R1
$0.70$2.5064,0002.7326YesNo
DeepSeek-R1
-------
DeepSeek-R1
-------
Apertus-8B-Instruct-2509
$0.10$0.20-0.77123NoYes
Step-3.7-Flash
---0.50102YesNo
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.42718YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.54124NoYes
gpt-oss-20b
$0.05$0.20131,0720.59166YesYes
gpt-oss-20b
$0.05$0.20131,0720.22108YesYes
gpt-oss-20b
$0.05$0.20131,0720.6055YesNo
gpt-oss-20b
$0.05$0.18131,0720.4533YesYes
gpt-oss-20b
---1.44133YesYes
Qwen3-VL-8B-Instruct
$0.08$0.50131,0720.5568YesYes
Qwen3-14B
$0.07$0.2040,9600.5994YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.46152NoYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.7076NoNo
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8001.2538YesNo
MiniMax-M2.7
$0.30$1.20196,6080.60121YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.90187YesNo
MiniMax-M2.7
---0.7329YesNo
Qwen3.5-27B
novita
cheapest fastest
$0.30$2.40262,1441.0150YesNo
Qwen3.5-27B
---0.2841YesYes
gemma-3-4b-it
---0.2950YesYes
gemma-3-12b-it
---0.3045YesYes
DeepSeek-OCR
$0.03$0.038,1920.88147NoNo
Kimi-K2.5
novita
cheapest
$0.60$3.00262,1440.8537YesYes
Kimi-K2.5
fireworks-ai
fastest
--262,1440.4062YesNo
Kimi-K2.5
---0.5726YesYes
GLM-5.1-FP8
fireworks-ai
fastest
--202,7521.0254YesNo
GLM-5.1-FP8
---4.4323NoNo
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.54152YesYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0721.16286YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.5351NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.5174YesYes
Llama-4-Scout-17B-16E-Instruct
---0.3361YesYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1441.1990YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.86162YesYes
Qwen3.5-397B-A17B
---0.5883YesYes
Qwen3.5-397B-A17B
$0.71$4.25262,1440.41110YesYes
Qwen3.5-397B-A17B
$0.49$3.60262,1440.4067YesYes
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.5649NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.42147YesYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.58167NoNo
Step-3.5-Flash
$0.10$0.30262,1440.2356YesNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.57278YesNo
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.6146YesNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.1612NoNo
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0720.77105YesYes
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.4427YesYes
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.5528YesNo
Ling-2.6-1T
$0.30$2.50262,1441.2585YesNo
aya-expanse-32b
---0.2744NoNo
GLM-4.6V-Flash
novita
cheapest fastest
$0.30$0.90131,0720.6971YesNo
GLM-4.6V-Flash
---3.0558NoNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.5123NoYes
Llama-3.1-70B-Instruct
---0.6681YesYes
GLM-4.6V
---2.1073YesNo
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.8691NoNo
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8001.5156YesNo
GLM-4.6
---3.7520YesNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5360.8732YesNo
GLM-4.5V
zai-org
fastest
---2.9233YesNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.1246YesYes
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.6013YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.3841YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
---0.38102YesYes
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0721.0672YesNo
GLM-4.5-Air
---1.8471YesNo
Qwen3-235B-A22B
novita
fastest
$0.20$0.8040,9600.4125NoNo
Qwen3-235B-A22B
nscale
cheapest
$0.20$0.6032,0000.8216YesYes
gemma-3-27b-it
scaleway
fastest
---0.4648YesYes
gemma-3-27b-it
---0.4824YesYes
rnj-1-instruct
$0.15$0.1532,7680.19122YesYes
gemma-3n-E4B-it
$0.06$0.1232,7680.2052NoYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.56159NoYes
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1441.3151YesYes
Qwen3-Coder-480B-A35B-Instruct
-------
DeepSeek-R1-0528
$0.70$2.50163,8401.9724YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
DeepSeek-V3-0324
$0.27$1.12163,8401.4030YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.65141NoNo
WizardLM-2-8x22B
$0.62$0.6265,5350.6828NoNo
gpt-oss-safeguard-20b
--131,0720.66600YesNo
Qwen3.5-35B-A3B
novita
cheapest fastest
$0.25$2.00262,1440.80117YesNo
Qwen3.5-35B-A3B
---0.30116YesYes
DeepSeek-V3.2
novita
cheapest fastest
$0.27$0.40163,8401.8943YesYes
DeepSeek-V3.2
---0.6915YesYes
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8000.9978YesNo
MiniMax-M2.5
deepinfra
fastest
---0.69140YesNo
tiny-aya-global
---0.44129NoNo
command-a-translate-08-2025
---0.4469YesNo
aya-vision-32b
---0.2042NoNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0721.1683YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.8374NoNo
Qwen3-VL-30B-A3B-Thinking
$0.20$1.00131,0721.03116YesNo
Kimi-K2-Thinking
$0.60$2.50262,1441.0856NoNo
MiniMax-M2
$0.30$1.20204,8001.0867YesNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0721.1653YesNo
GLM-4.5
---2.2749NoNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8001.5158YesNo
GLM-4.7
cerebras
fastest
---0.22370YesNo
GLM-4.7
---2.2121YesNo
GLM-4.7
---0.7628YesNo
Gemma-4-31B-it-pearl
$0.28$0.86262,1440.2427YesNo
MiniMax-M2.1
$0.30$1.20204,8001.1188YesNo
tiny-aya-fire
---1.04117NoNo
tiny-aya-earth
---0.24133NoNo
tiny-aya-water
---0.31131NoNo
command-a-reasoning-08-2025
---0.3567YesNo
command-a-vision-07-2025
---0.2046NoNo
c4ai-command-r7b-arabic-02-2025
---0.2383YesNo
GLM-4.6-FP8
---3.4615YesNo
GLM-4.5V-FP8
---3.1132YesNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.53196NoYes
c4ai-command-r-08-2024
---0.2732YesNo
GLM-4.6V-FP8
---1.8075YesNo
GLM-4.7-FP8
---1.63102YesNo
c4ai-command-r7b-12-2024
---0.3787YesNo
c4ai-command-a-03-2025
---0.2464YesNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.5153NoYes
GLM-4-32B-0414
$0.55$1.6632,0000.8840NoNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.0153NoYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.3244NoYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.0367YesYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.7355YesNo
DeepSeek-V3.1
$0.27$1.00131,0721.6531YesYes
Kimi-K2-Instruct
$0.57$2.30131,0721.5921YesNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.3043NoNo
MiniMax-M1-80k
$0.55$2.201,000,0001.1477YesNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.9888YesNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.7926NoNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.5527YesYes
cogito-671b-v2.1
$1.25$1.25163,8400.3368NoNo
cogito-671b-v2.1
-------
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.4743NoYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.5632NoYes
DeepSeek-V3
$0.40$1.3064,0001.2237YesNo
DeepSeek-R1-Distill-Llama-70B
novita
cheapest
$0.80$0.808,1920.5529NoNo
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.4087YesYes
L3-8B-Lunaris-v1
$0.05$0.058,1920.4381NoNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.8337YesYes
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.3542YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.4028YesYes
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2868NoNo