Inference Providers

·

Metrics for top trending models

Qwen3.5-9B
$0.10$0.15262,1440.3575YesYes
Qwen3.5-35B-A3B
$0.25$2.00262,1441.60126YesNo
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8000.842YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.61151YesNo
Kimi-K2.5
$0.60$3.00262,1442.3710NoYes
Kimi-K2.5
together
cheapest
$0.50$2.80262,1440.3959YesYes
Kimi-K2.5
fireworks-ai
fastest
--262,1440.5287YesNo
Qwen3.5-27B
$0.30$2.40262,1441.3352YesNo
Qwen3-Coder-Next
$0.20$1.50262,1440.74124YesYes
GLM-5
novita
cheapest
$1.00$3.20202,8002.6732NoNo
GLM-5
$1.00$3.20202,7520.4845YesYes
GLM-5
fireworks-ai
fastest
--202,7521.1266YesNo
GLM-5
---4.8932NoNo
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.6450NoYes
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.231,305NoNo
Llama-3.1-8B-Instruct
$0.10$0.2016,3840.53651YesYes
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.7360NoYes
Llama-3.1-8B-Instruct
---0.27114YesYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1440.9147YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1442.3285YesYes
gpt-oss-120b
$0.15$0.75131,0720.12447YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.4159YesYes
gpt-oss-120b
sambanova
fastest
$0.22$0.59131,0720.69524YesYes
gpt-oss-120b
$0.10$0.40131,0720.94107YesYes
gpt-oss-120b
$0.30$0.30131,0720.6199YesNo
gpt-oss-120b
$0.15$0.60131,0720.34148YesYes
gpt-oss-120b
$0.15$0.60131,0720.29140YesNo
gpt-oss-120b
---0.35180YesYes
gpt-oss-120b
$0.09$0.47131,0720.2788YesYes
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.4690NoYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.21131YesYes
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.0331YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8402.5059YesNo
MiMo-V2-Flash
$0.10$0.30262,1441.4383YesNo
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.6351YesYes
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.23119NoYes
GLM-4.7-Flash
novita
cheapest fastest
$0.07$0.40200,0001.0079YesNo
GLM-4.7-Flash
---1.9575YesNo
DeepSeek-R1
$0.70$2.5064,0001.1629YesYes
DeepSeek-R1
sambanova
fastest
---0.62154YesYes
DeepSeek-R1
hyperbolic
cheapest
$2.00$2.00163,8400.6577NoNo
DeepSeek-R1
$3.00$7.00163,8400.4282NoYes
Llama-3.2-1B-Instruct
--131,0000.71186NoNo
Qwen3.5-122B-A10B
$0.40$3.20262,1440.76100YesNo
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9600.7746YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.64120YesNo
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.12806YesNo
gpt-oss-20b
$0.04$0.15131,0720.7576NoYes
gpt-oss-20b
$0.05$0.20131,0720.91156YesYes
gpt-oss-20b
hyperbolic
cheapest
$0.10$0.10131,0720.51121YesNo
gpt-oss-20b
$0.05$0.20131,0720.22157YesNo
gpt-oss-20b
$0.05$0.20131,0720.33125YesNo
gpt-oss-20b
$0.05$0.18131,0720.3492YesYes
Qwen2.5-VL-7B-Instruct
$0.20$0.2032,7680.4798NoNo
gemma-3-27b-it
---0.3948YesYes
DeepSeek-OCR
$0.03$0.038,1920.89219NoNo
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.82140NoNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.19320YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.5828YesNo
Llama-3.3-70B-Instruct
$0.60$1.20131,0720.67256YesYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.9016NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.6784YesNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.5285YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.24136NoNo
Llama-3.3-70B-Instruct
---0.3682YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.4634YesYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.7681YesNo
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.3696YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.5346YesYes
gemma-3n-E4B-it
$0.02$0.0432,7680.2645NoYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.22364YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.4051NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.7833YesYes
