Inference Providers

·

Metrics for top trending models

GLM-5.2
---1.6135YesYes
GLM-5.2
together
cheapest fastest
$1.40$4.40262,1440.47119YesYes
GLM-5.2
---0.8643YesNo
GLM-5.2
---4.2132NoNo
GLM-5.2
---0.7456YesYes
MiniMax-M3
---2.1639YesNo
MiniMax-M3
together
cheapest
$0.30$1.20524,2880.6136YesYes
MiniMax-M3
fireworks-ai
fastest
---0.65126YesNo
Kimi-K2.7-Code
---1.1245YesNo
Kimi-K2.7-Code
together
cheapest
$0.95$4.00262,1440.5851YesYes
Kimi-K2.7-Code
fireworks-ai
fastest
---0.60115YesNo
Kimi-K2.7-Code
---0.7228YesNo
DeepSeek-V4-Pro
novita
cheapest fastest
$1.60$3.381,048,5760.6258YesNo
DeepSeek-V4-Pro
$1.74$3.48512,0000.7257YesNo
DeepSeek-V4-Pro
--1,048,5760.6650YesNo
DeepSeek-V4-Pro
$1.74$3.4865,5360.4822YesYes
GLM-5.2-FP8
---4.0036NoNo
Qwen3.6-35B-A3B
$0.15$0.95262,1440.22149YesYes
Qwen3.6-27B
---0.4562YesYes
Qwen3.6-27B
deepinfra
fastest
---0.3068YesYes
DeepSeek-V4-Flash
novita
cheapest
$0.14$0.281,048,5760.9670YesNo
DeepSeek-V4-Flash
fireworks-ai
fastest
---2.06107NoNo
DeepSeek-V4-Flash
$0.14$0.281,048,5764.097YesYes
GLM-5.1
$1.40$4.40202,7522.4735YesYes
GLM-5.1
--202,7520.8649YesNo
GLM-5.1
---3.3836YesNo
GLM-5.1
deepinfra
cheapest fastest
$1.05$3.50202,7520.8168YesYes
gemma-4-31B-it
$0.14$0.40262,1441.7414YesYes
gemma-4-31B-it
$0.39$0.97262,1440.4211NoNo
gemma-4-31B-it
deepinfra
cheapest fastest
$0.13$0.38262,1440.3245YesYes
gemma-4-26B-A4B-it
novita
fastest
$0.13$0.40262,1441.7032NoNo
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1442.0522YesNo
MiMo-V2.5-Pro
---0.3374YesNo
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
together
cheapest
$0.60$3.60512,2880.32137YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
fireworks-ai
fastest
---0.35163YesNo
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
---0.70110NoNo
Llama-3.1-8B-Instruct
novita
cheapest fastest
$0.02$0.0516,3840.69164NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.62148NoYes
Llama-3.1-8B-Instruct
---0.37119YesYes
Qwen3.5-9B
$0.17$0.25262,1440.2687YesYes
Qwen3.5-9B
ovhcloud
cheapest
$0.12$0.18262,1440.4342YesYes
Qwen3.5-9B
deepinfra
fastest
---2.2690YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.1859YesYes
Kimi-K2.6
together
fastest
$1.20$4.50262,1440.46112YesYes
Kimi-K2.6
--262,1440.5842YesNo
Kimi-K2.6
$0.75$3.50262,1441.0414YesNo
gpt-oss-120b
$0.15$0.75131,0720.19443YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.37151YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.20898YesNo
gpt-oss-120b
$0.22$0.59131,0721.32430YesYes
gpt-oss-120b
$0.10$0.40131,0720.58114YesYes
gpt-oss-120b
$0.15$0.60131,0720.2550YesNo
gpt-oss-120b
$0.15$0.60131,0720.44174YesNo
gpt-oss-120b
---0.41178YesYes
gpt-oss-120b
$0.09$0.47131,0720.27132YesYes
gpt-oss-120b
---0.7446YesYes
DeepSeek-R1
$0.70$2.5064,0001.6727YesYes
DeepSeek-R1
-------
DeepSeek-R1
-------
Qwen3-Coder-Next
$0.20$1.50262,1440.99122YesNo
Meta-Llama-3-8B-Instruct
-------
Meta-Llama-3-8B-Instruct
$0.14$0.148,1920.81113NoNo
Qwen3-8B
$0.07$0.1840,9600.61117YesNo
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8001.1242YesNo
MiniMax-M2.7
$0.30$1.20196,6080.40147YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.59199YesNo
MiniMax-M2.7
---0.7120YesNo
Step-3.7-Flash
---0.27119YesNo
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.34145YesYes
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.5939YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.17134YesYes
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.18269YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4245YesNo
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.5431NoNo
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.7896NoNo
Llama-3.3-70B-Instruct
$1.04$1.04131,0720.41120YesYes
Llama-3.3-70B-Instruct
---0.3883YesYes
Llama-3.3-70B-Instruct
-------
GLM-5
novita
cheapest
$1.00$3.20202,8001.3031YesNo
GLM-5
together
fastest
$1.00$3.20202,7520.6998YesYes
GLM-5
---3.3842YesNo
GLM-5
---1.1921YesNo
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.12780YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.6075NoYes
gpt-oss-20b
$0.05$0.20131,0720.55164YesYes
gpt-oss-20b
$0.05$0.20131,0720.26113YesYes
gpt-oss-20b
$0.05$0.20131,0721.0051YesNo
gpt-oss-20b
$0.05$0.18131,0721.4825YesYes
gpt-oss-20b
---0.2470YesYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1440.9481YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.54217YesYes
