Inference Providers

·

Metrics for top trending models

Inkling
$1.00$4.05524,2880.25113YesYes
Ternary-Bonsai-27B-gguf
$0.00$0.00262,1440.3494YesNo
GLM-5.2
$1.40$4.401,048,5761.1338YesYes
GLM-5.2
together
fastest
$1.40$4.40262,1440.4581YesYes
GLM-5.2
$1.40$4.401,048,5760.7850YesNo
GLM-5.2
---3.5041NoNo
GLM-5.2
$2.05$6.27-0.6080YesNo
GLM-5.2
deepinfra
cheapest
$0.93$3.001,048,5760.6835YesYes
gemma-4-31B-it
$0.14$0.40262,1440.729YesNo
gemma-4-31B-it
cerebras
fastest
---0.22663YesNo
gemma-4-31B-it
$0.39$0.97262,1440.5479YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.7419YesYes
Kimi-K2.7-Code
$0.95$4.00262,1441.3037YesYes
Kimi-K2.7-Code
$0.95$4.00262,1440.5376YesYes
Kimi-K2.7-Code
fireworks-ai
fastest
$0.95$4.00262,1440.58101YesNo
Kimi-K2.7-Code
deepinfra
cheapest
$0.74$3.50262,1440.9476YesYes
Qwen3.6-35B-A3B
scaleway
fastest
$0.29$1.71-0.31123YesYes
Qwen3.6-35B-A3B
deepinfra
cheapest
$0.15$0.95262,1440.3288YesYes
Qwen3.6-27B
-------
Qwen3.6-27B
$0.32$3.20262,1440.2219YesYes
DeepSeek-V4-Flash
$0.14$0.281,048,5761.1879YesNo
DeepSeek-V4-Flash
fireworks-ai
fastest
$0.14$0.281,048,5760.8090YesNo
DeepSeek-V4-Flash
deepinfra
cheapest
$0.09$0.181,048,5760.9323YesYes
DeepSeek-V4-Pro
$1.60$3.201,048,5760.8745YesNo
DeepSeek-V4-Pro
$1.74$3.48512,0000.6267YesYes
DeepSeek-V4-Pro
fireworks-ai
fastest
$1.74$3.481,048,5760.7768YesNo
DeepSeek-V4-Pro
deepinfra
cheapest
$1.30$2.601,048,5760.3144YesYes
Ornith-1.0-35B
$0.10$0.75262,1440.25108YesYes
Llama-3.1-8B-Instruct
novita
cheapest fastest
$0.02$0.0516,3840.46149NoNo
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.57147NoYes
Llama-3.1-8B-Instruct
$0.02$0.05131,0720.6273YesNo
gemma-4-26B-A4B-it
$0.13$0.40262,1441.4729NoYes
gemma-4-26B-A4B-it
scaleway
fastest
$0.29$0.57-0.42186YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.3223YesYes
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.2343YesNo
Qwen3.5-9B
-------
Qwen3.5-9B
deepinfra
cheapest
$0.10$0.15262,1440.4437YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.25714YesNo
gpt-oss-20b
$0.04$0.15131,0720.3358NoNo
gpt-oss-20b
$0.05$0.20131,0720.54154YesYes
gpt-oss-20b
$0.05$0.20131,0720.33107YesNo
gpt-oss-20b
$0.07$0.30131,0720.31171YesNo
gpt-oss-20b
-------
gpt-oss-20b
deepinfra
cheapest
$0.03$0.14131,0720.30107YesYes
MiniMax-M3
novita
cheapest
$0.30$1.201,000,0001.0382YesNo
MiniMax-M3
$0.30$1.20524,2880.3969YesYes
MiniMax-M3
fireworks-ai
fastest
$0.30$1.20512,0000.68144YesNo
MiniMax-M3
$0.30$1.20524,2880.5046YesNo
gpt-oss-120b
$0.15$0.75131,0720.20448YesNo
gpt-oss-120b
$0.05$0.25131,0720.59155YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.201,167YesNo
gpt-oss-120b
$0.10$0.40131,0720.6296YesYes
gpt-oss-120b
$0.15$0.60131,0720.20183YesYes
gpt-oss-120b
$0.15$0.60131,0720.34146YesNo
gpt-oss-120b
$0.17$0.68-0.32176YesYes
gpt-oss-120b
-------
gpt-oss-120b
deepinfra
cheapest
$0.04$0.17131,0720.2766YesYes
GLM-5.2-FP8
---3.0648NoNo
Ling-2.6-1T
$0.30$2.50262,1441.2191YesNo
Qwen3-Coder-Next
$0.20$1.50262,1441.79115YesNo
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.3943NoNo
Kimi-K2.6
together
fastest
$1.20$4.50262,1440.48184YesYes
Kimi-K2.6
$0.95$4.00262,1440.4555YesNo
Kimi-K2.6
$0.75$3.50262,1441.5345YesNo
DeepSeek-R1
$0.70$2.5064,0001.0720NoYes
Ternary-Bonsai-27B-AWQ-4bit
$0.00$0.00262,1440.3792YesNo
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
$1.00$5.00262,1440.9343YesYes
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.28248YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.406,0000.4427YesNo
Llama-3.3-70B-Instruct
$1.04$1.04131,0720.5083YesYes
Llama-3.3-70B-Instruct
$1.03$1.03-0.4785YesYes
Llama-3.3-70B-Instruct
-------
Qwen3-8B
$0.07$0.1840,9600.57132YesNo
gemma-3-4b-it
$0.05$0.10131,0720.3973YesYes
Qwen3-Coder-30B-A3B-Instruct
$0.23$0.91-0.22151YesYes
Qwen3-14B
nscale
cheapest fastest
$0.07$0.2040,9600.6195YesYes
