Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.60$3.381,048,5760.6235YesNo
DeepSeek-V4-Pro
$2.10$4.40512,0000.9142YesYes
DeepSeek-V4-Pro
fireworks-ai
fastest
--1,048,5760.8074YesNo
DeepSeek-V4-Pro
$1.74$3.4865,5360.5331YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
$0.60$3.60512,2880.43110YesNo
DeepSeek-V4-Flash
novita
cheapest
$0.14$0.281,048,5760.80101YesNo
DeepSeek-V4-Flash
fireworks-ai
fastest
---0.71119YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5760.7729YesYes
gemma-4-31B-it
$0.14$0.40262,1440.9576YesYes
gemma-4-31B-it
together
fastest
$0.39$0.97262,1440.2380YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.3433YesYes
Qwen3.6-27B
---0.5271YesNo
Qwen3.6-35B-A3B
$0.15$0.95262,1440.24141YesYes
gemma-4-26B-A4B-it
$0.13$0.40262,1441.2835YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest fastest
$0.07$0.34262,1440.3444YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.7481NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.59143NoYes
Llama-3.1-8B-Instruct
scaleway
fastest
---0.39149YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.7419YesNo
Kimi-K2.6
$1.20$4.50262,1440.3356YesYes
Kimi-K2.6
fireworks-ai
fastest
--262,1440.3585YesNo
Kimi-K2.6
$0.75$3.50262,1440.7671YesNo
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8001.9334YesNo
MiniMax-M2.7
$0.30$1.20196,6080.4622YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.82180YesNo
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.21121YesYes
Qwen3.5-9B
ovhcloud
cheapest
$0.12$0.18262,1440.6740YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.20759YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.74121NoYes
gpt-oss-20b
$0.05$0.20131,0720.60144YesYes
gpt-oss-20b
$0.05$0.20131,0720.24123NoNo
gpt-oss-20b
$0.05$0.20131,0721.50137YesNo
gpt-oss-20b
$0.05$0.18131,0720.3589YesYes
Qwen3-Coder-Next
$0.20$1.50262,1441.04121YesNo
GLM-5.1
$1.40$4.40202,7520.3756YesNo
GLM-5.1
fireworks-ai
fastest
--202,7520.9272YesNo
GLM-5.1
---3.7131YesNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7520.6940YesYes
DeepSeek-R1
$0.70$2.5064,0001.7923YesYes
DeepSeek-R1
-------
DeepSeek-R1
-------
gpt-oss-120b
$0.15$0.75131,0720.20444YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.36142YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.20984YesNo
gpt-oss-120b
-------
gpt-oss-120b
$0.10$0.40131,0720.64109YesYes
gpt-oss-120b
$0.15$0.60131,0720.39182YesYes
gpt-oss-120b
$0.15$0.60131,0720.34170YesNo
gpt-oss-120b
---0.36138YesYes
gpt-oss-120b
$0.09$0.47131,0720.29125YesYes
Qwen3-VL-8B-Instruct
$0.08$0.50131,0720.8460YesNo
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.32102YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.5447YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.19137YesNo
Qwen3-8B
$0.07$0.1840,9600.63133YesNo
Meta-Llama-3-8B-Instruct
-------
Meta-Llama-3-8B-Instruct
$0.14$0.148,1920.69139NoYes
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.5848NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.3592YesNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.19297YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4440YesNo
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.5837NoNo
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.9142NoNo
Llama-3.3-70B-Instruct
$1.04$1.04131,0720.3977YesYes
Llama-3.3-70B-Instruct
---0.3386YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.3436YesNo
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1440.72103YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.3487YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.55143NoYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.26387YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.2863NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.5873YesYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1441.3352YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.52190YesYes
Qwen3.5-397B-A17B
---0.8783YesNo
Qwen3.5-397B-A17B
$0.71$4.25262,1440.35123YesYes
Qwen3.5-397B-A17B
$0.49$3.60262,1440.2691YesYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.53151YesYes
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8000.9173YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.9994YesNo
Kimi-K2.5
novita
cheapest
$0.60$3.00262,1440.9134YesYes
Kimi-K2.5
fireworks-ai
fastest
--262,1440.6439YesNo
GLM-4.7-Flash
novita
cheapest
$0.07$0.40200,0001.2954NoNo
GLM-4.7-Flash
zai-org
fastest
---2.3757NoNo
DeepSeek-OCR
$0.03$0.038,1920.99138NoNo
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.55327NoNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0002.3626YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.78103YesNo
DeepSeek-V3-0324
$0.27$1.12163,8400.9334YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
tiny-aya-global
---1.06111NoNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0720.6972YesNo
GLM-4.6V-Flash
zai-org
fastest
---1.5272YesNo
Qwen3-14B
$0.07$0.2040,9600.6494YesNo
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8001.8850YesNo
GLM-4.6
---3.7520YesNo
