Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest fastest
$1.74$3.481,048,5761.2046YesNo
DeepSeek-V4-Pro
$2.10$4.40512,0000.6642YesYes
DeepSeek-V4-Pro
--1,048,5760.7038YesYes
DeepSeek-V4-Pro
$1.74$3.4865,5360.3220NoYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.42123YesYes
DeepSeek-V4-Flash
novita
cheapest fastest
$0.14$0.281,048,5760.8365YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5762.2814YesYes
gemma-4-31B-it
novita
fastest
$0.14$0.40262,1440.7228YesYes
gemma-4-31B-it
$0.20$0.50262,1440.588NoYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.4122YesYes
Ling-2.6-1T
$0.00$0.00262,1440.7781YesYes
Kimi-K2.6
novita
fastest
$0.95$4.00262,1441.1294YesNo
Kimi-K2.6
$1.20$4.50262,1440.8741YesYes
Kimi-K2.6
--262,1440.4571YesNo
Kimi-K2.6
deepinfra
cheapest
$0.75$3.50262,1440.8813YesNo
gemma-4-26B-A4B-it
novita
fastest
$0.13$0.40262,1440.7646YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.2845YesYes
GLM-5.1
together
fastest
$1.40$4.40202,7521.6250YesYes
GLM-5.1
--202,7520.8739YesNo
GLM-5.1
---3.6531YesNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7520.7519YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8000.9046YesNo
MiniMax-M2.7
$0.30$1.20196,6080.6124YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6081.09140YesNo
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.4947NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.191,472NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
---0.36149YesYes
Qwen3.5-9B
together
cheapest fastest
$0.10$0.15262,1440.3266YesYes
Qwen3.5-9B
$0.12$0.18262,1440.4240YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.42695YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.7055NoYes
gpt-oss-20b
-------
gpt-oss-20b
$0.05$0.20131,0720.24209YesYes
gpt-oss-20b
$0.05$0.20131,0720.6543YesNo
gpt-oss-20b
$0.05$0.18131,0720.3368YesYes
Qwen3-Coder-Next
$0.20$1.50262,1440.88123YesNo
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.21124YesYes
gpt-oss-120b
$0.15$0.75131,0720.15439YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.5333YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.191,093YesNo
gpt-oss-120b
$0.22$0.59131,0724.75168NoYes
gpt-oss-120b
-------
gpt-oss-120b
$0.15$0.60131,0720.2773YesYes
gpt-oss-120b
$0.15$0.60131,0720.55191YesNo
gpt-oss-120b
---0.38152YesYes
gpt-oss-120b
$0.09$0.47131,0722.0151YesYes
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.4270YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1441.4259NoYes
GLM-4.7-Flash
novita
cheapest fastest
$0.07$0.40200,0000.7681NoNo
GLM-4.7-Flash
---2.9358YesNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.15291YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.6028YesNo
Llama-3.3-70B-Instruct
$0.60$1.20131,0720.94258YesYes
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.2631NoNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.7365YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.34102NoNo
Llama-3.3-70B-Instruct
---0.4183YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.4134YesYes
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.4487NoYes
Qwen3.5-122B-A10B
$0.40$3.20262,1440.6784YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest fastest
$0.29$2.40262,1440.2890YesYes
Qwen3.5-35B-A3B
$0.25$2.00262,1440.69123YesNo
Qwen3-8B
-------
Qwen3-8B
--40,9600.2473YesNo
Qwen3-VL-8B-Instruct
novita
cheapest
$0.08$0.50131,0720.4776YesYes
Qwen3-VL-8B-Instruct
together
fastest
$0.18$0.68262,1440.24137YesYes
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8001.1065YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.39156YesNo
MiMo-V2-Flash
$0.10$0.30262,1441.1191YesNo
Llama-3.2-1B-Instruct
--131,0000.48197NoNo
Kimi-K2.5
$0.60$3.00262,1440.6745YesYes
Kimi-K2.5
together
cheapest fastest
$0.50$2.80262,1440.4454YesYes
Kimi-K2.5
--262,1441.4238YesNo
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8000.7043YesNo
GLM-4.6
---2.4933NoNo
Qwen3.5-27B
$0.30$2.40262,1440.6751YesNo
Qwen2.5-Coder-32B-Instruct
-------
Qwen2.5-Coder-32B-Instruct
---0.4775YesNo
gemma-3-27b-it
---0.4148YesYes
GLM-5.1-FP8
--202,7520.9427YesNo
GLM-5.1-FP8
zai-org
fastest
---3.6033YesNo
GLM-5
novita
cheapest
$1.00$3.20202,8001.3539YesNo
GLM-5
$1.00$3.20202,7520.5040YesYes
GLM-5
fireworks-ai
fastest
--202,7521.2466YesNo
GLM-5
---3.1039NoNo
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.4331YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8401.0545YesNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6988NoNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.7822YesNo
Step-3.5-Flash
$0.10$0.30262,1440.3634YesNo
Qwen3-Coder-Next-FP8
$0.50$1.20262,1440.51139YesYes
Arch-Router-1.5B
---0.1178NoYes
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0720.8350YesNo
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.19542YesNo
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.1944YesYes
Qwen3-235B-A22B-Instruct-2507
---0.3957YesYes
gemma-3n-E4B-it
$0.06$0.1232,7680.3927NoYes
Llama-Guard-4-12B
$0.20$0.201,048,5760.1910NoNo
DeepSeek-V3
$0.40$1.3064,0001.3232YesNo
DeepSeek-V3
together
cheapest fastest
$1.25$1.25131,0720.4649YesYes
Llama-4-Scout-17B-16E-Instruct
groq
cheapest fastest
$0.11$0.34131,0720.80310YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3961NoNo