Qwen3-14B
$0.12$0.2440,9602.1147YesNo
GLM-4.7-Flash
novita
cheapest
$0.07$0.40200,0000.6771NoNo
GLM-4.7-Flash
zai-org
fastest
---1.5898YesNo
GLM-4.7-Flash
$0.06$0.40202,7520.3683YesNo
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
$0.60$3.60512,2880.26124YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
fireworks-ai
cheapest fastest
$0.60$2.40262,1440.44128YesNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.21255YesNo
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.5048YesYes
Qwen3-32B
$0.08$0.2840,9600.22100YesNo
Ornith-1.0-35B-FP8
$0.10$0.75262,1440.46105YesYes
Qwen2.5-Coder-32B-Instruct
$0.06$0.20131,0720.5748NoYes
Kimi-K2-Instruct-0905
$0.60$2.50262,1440.8439YesYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.52369YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.5349NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.5973YesYes
Llama-4-Scout-17B-16E-Instruct
$0.10$0.30327,6800.1977YesYes
gemma-3-27b-it
scaleway
fastest
$0.29$0.57-0.4849YesYes
gemma-3-27b-it
deepinfra
cheapest
$0.08$0.16131,0720.3519YesNo
phi-4
$0.07$0.1416,3840.2543NoYes
Qwen3.5-27B
novita
cheapest fastest
$0.30$2.40262,1441.4042YesNo
Qwen3.5-27B
$0.26$2.60262,1441.388YesYes
MiMo-V2.5-Pro
$1.00$3.001,048,5760.2780YesYes
Step-3.7-Flash
$0.20$1.15262,1440.33137YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1441.1084YesNo
Qwen3.5-35B-A3B
deepinfra
cheapest fastest
$0.14$1.00262,1440.2890YesYes
Llama-Guard-4-12B
together
fastest
$0.20$0.201,048,5760.1612NoNo
Llama-Guard-4-12B
deepinfra
cheapest
$0.18$0.18163,8400.299NoNo
Kimi-K2.5
novita
fastest
$0.60$3.00262,1440.8239YesYes
Kimi-K2.5
deepinfra
cheapest
$0.45$2.25262,1440.7512YesNo
Bielik-11B-v3.0-Instruct
$0.40$0.40-0.7956YesYes
GLM-5
novita
fastest
$1.00$3.20202,8001.1541NoNo
GLM-5
---3.2938YesNo
GLM-5
deepinfra
cheapest
$0.60$2.08202,7520.8915NoNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.61149NoYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.2095YesYes
GLM-5.1
fireworks-ai
fastest
$1.40$4.40202,7520.9962YesNo
GLM-5.1
---4.0337YesNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7520.9947YesYes
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.5343YesYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.94107YesNo
tiny-aya-global
---0.22132NoNo
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1441.0568YesYes
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.6054YesNo
GLM-4.5-Air
---2.9239YesNo
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.5797YesYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.72129YesYes
gemma-3-12b-it
$0.05$0.15131,0720.3049YesYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.49118NoNo
Qwen3.5-397B-A17B
$0.60$3.60262,1441.1654YesNo
Qwen3.5-397B-A17B
scaleway
fastest
$0.68$4.10-0.4796YesYes
Qwen3.5-397B-A17B
-------
Qwen3.5-397B-A17B
deepinfra
cheapest
$0.45$3.00262,1440.3930YesYes
Step-3.5-Flash
$0.10$0.30262,1440.26142YesNo
DeepSeek-V3.1
novita
fastest
$0.27$1.00131,0721.9236YesYes
DeepSeek-V3.1
deepinfra
cheapest
$0.25$0.95163,8400.9111YesYes
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0721.1346YesNo
GLM-4.6V-Flash
zai-org
fastest
---2.0762NoNo
GLM-4.5
---2.4153NoNo
Kimi-K2-Instruct
$0.57$2.30131,0720.9838YesNo
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.5594NoYes
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0720.69100YesYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.62149NoNo
Qwen3-235B-A22B-Instruct-2507
$0.09$0.58131,0720.6251YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.8715YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
$0.86$2.57-0.3797YesYes
Qwen3-235B-A22B-Instruct-2507
deepinfra
cheapest
$0.09$0.55262,1440.3424YesYes
GLM-4.7
$0.60$2.20204,8001.5737YesNo
GLM-4.7
cerebras
fastest
---0.17389YesNo
GLM-4.7
---2.2121YesNo
GLM-4.7
deepinfra
cheapest