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0720.8955YesNo
GLM-4.5-Air
zai-org
fastest
---1.9669YesNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.52173NoYes
Step-3.5-Flash
$0.10$0.30262,1440.2646YesNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.4824NoNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6377NoNo
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.55167NoYes
c4ai-command-a-03-2025
---0.2656YesNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8001.4247YesNo
GLM-4.7
cerebras
fastest
---0.21400YesNo
GLM-4.7
---2.2121YesNo
Qwen3.5-27B
$0.30$2.40262,1441.7757YesNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.63154YesYes
Llama-Guard-4-12B
$0.20$0.201,048,5760.1414NoNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0721.0529YesYes
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0721.3151YesYes
gpt-oss-safeguard-20b
--131,0720.46680YesNo
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1441.1652YesYes
Qwen3-Coder-480B-A35B-Instruct
-------
DeepSeek-V3.2
$0.27$0.40163,8401.6737YesYes
gemma-3-27b-it
---0.4348YesYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.4049NoYes
Gemma-4-31B-it-pearl
$0.28$0.86262,1440.2943YesNo
GLM-5.1-FP8
fireworks-ai
fastest
--202,7521.2063YesNo
GLM-5.1-FP8
---3.6031NoNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.55267YesNo
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.6245YesYes
Qwen3-32B
$0.09$0.2532,7680.3841YesYes
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.0848YesYes
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.6514YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1441.6027YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
---0.37100YesYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.68123NoYes
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2655NoNo
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
GLM-5
novita
cheapest
$1.00$3.20202,8002.0339YesNo
GLM-5
together
fastest
$1.00$3.20202,7520.5985YesYes
GLM-5
---3.6139YesNo
command-a-vision-07-2025
---0.1745NoNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.9255YesNo
Arch-Router-1.5B
---0.1068NoYes
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.3625NoYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.78111YesNo
tiny-aya-earth
---0.26121NoNo
tiny-aya-water
---0.33122NoNo
MiniMax-M1-80k
$0.55$2.201,000,0001.2060YesNo
DeepSeek-R1-0528
$0.70$2.50163,8402.4923YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.5226NoNo
QwQ-32B
$0.18$0.20131,0720.6248YesYes
c4ai-command-r7b-12-2024
---0.67100YesNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.6335NoYes
DeepSeek-V3
$0.40$1.3064,0001.3034YesNo
gemma-3n-E4B-it
$0.06$0.1232,7680.3045NoYes
rnj-1-instruct
$0.15$0.1532,7680.18121YesYes
cogito-671b-v2.1
$1.25$1.25163,8400.2555NoNo
cogito-671b-v2.1
-------
Llama-3.1-70B-Instruct
---0.3786YesYes
tiny-aya-fire
---0.22122NoNo
command-a-translate-08-2025
---0.4968YesNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.9357YesNo
GLM-4.5
---2.1542YesNo
command-a-reasoning-08-2025
---0.2980YesNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5361.5217YesNo
GLM-4.5V
zai-org
fastest
---3.5523NoNo
GLM-4.6-FP8
---3.4615YesNo
GLM-4.5V-FP8
---2.6816YesNo
GLM-4.6V
---1.8368YesNo
c4ai-command-r7b-arabic-02-2025
---0.2699YesNo
GLM-4.6V-FP8
---1.8569YesNo
aya-vision-32b
---0.5236NoNo
GLM-4.7-FP8
---1.63102YesNo
aya-expanse-32b
---0.2541NoNo
c4ai-command-r-08-2024
---0.2759YesNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.2536YesNo
Qwen3-235B-A22B
novita
fastest
$0.20$0.8040,9600.4232NoNo
Qwen3-235B-A22B
nscale
cheapest
$0.20$0.6032,0000.7516YesYes
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.6050NoYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.5194NoYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.59131NoNo
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.4148NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.6738NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.2688YesYes
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.4853NoYes
Ling-2.6-1T
$0.30$2.50262,1441.0186YesNo
MiniMax-M2.1
$0.30$1.20204,8001.1372YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.63102NoNo
Kimi-K2-Thinking
$0.60$2.50262,1441.0039NoNo
MiniMax-M2
$0.30$1.20204,8000.9274YesNo
Qwen3-VL-30B-A3B-Thinking
$0.20$1.00131,0721.0572YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.4441YesYes
Apertus-70B-Instruct-2509
$0.82$2.92-0.8160NoYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.2648NoYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.9142YesYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.2466YesYes
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.8322YesYes
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.89164YesNo
DeepSeek-V3.1
$0.27$1.00131,0721.4523YesYes
Kimi-K2-Instruct
$0.57$2.30131,0721.5427YesNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.2734NoNo
GLM-4-32B-0414
$0.55$1.6632,0001.1837NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.3179NoNo
WizardLM-2-8x22B
$0.62$0.6265,5350.9417NoNo