Inference Providers

·

Metrics for top trending models

DeepSeek-V4.1-Flash
$0.30$1.201,048,5760.79123YesNo
Qwen3.8-27B
$0.42$3.001,000,0000.7330YesNo
Qwen3.8-27B
cerebras
cheapest fastest
$0.00$0.0065,5360.17576YesYes
Qwen3.8-27B
$0.00$0.00262,1440.4644YesYes
Qwen3.8-27B
$0.40$3.00262,1440.3735YesYes
DeepSeek-V4-Flash-Vision-Exp
novita
cheapest fastest
$0.44$1.321,048,5760.49122YesNo
DeepSeek-V4-Flash-Vision-Exp
--1,048,5760.5999YesYes
DeepSeek-V4-Flash-Vision-Exp
$0.44$1.321,048,5761.8545YesYes
GLM-5.3-Flash
novita
cheapest
$0.15$0.501,048,5761.3970YesNo
GLM-5.3-Flash
$0.15$0.501,048,5750.1659YesNo
GLM-5.3-Flash
--1,048,5760.4785YesYes
GLM-5.3-Flash
---1.9463YesNo
GLM-5.3-Flash
baseten
fastest
$0.15$0.501,048,5760.5791YesYes
GLM-5.3-Flash
$0.15$0.501,048,5761.1815YesYes
GLM-5.3
$1.40$4.401,048,5761.0251YesYes
GLM-5.3
together
fastest
$1.40$4.401,048,5750.85129YesNo
GLM-5.3
--1,048,5761.7358YesYes
GLM-5.3
---3.1833YesNo
GLM-5.3
$1.40$4.401,048,5760.7378YesYes
GLM-5.3
deepinfra
cheapest
$1.20$4.001,048,5760.6232YesYes
Ling-3.0-flash-Fin
novita
cheapest fastest
$0.00$0.00262,1440.65291YesNo
Ling-3.0-flash-Fin
$0.06$0.18262,1440.45142YesYes
Kimi-K3
$3.00$15.001,048,5761.0152YesNo
Kimi-K3
$3.00$15.001,048,5761.9050YesYes
Kimi-K3
baseten
fastest
$3.00$15.001,048,5760.7852YesYes
Kimi-K3
deepinfra
cheapest
$2.85$14.251,048,5760.8348YesYes
Ling-3.0-flash-VL
$0.00$0.00262,1440.79139YesNo
Llama-3.1-8B-Instruct
novita
cheapest fastest
$0.02$0.0516,3840.51152NoNo
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.67146NoNo
Llama-3.1-8B-Instruct
$0.02$0.05131,0720.5932YesNo
Ternary-Bonsai-27B-gguf
$0.00$0.00262,1440.3180YesNo
DeepSeek-V4-Flash-0731
novita
fastest
$0.44$1.321,048,5760.60126YesNo
DeepSeek-V4-Flash-0731
$0.14$0.281,048,5760.7222YesNo
DeepSeek-V4-Flash-0731
--1,048,5760.7088YesYes
DeepSeek-V4-Flash-0731
---1.4140YesNo
DeepSeek-V4-Flash-0731
$0.13$0.261,048,5760.6678YesYes
DeepSeek-V4-Flash-0731
deepinfra
cheapest
$0.06$0.181,048,5760.6220YesYes
Muse-Glimmer-30B
together
fastest
$0.35$1.50131,0720.22102YesYes
Muse-Glimmer-30B
--131,0720.1154YesNo
Muse-Glimmer-30B
deepinfra
cheapest
$0.30$1.20131,0720.5691YesYes
gemma-4-31B-it
novita
fastest
$0.14$0.40262,1440.9132YesYes
gemma-4-31B-it
$0.39$0.97262,1443.425YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.718YesYes
gpt-oss-120b
$0.15$0.75131,0720.15441YesYes
gpt-oss-120b
$0.05$0.25131,0720.5482YesYes
gpt-oss-120b
cerebras
fastest
$0.35$0.75131,0720.36990YesYes
gpt-oss-120b
$0.10$0.40131,0720.62106YesYes
gpt-oss-120b
$0.15$0.60131,0720.25160YesYes
gpt-oss-120b
$0.15$0.60131,0720.35166YesYes
gpt-oss-120b
$0.17$0.68-0.4567YesYes
gpt-oss-120b
$0.10$0.50128,0720.27229YesYes
gpt-oss-120b
$0.09$0.47131,0720.5768YesYes
gpt-oss-120b
deepinfra
cheapest
$0.04$0.17131,0720.5630YesYes
Qwen3.6-35B-A3B
scaleway
fastest