$0.40$1.75202,7520.4731YesNo
MiniMax-M2.7
$0.30$1.20204,8001.5550YesNo
MiniMax-M2.7
$0.30$1.20196,6080.3578YesYes
MiniMax-M2.7
fireworks-ai
fastest
$0.30$1.20196,6080.64174YesNo
MiniMax-M2.7
deepinfra
cheapest
$0.25$1.00196,6080.6589YesNo
GLM-5.1-FP8
fireworks-ai
cheapest fastest
$1.40$4.40202,7521.0270YesNo
GLM-5.1-FP8
---3.8538YesNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.5493NoNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.1742NoNo
DeepSeek-R1-0528
$0.70$2.50163,8400.9417NoYes
DeepSeek-R1-0528
deepinfra
cheapest fastest
$0.50$2.15163,8400.6717NoNo
DeepSeek-V3-0324
$0.27$1.12163,8401.0434YesNo
DeepSeek-V3-0324
deepinfra
cheapest fastest
$0.24$0.90163,8400.9051YesYes
MiniMax-M1-80k
$0.55$2.201,000,0001.4045YesNo
gpt-oss-safeguard-20b
--131,0720.22777YesNo
Qwen3.5-122B-A10B
$0.40$3.20262,1440.8865YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest fastest
$0.29$2.40262,1440.59103YesNo
MiniMax-M2.5
$0.30$1.20204,8001.3146YesNo
MiniMax-M2.5
deepinfra
cheapest fastest
$0.15$1.15196,6080.9550YesNo
MiniMax-M2.1
$0.30$1.20204,8001.3148YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.6827YesYes
DeepSeek-OCR
$0.03$0.038,1920.62234NoNo
Gemma-4-31B-it-pearl
$0.28$0.86262,1440.2751YesNo
DeepSeek-V3
novita
fastest
$0.40$1.3064,0001.2133YesNo
DeepSeek-V3
deepinfra
cheapest
$0.32$0.89163,8400.5725YesYes
aya-vision-32b
---0.2142NoNo
Qwen3-235B-A22B-Thinking-2507
novita
fastest
$0.30$3.00131,0720.6769YesNo
Qwen3-235B-A22B-Thinking-2507
deepinfra
cheapest
$0.23$2.30262,1440.3929YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0722.1436YesYes
DeepSeek-V3.1-Terminus
deepinfra
cheapest fastest
$0.27$0.95163,8400.4595NoYes
GLM-4.6
novita
fastest
$0.55$2.20204,8000.9241YesNo
GLM-4.6
---3.4027YesNo
GLM-4.6
deepinfra
cheapest
$0.50$2.00202,7520.4639YesYes
c4ai-command-r7b-arabic-02-2025
---0.28128YesNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.3369NoNo
cogito-671b-v2.1
$1.25$1.25163,8400.6771NoNo
cogito-671b-v2.1
-------
c4ai-command-r7b-12-2024
---0.2279YesNo
aya-expanse-32b
---0.2341NoNo
DeepSeek-V3.2
novita
fastest
$0.27$0.40163,8402.2736YesYes
DeepSeek-V3.2
deepinfra
cheapest
$0.26$0.38163,8400.6016YesYes
c4ai-command-r-08-2024
---0.3024YesNo
command-a-translate-08-2025
---0.2870YesNo
GLM-4.6-FP8
---4.5718YesNo
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5360.8671YesNo
GLM-4.5V
---1.8567YesNo
GLM-4.6V-FP8
---2.2962YesNo
GLM-4.5V-FP8
---1.9264YesNo
tiny-aya-water
---0.19132NoNo
tiny-aya-earth
---0.17134NoNo
c4ai-command-a-03-2025
---0.2443YesNo
command-a-reasoning-08-2025
---0.8096YesNo
tiny-aya-fire
---0.19134NoNo
GLM-4.7-FP8
---1.63102NoNo
command-a-vision-07-2025
---0.1846NoNo
Qwen2.5-72B-Instruct
-------
Qwen2.5-72B-Instruct
$0.36$0.4032,7681.396YesYes
GLM-4.6V
---2.9161YesNo
Qwen3-235B-A22B
$0.20$0.8040,9601.0615NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0000.8316YesYes
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.8149YesNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.6155NoYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.60183NoYes
MiniMax-M2
$0.30$1.20204,8001.3651YesNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.6753NoYes
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.45100NoNo
WizardLM-2-8x22B
$0.62$0.6265,5351.0415NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.3776NoNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.1864YesYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
gemma-3n-E4B-it
$0.06$0.1232,7680.4165NoYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.1948YesYes
Apertus-70B-Instruct-2509
$0.82$2.92-0.8728YesYes
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1921.1019NoNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-2.1744NoNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.5237NoYes
GLM-4-32B-0414
$0.55$1.6632,0000.7746NoNo