Llama-4-Scout-17B-16E-Instruct
-------
gpt-oss-safeguard-20b
--131,0720.13769YesNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.4536NoYes
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8401.0135NoYes
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
hyperbolic
fastest
$1.25$1.25163,8400.6359NoNo
DeepSeek-V3-0324
$1.25$1.25131,0720.4846YesYes
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0721.20352YesYes
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.6547NoNo
Apertus-8B-Instruct-2509
$0.10$0.20-0.71114NoYes
Qwen3.5-397B-A17B
$0.60$3.60262,1441.2746YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.72109YesYes
Qwen3.5-397B-A17B
---0.9744YesYes
Qwen3.5-397B-A17B
deepinfra
cheapest
$0.54$3.40262,1440.2692YesNo
DeepSeek-R1
$0.70$2.5064,0001.9025YesYes
DeepSeek-R1
-------
DeepSeek-R1
hyperbolic
cheapest fastest
$2.00$2.00163,8400.6998NoNo
DeepSeek-R1
$3.00$7.00163,8400.6396NoNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.16242YesNo
Qwen3-32B
$0.10$0.4540,9600.4938NoNo
Qwen3-32B
-------
Qwen3-32B
ovhcloud
cheapest
$0.09$0.2532,7680.9426YesYes
Qwen3-30B-A3B
$0.09$0.4540,9600.7667YesNo
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0721.03119YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.27131YesNo
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20$0.70131,0720.69110YesYes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
--262,1440.21129YesNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8000.8658NoNo
GLM-4.7
cerebras
fastest
---0.24406YesNo
GLM-4.7
--202,7521.5775YesNo
GLM-4.7
---2.6841YesNo
rnj-1-instruct
$0.15$0.1532,7680.15124YesYes
tiny-aya-global
---0.21120NoNo
aya-expanse-32b
---0.1840NoNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0720.9545YesNo
GLM-4.6V-Flash
zai-org
fastest
---1.3776NoNo
DeepSeek-OCR
$0.03$0.038,1920.73178NoNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.2832YesYes
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.6836YesYes
c4ai-command-a-03-2025
---0.6454NoNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.1151YesNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.4433NoYes
command-a-translate-08-2025
---0.3468YesNo
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.5999YesNo
GLM-4.5-Air
---2.1372YesNo
tiny-aya-water
---0.21119NoNo
MiniMax-M2
$0.30$1.20204,8000.8665YesNo
tiny-aya-earth
---0.24120NoNo
tiny-aya-fire
---0.19122NoNo
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.6132YesYes
DeepSeek-V3.1
$0.60$1.70131,0720.5066YesYes
DeepSeek-V3.1
fireworks-ai
fastest
--163,8400.3368NoNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.5917NoNo
cogito-671b-v2.1
$1.25$1.25163,8400.4863NoNo
cogito-671b-v2.1
-------
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2563NoNo
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8401.5527NoNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
$3.00$3.00163,8400.6557NoNo
DeepSeek-R1-0528
together
fastest
$3.00$7.00163,8400.4977NoYes
MiniMax-M1-80k
$0.55$2.201,000,0002.1152YesNo
GLM-4.6-FP8
---1.7977YesNo
c4ai-command-r7b-12-2024
---0.2073YesNo
c4ai-command-r-08-2024
---0.2328NoNo
GLM-4.7-FP8
---2.0847YesNo
GLM-4-32B-0414
$0.55$1.6632,0000.8248NoNo
GLM-4.6V-FP8
---2.0850YesNo
MiniMax-M2.1
$0.30$1.20204,8001.1464YesNo
GLM-4.6V
---2.3049YesNo
GLM-4.5V-FP8
---3.0828NoNo
command-a-reasoning-08-2025
---0.2884YesNo
Kimi-K2-Thinking
$0.60$2.50262,1441.0119YesNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5360.5427YesNo
GLM-4.5V
zai-org
fastest
---2.3137YesNo
GLM-4.5
novita
cheapest
$0.60$2.20131,0720.7447YesNo
GLM-4.5
zai-org
fastest
---2.0850YesNo
aya-vision-32b
---0.2537NoNo
c4ai-command-r7b-arabic-02-2025
---0.1879YesNo
command-a-vision-07-2025
---0.1547NoNo
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.8039YesNo
WizardLM-2-8x22B
$0.62$0.6265,5350.9411NoNo
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30$1.30262,1440.9251YesYes
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.5276NoNo
Qwen3-Coder-480B-A35B-Instruct
together
fastest
$2.00$2.00262,1440.2183YesYes
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.4621NoYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.4265YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.4045YesYes
DeepSeek-R1-Distill-Llama-70B
novita
cheapest
$0.80$0.808,1920.8346NoNo
DeepSeek-R1-Distill-Llama-70B
-------
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.2785YesYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.7647NoYes
Apertus-70B-Instruct-2509
$0.82$2.92-0.9954NoYes
Kimi-K2-Instruct
$0.57$2.30131,0721.0228YesNo
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.43112NoNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.2245NoNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.6829NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.5535NoNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.5821NoYes
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.4932YesYes
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.91162YesNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.7989YesNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1440.7737YesNo
Llama-3.1-70B-Instruct
---0.2782YesYes
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.2249YesYes