$0.29$1.71-0.5284YesYes
Qwen3.6-35B-A3B
deepinfra
cheapest
$0.10$0.95262,1440.7023YesYes
DeepSeek-V4-Flash
novita
fastest
$0.14$0.281,048,5761.3589YesNo
DeepSeek-V4-Flash
deepinfra
cheapest
$0.09$0.181,048,5760.9819YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.36574YesYes
gpt-oss-20b
$0.04$0.15131,0720.48132NoYes
gpt-oss-20b
$0.05$0.20131,0720.69135YesYes
gpt-oss-20b
$0.05$0.20131,0720.32112YesYes
gpt-oss-20b
$0.05$0.18131,0720.3573YesYes
gpt-oss-20b
deepinfra
cheapest
$0.03$0.14131,0720.25117YesYes
DeepSeek-V4-Pro
$1.60$3.201,048,5760.4648YesNo
DeepSeek-V4-Pro
-------
DeepSeek-V4-Pro
baseten
fastest
$1.74$3.481,048,5760.5699YesNo
DeepSeek-V4-Pro
deepinfra
cheapest
$1.30$2.601,048,5760.7239YesYes
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.3391YesYes
Qwen3.5-9B
$0.12$0.18262,1440.4038YesYes
Qwen3.5-9B
deepinfra
cheapest
$0.10$0.15262,1441.8212YesYes
Ling-3.0-flash
novita
cheapest fastest
$0.06$0.18262,1440.73276YesNo
Ling-3.0-flash
$0.06$0.18131,0720.4465YesYes
Qwen3-8B
$0.07$0.1840,9600.65133YesNo
granite-4.2-3b
$0.03$0.12131,0720.18233YesNo
Qwen3.8-2.4T-A95B
$2.00$6.001,000,0001.4425YesYes
Qwen3.8-2.4T-A95B
together
fastest
$2.00$6.001,010,0000.30151YesNo
Qwen3.8-2.4T-A95B
--262,1441.0757YesYes
Qwen3.8-2.4T-A95B
deepinfra
cheapest
$2.00$6.00262,1440.6048YesYes
granite-4.2-8b
$0.06$0.25131,0720.2196YesNo
DeepSeek-V4-Pro-0813
$1.32$3.961,048,5761.4349YesNo
DeepSeek-V4-Pro-0813
together
fastest
$1.32$3.961,048,5760.2684YesNo
DeepSeek-V4-Pro-0813
--1,048,5760.7656YesYes
DeepSeek-V4-Pro-0813
$1.32$3.961,048,5760.5353YesYes
DeepSeek-V4-Pro-0813
deepinfra
cheapest
$1.30$2.601,048,5760.3551YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.21145YesNo
MiniMax-M3
$0.30$1.201,000,0001.3476YesNo
MiniMax-M3
$0.30$1.20524,2880.4237YesNo
MiniMax-M3
fireworks-ai
fastest
$0.30$1.20512,0000.7080YesYes
MiniMax-M3
deepinfra
cheapest
$0.28$1.10524,2880.7513YesYes
gemma-4-26B-A4B-it
$0.13$0.40262,1440.8110YesYes
gemma-4-26B-A4B-it
scaleway
fastest
$0.29$0.57-0.5677YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.697YesYes
Qwen3-Coder-30B-A3B-Instruct
$0.23$0.91-0.32116YesYes
granite-4.2-30b
$0.16$0.65131,0720.1885YesNo
Inkling
together
cheapest
$1.00$4.05524,2880.1194YesYes
Inkling
--1,048,5760.4790YesYes
Inkling
baseten
fastest
$1.00$4.051,048,5760.24105YesYes
Inkling
$0.95$4.05524,2880.52103YesNo
DeepSeek-R1
$0.70$2.5064,0001.3013YesYes
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.4012,2880.5446YesNo
Llama-3.3-70B-Instruct
together
fastest
$1.04$1.04131,0720.54103YesYes
Llama-3.3-70B-Instruct
$1.03$1.03-0.3656YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.3934YesYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.66114YesYes
Inkling-Small
together
cheapest fastest
$0.50$1.20524,2880.17173YesNo
Inkling-Small
$0.50$1.201,048,5760.80144YesYes
Inkling-Small