Qwen3-Coder-Next-FP8
$0.50$1.20262,1441.09121YesYes
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.24296YesNo
Qwen3-32B
$0.10$0.4540,9600.9343NoNo
Qwen3-32B
$0.40$0.8032,7681.60216YesYes
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.9628YesYes
Qwen3-32B
$0.09$0.2532,7680.3639YesYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.8688YesNo
tiny-aya-global
---0.31118NoNo
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8400.6938YesYes
DeepSeek-V3-0324
sambanova
fastest
$3.00$4.50131,0720.60183YesYes
DeepSeek-V3-0324
$1.25$1.25163,8400.6146YesNo
DeepSeek-V3-0324
$1.25$1.25131,0720.3556YesYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0721.0476YesNo
Qwen3-Next-80B-A3B-Instruct
hyperbolic
cheapest fastest
$0.30$0.30262,1440.51173YesNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50262,1440.51134YesYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.9062NoNo
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8401.4418YesNo
DeepSeek-R1-0528
sambanova
fastest
$5.00$7.00131,0721.08195YesYes
DeepSeek-R1-0528
$3.00$3.00163,8400.5778NoNo
DeepSeek-R1-0528
$3.00$7.00163,8400.4380NoYes
DeepSeek-V3
$0.40$1.3064,0001.1636YesYes
DeepSeek-V3
together
cheapest fastest
$1.25$1.25131,0720.3469YesYes
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0720.9971YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.29137YesNo
Kimi-K2-Thinking
novita
cheapest fastest
$0.60$2.50262,1440.9048YesNo
Kimi-K2-Thinking
-------
Kimi-K2-Thinking
---0.9325YesNo
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30$1.30262,1440.8746YesYes
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.6672YesNo
Qwen3-Coder-480B-A35B-Instruct
together
fastest
$2.00$2.00262,1440.3280YesYes
Qwen2.5-VL-72B-Instruct
hyperbolic
cheapest fastest
$0.60$0.6032,7680.6843NoNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.5234NoYes
Kimi-K2-Instruct
$0.57$2.30131,0721.1428YesNo
Kimi-K2-Instruct
-------
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0720.9719YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7681.2123YesYes
Qwen3-235B-A22B-Instruct-2507
$2.00$2.00262,1441.0140YesNo
Qwen3-235B-A22B-Instruct-2507
together
fastest
$0.20$0.60262,1440.4765YesYes
Qwen3-235B-A22B-Instruct-2507
---0.4349YesYes
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.82131YesNo
Qwen3-Next-80B-A3B-Thinking
hyperbolic
cheapest fastest
$0.30$0.30262,1440.53195YesNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.7261NoYes
Apriel-1.6-15b-Thinker
$0.00$0.00131,0720.18148NoNo
DeepSeek-R1-Distill-Llama-70B
novita
fastest
$0.80$0.808,1920.5860NoNo
DeepSeek-R1-Distill-Llama-70B
-------
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.9617NoYes
DeepSeek-R1-Distill-Llama-70B
---0.5838NoYes
Llama-3.1-70B-Instruct
---0.3881YesYes
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.8777YesNo
GLM-4.5-Air
---2.1776YesNo
Qwen3-14B
$0.07$0.2040,9600.8646YesYes
Apertus-8B-Instruct-2509
$0.10$0.20-1.0868NoYes
gpt-oss-safeguard-20b
--131,0720.12836YesNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.9228NoNo
tiny-aya-water
---0.23122NoNo
GLM-4.6
novita
cheapest
$0.55$2.20204,8001.1734YesNo
GLM-4.6
together
fastest
$0.60$2.20202,7521.1668YesNo
GLM-4.6
---3.1926YesNo
rnj-1-instruct
$0.15$0.1532,7680.31121YesYes
GLM-4.7
novita
cheapest
$0.60$2.20204,8000.8150YesNo
GLM-4.7
fireworks-ai
fastest
--202,7521.1571YesNo
GLM-4.7
---2.2554YesNo
Kimi-K2-Instruct-0905
groq
fastest
--262,1440.11170YesNo
Kimi-K2-Instruct-0905
novita
cheapest
$0.60$2.50262,1440.6052YesYes
Kimi-K2-Instruct-0905
-------
Kimi-K2-Instruct-0905
--262,1440.5243YesNo
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20$0.70131,0720.59123YesYes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
--262,1440.27144YesNo
MiniMax-M2
$0.30$1.20204,8001.2748YesNo
MiniMax-M2.1
novita
cheapest
$0.30$1.20204,8002.0040NoNo
MiniMax-M2.1