$0.45$1.20524,2880.37137YesYes
Bielik-11B-v3.0-Instruct
$0.40$0.40-1.0855YesYes
Kimi-K2.7-Code
$0.95$4.00262,1441.3843YesYes
Kimi-K2.7-Code
-------
Kimi-K2.7-Code
fireworks-ai
fastest
$0.95$4.00262,1440.3275YesYes
Kimi-K2.7-Code
$0.95$4.00262,0000.4838YesYes
Kimi-K2.7-Code
deepinfra
cheapest
$0.68$3.40262,1440.9532YesNo
GLM-5.3-Flash-BF16
---1.7371YesNo
Step-3.7-Flash
$0.20$1.15262,1440.22125YesNo
Qwen2.5-Coder-32B-Instruct
$0.06$0.20131,0720.5936NoYes
Qwen3-Coder-Next
$0.20$1.50262,1441.69113YesNo
GLM-5.2
$1.40$4.401,048,5761.6047YesNo
GLM-5.2
together
fastest
$1.40$4.401,048,5750.18160YesNo
GLM-5.2
$1.40$4.401,048,5761.6264YesYes
GLM-5.2
---2.8951YesNo
GLM-5.2
$2.05$6.27-0.8634YesYes
GLM-5.2
$1.40$4.401,048,5761.8780YesYes
GLM-5.2
deepinfra
cheapest
$0.75$2.401,048,5761.2723YesYes
Qwen3-14B
nscale
cheapest fastest
$0.07$0.2040,9600.5968YesNo
Qwen3-14B
$0.12$0.2440,9600.2263YesNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.62148NoYes
gemma-3-4b-it
$0.05$0.10131,0720.3157YesYes
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
--262,1440.46316YesYes
Qwen3-VL-30B-A3B-Instruct
novita
fastest
$0.20$0.70131,0720.7792YesYes
Qwen3-VL-30B-A3B-Instruct
deepinfra
cheapest
$0.15$0.60262,1440.3223YesYes
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.84150YesYes
Qwen3.5-122B-A10B
$0.40$3.20262,1440.6993YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest fastest
$0.29$2.40262,1440.23111YesNo
Qwen3-32B
-------
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest fastest
$0.08$0.2540,9600.7443YesYes
Qwen3-32B
$0.08$0.2840,9600.2530YesNo
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.68164NoNo
MiMo-V2.5
novita
cheapest fastest
$0.17$0.341,048,5761.3337YesNo
MiMo-V2.5
$0.40$2.00262,1440.9812YesYes
gemma-3-12b-it
$0.05$0.15131,0720.8451YesYes
Qwen3-30B-A3B
-------
Qwen3-30B-A3B
$0.12$0.5040,9600.20120YesYes
Llama-4-Scout-17B-16E-Instruct
-------
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.5911NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest fastest
$0.09$0.29890,0000.7972YesYes
Llama-4-Scout-17B-16E-Instruct
$0.10$0.30327,6800.4624YesYes
GLM-4.7-Flash
novita
cheapest
$0.07$0.40200,0002.5459YesNo
GLM-4.7-Flash
---1.9274YesNo
GLM-4.7-Flash
deepinfra
fastest
$0.06$0.40202,7520.2683YesNo
DeepSeek-V3
-------
DeepSeek-V3
$0.32$0.89163,8401.7319YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
-------
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
$0.60$2.40262,1440.34102YesYes
Qwen3.6-27B
ovhcloud
cheapest
$0.47$3.19262,1440.3740YesYes
Qwen3.6-27B
deepinfra
fastest
$0.32$3.20262,1440.4360YesYes
Apertus-v1.5-70B
$0.82$2.92-1.3727NoYes
Apertus-v1.5-8B
$0.10$0.20-1.19112NoYes
GLM-5.3-BF16
---2.7139YesNo
Kimi-K2.5
novita
fastest
$0.60$3.00262,1441.9138YesYes
Kimi-K2.5
deepinfra
cheapest
$0.45$2.25262,1440.6815YesYes
phi-4
$0.07$0.1416,3840.2868NoYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.2160YesNo
Kimi-K2.6
$0.95$4.00262,1440.4162YesYes
Kimi-K2.6
baseten
fastest
$0.95$4.00262,0000.50124YesYes
Kimi-K2.6
$0.75$3.50262,1440.5416YesYes
MiniMax-M2.7
$0.30$1.20204,8001.0942YesNo
MiniMax-M2.7
deepinfra
cheapest fastest
$0.25$1.00196,6080.79103YesNo
DeepSeek-V3.2
$0.27$0.40163,8401.6223YesYes
DeepSeek-V3.2
deepinfra
cheapest fastest
$0.26$0.38163,8401.1643YesYes
Qwen3.5-35B-A3B
$0.25$2.00262,1440.9967YesNo
Qwen3.5-35B-A3B
deepinfra
cheapest fastest
$0.14$1.00262,1440.37138YesYes
Qwen3.5-397B-A17B
$0.60$3.60262,1441.0572YesNo
Qwen3.5-397B-A17B
$0.68$4.10-0.4787YesYes
Qwen3.5-397B-A17B
ovhcloud
fastest
$0.71$4.25262,1440.41106YesYes
Qwen3.5-397B-A17B
deepinfra
cheapest
$0.45$3.00262,1440.4428YesYes
MiMo-V2.5-Pro
novita
cheapest
$0.52$1.041,048,5762.5728YesNo
MiMo-V2.5-Pro
deepinfra
fastest
$1.00$3.001,048,5760.3729YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
$1.00$5.00262,1441.1031YesYes
DeepSeek-V3.1
novita
fastest
$0.27$1.00131,0721.5423YesYes
DeepSeek-V3.1
deepinfra
cheapest
$0.25$0.95163,8400.6211YesYes
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1921.1014NoNo
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1441.3257YesNo
Qwen3-Next-80B-A3B-Instruct
novita
fastest
$0.15$1.50131,0720.67145YesNo
Qwen3-Next-80B-A3B-Instruct
deepinfra
cheapest
$0.09$1.10262,1440.4947YesYes
Qwen3-235B-A22B
novita
fastest
$0.20$0.8040,9600.8028NoNo
Qwen3-235B-A22B
nscale
cheapest
$0.20$0.6032,0000.6716YesYes
GLM-5.1-FP8
---4.3126YesNo
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.6591NoYes
GLM-4.7-FP8
---2.2951YesNo
GLM-4.7
$0.60$2.20204,8001.9920YesNo
GLM-4.7
-------
GLM-4.7
baseten
fastest
$0.60$2.20200,0000.34149YesYes
GLM-4.7
deepinfra
cheapest
$0.40$1.75202,7521.7723YesNo
Hy3
$0.14$0.58262,1440.3864YesYes
Qwen2.5-72B-Instruct
novita
cheapest
$0.38$0.4032,0000.4626YesNo
Qwen2.5-72B-Instruct
deepinfra
fastest
$0.36$0.4032,7680.7233YesYes
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6695NoNo
DeepSeek-R1-0528
$0.70$2.50163,8401.0317YesNo
DeepSeek-R1-0528
deepinfra
cheapest fastest
$0.50$2.15163,8400.7918YesNo
Step-3.5-Flash
$0.10$0.30262,1440.2179YesNo
Kimi-K2-Instruct
$0.57$2.30131,0720.9338YesNo
Qwen3.5-27B
novita
cheapest
$0.30$2.40262,1441.3754YesNo
Qwen3.5-27B
deepinfra
fastest
$0.26$2.60262,1440.2175YesYes
gemma-3-27b-it
$0.08$0.16131,0721.359YesYes
GLM-4.6
$0.55$2.20204,8002.5123YesNo
GLM-4.6
-------
GLM-4.6
deepinfra
cheapest fastest
$0.50$2.00202,7520.5223YesYes
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.5223YesYes
Hermes-3-Llama-3.1-70B
$0.70$0.70131,0720.1832NoYes
gpt-oss-safeguard-20b
--131,0720.48677YesYes
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
$0.24$0.90163,8400.4026YesYes
GLM-5
$1.00$3.20202,8001.2245YesNo
GLM-5
zai-org
fastest