fireworks-ai
fastest
--204,8001.75101YesNo
ERNIE-4.5-21B-A3B-PT
$0.07$0.28120,0000.8878NoNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.7957NoYes
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.8525NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.3588YesNo
Llama-3.3-Swallow-70B-Instruct-v0.4
$0.60$1.20131,0723.44124NoYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6549NoNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0001.1118YesNo
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5360.8958YesNo
GLM-4.5V
---2.7344YesNo
command-a-reasoning-08-2025
---0.4032YesNo
GLM-4.7-FP8
together
cheapest fastest
$0.45$2.00202,7520.4072YesNo
GLM-4.7-FP8
---3.9419NoNo
c4ai-command-r7b-arabic-02-2025
---0.2997YesNo
aya-vision-32b
---0.2637NoNo
c4ai-command-r-08-2024
---0.1949YesNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.5957YesNo
GLM-4.5
---2.4544YesNo
GLM-4.6V
---3.8022YesNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0721.2920YesNo
GLM-4.6V-Flash
zai-org
fastest
---1.3677YesNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.6929YesYes
DeepSeek-Prover-V2-671B
$0.70$2.50160,0001.0029NoNo
Qwen3-30B-A3B
$0.09$0.4540,9600.8664YesNo
MiniMax-M1-80k
$0.55$2.201,000,0001.5244YesNo
Qwen3-235B-A22B
$0.20$0.8040,9600.845NoYes
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.1623YesNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.1844NoNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.7534NoNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.0628YesYes
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.9651YesNo
Llama-4-Maverick-17B-128E-Instruct
-------
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0721.30322YesYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.9644YesYes
Olmo-3.1-32B-Think
$0.15$0.50-2.1167NoNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.6920NoYes
QwQ-32B
$0.18$0.20131,0720.8729YesNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.9453YesNo
Mixtral-8x22B-Instruct-v0.1
nscale
cheapest
$1.20$1.2065,5360.8825NoYes
Mixtral-8x22B-Instruct-v0.1
fireworks-ai
fastest
$1.20$1.2065,5360.2369NoNo
ERNIE-4.5-VL-28B-A3B-PT
$0.14$0.5630,0001.0562NoNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.6762NoNo
command-a-vision-07-2025
---0.2542NoNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.7683NoYes
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.7427YesYes
DeepSeek-V3.1
$0.60$1.70131,0721.7529YesYes
DeepSeek-V3.1
fireworks-ai
fastest
--163,8400.4555YesNo
cogito-671b-v2.1
together
cheapest fastest
$1.25$1.25163,8400.1871NoNo
cogito-671b-v2.1
--163,8400.3639YesNo
aya-expanse-32b
---0.2342NoNo
Arch-Router-1.5B
---0.1080NoYes
GLM-4.6-FP8
---3.1322NoNo
GLM-4.5V-FP8
---2.6542YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.4527YesYes
GLM-4.6V-FP8
---4.0422NoNo
c4ai-command-r7b-12-2024
---0.3477YesNo
c4ai-command-a-03-2025
---0.6540YesNo
Apertus-70B-Instruct-2509
$0.82$2.92-1.0245NoYes
WizardLM-2-8x22B
$0.62$0.6265,5351.4411NoNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.5523NoYes
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.63106NoNo
tiny-aya-fire
---0.24115NoNo
tiny-aya-earth
---1.26106NoNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Olmo-3.1-32B-Instruct
$0.20$0.60-1.1826YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.6942YesYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.9846NoYes
L3-8B-Lunaris-v1
$0.05$0.058,1921.6724NoNo
command-a-translate-08-2025
---0.3164YesNo
Llama-4-Maverick-17B-128E-Instruct-FP8
novita
cheapest
$0.27$0.851,048,5760.4644NoNo
Llama-4-Maverick-17B-128E-Instruct-FP8
together
fastest
$0.27$0.851,048,5760.2581YesYes
GLM-4-32B-0414
$0.55$1.6632,0000.8541NoNo
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.5657YesYes
GLM-4.5-Air-FP8
$0.20$1.10131,0720.42140YesYes
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2966NoNo