---3.8857YesNo
GLM-5
deepinfra
cheapest
$0.60$2.08202,7521.1127YesYes
Llama-Guard-4-12B
-------
Llama-Guard-4-12B
$0.18$0.18163,8400.3110NoNo
tiny-aya-earth
---0.20133NoNo
tiny-aya-fire
---0.18126NoNo
GLM-5.1
-------
GLM-5.1
$1.05$3.50202,7520.7673YesYes
Ternary-Bonsai-27B-AWQ-4bit
$0.00$0.00262,1440.5383YesNo
DeepSeek-V3.1-Terminus
novita
fastest
$0.27$1.00131,0721.3424YesYes
DeepSeek-V3.1-Terminus
deepinfra
cheapest
$0.27$0.95163,8400.8520YesYes
Qwen3-235B-A22B-Thinking-2507
novita
fastest
$0.30$3.00131,0720.9660YesNo
Qwen3-235B-A22B-Thinking-2507
deepinfra
cheapest
$0.23$2.30262,1440.2922YesYes
Qwen3-235B-A22B-Instruct-2507
$0.09$0.58131,0720.7248YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.7313YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
$0.86$2.57-0.3091YesYes
Qwen3-235B-A22B-Instruct-2507
deepinfra
cheapest
$0.09$0.55262,1440.4025YesYes
GLM-4.6V
---2.7840YesNo
GLM-5.2-FP8
---3.0848YesNo
c4ai-command-a-03-2025
---0.2248YesYes
c4ai-command-r7b-12-2024
---0.1979YesYes
c4ai-command-r-08-2024
---0.1754YesYes
GLM-4.6V-FP8
---3.5336YesNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0721.4736YesNo
GLM-4.6V-Flash
zai-org
fastest
---1.9173YesNo
tiny-aya-global
---0.17134NoNo
GLM-4.5V-FP8
---2.9532YesNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5361.5434YesNo
GLM-4.5V
zai-org
fastest
---3.0339YesNo
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.5389YesNo
GLM-4.5-Air
---1.8571YesNo
aya-expanse-32b
---0.2647NoNo
aya-vision-32b
---0.1942NoNo
command-a-reasoning-08-2025
---0.15108YesYes
command-a-translate-08-2025
---0.3970YesYes
tiny-aya-water
---0.17133NoNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.49162NoYes
GLM-4-32B-0414
$0.55$1.6632,0002.0732NoNo
MiniMax-M1-80k
$0.55$2.201,000,0001.0754YesNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.7940NoNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1440.6939YesYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.68145NoYes
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.6354NoYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.3679NoYes
Qwen3-VL-235B-A22B-Instruct
novita
fastest
$0.30$1.50131,0720.5644YesYes
Qwen3-VL-235B-A22B-Instruct
deepinfra
cheapest
$0.20$0.88262,1441.2211YesYes
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.0448YesNo
MiniMax-M2
$0.30$1.20204,8001.0364YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.5097NoNo
MiniMax-M2.1
$0.30$1.20204,8001.2058YesNo
MiniMax-M2.5
$0.30$1.20204,8000.8362YesNo
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.4340YesYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.4247NoYes
Apertus-8B-Instruct-2509
$0.10$0.20-2.7898NoYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7681.3428NoYes
WizardLM-2-8x22B
$0.62$0.6265,5350.7121NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.3381NoNo