Qwen3.5-397B-A17B
---0.4560YesYes
Qwen3.5-397B-A17B
$0.71$4.25262,1440.4885YesNo
Qwen3.5-397B-A17B
$0.49$3.60262,1440.4368YesYes
GLM-4.7-Flash
novita
cheapest fastest
$0.07$0.40200,0000.9864YesNo
GLM-4.7-Flash
---2.2464NoNo
GLM-4.7-Flash
---0.4932YesNo
Qwen3-VL-8B-Instruct
$0.08$0.50131,0720.6478YesNo
GLM-5.1-FP8
fireworks-ai
fastest
--202,7521.0764YesNo
GLM-5.1-FP8
---4.0029NoNo
Kimi-K2.5
novita
cheapest
$0.60$3.00262,1440.6945YesYes
Kimi-K2.5
fireworks-ai
fastest
--262,1441.0175YesNo
Kimi-K2.5
---0.6728YesYes
gemma-3-4b-it
---0.3231YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.52149NoYes
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1440.8479YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.4433YesYes
MiniMax-M2.5
novita
cheapest fastest
$0.30$1.20204,8000.8578YesNo
MiniMax-M2.5
---0.6537YesNo
gemma-3-12b-it
---0.3332YesYes
DeepSeek-V3.2
novita
cheapest fastest
$0.27$0.40163,8401.3133YesYes
DeepSeek-V3.2
---0.6715YesYes
Kimi-K2-Thinking
$0.60$2.50262,1441.1346NoNo
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.60166NoNo
Qwen3.5-27B
novita
cheapest fastest
$0.30$2.40262,1440.9470YesNo
Qwen3.5-27B
---0.3525YesYes
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.62315NoNo
Qwen3-14B
$0.07$0.2040,9600.6488YesNo
gemma-3-27b-it
scaleway
fastest
---0.5148YesYes
gemma-3-27b-it
---0.3518YesYes
GLM-4.7
novita
cheapest
$0.60$2.20204,8001.6248YesNo
GLM-4.7
cerebras
fastest
---0.15112YesNo
GLM-4.7
---2.2121YesNo
GLM-4.7
---0.4452YesNo
Qwen3.5-35B-A3B
novita
cheapest fastest
$0.25$2.00262,1440.70119YesNo
Qwen3.5-35B-A3B
---2.1354YesYes
MiniMax-M2.1
$0.30$1.20204,8001.1473YesNo
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.48350YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.6061NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.5573YesYes
Llama-4-Scout-17B-16E-Instruct
---0.2368YesYes
MiniMax-M2
$0.30$1.20204,8001.2780YesNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.6441NoYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.56133YesYes
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.4648NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.30150YesYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.50164NoYes
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0720.8060YesNo
GLM-4.6V-Flash
zai-org
fastest
---3.1173YesNo
QwQ-32B
$0.18$0.20131,0720.7048YesYes
DeepSeek-OCR
$0.03$0.038,1921.04171NoNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.45203YesNo
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.6741YesYes
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.5994NoNo
Qwen3-235B-A22B
novita
fastest
$0.20$0.8040,9600.4040NoNo
Qwen3-235B-A22B
nscale
cheapest
$0.20$0.6032,0000.7716YesYes
DeepSeek-V3
$0.40$1.3064,0000.7737YesNo
DeepSeek-R1-0528
$0.70$2.50163,8401.7526YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.3711YesNo
Kimi-K2-Instruct
$0.57$2.30131,0721.5324YesNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.1612NoNo
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8001.3457YesNo
GLM-4.6
---3.7520YesNo
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Apertus-8B-Instruct-2509
$0.10$0.20-0.75122NoYes
Arch-Router-1.5B
---0.1079NoYes
Ling-2.6-1T
$0.30$2.50262,1441.4479YesNo
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0720.6560YesNo
GLM-4.5-Air
zai-org
fastest
---1.6372YesNo
gemma-3n-E4B-it
$0.06$0.1232,7680.2661NoYes
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.1345YesYes
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.7318YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.2538YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
---0.5961YesYes
Llama-3.1-70B-Instruct
---0.3486YesYes
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.6353NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.6837NoNo
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3484YesYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.5334NoYes
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5362.7020NoNo
GLM-4.5V
---2.9019NoNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.4521YesYes
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1441.1764YesYes
Qwen3-Coder-480B-A35B-Instruct
-------
DeepSeek-V3-0324
$0.27$1.12163,8400.9937YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
L3-8B-Stheno-v3.2
$0.05$0.058,1920.62101NoNo
tiny-aya-global
---0.32130NoNo
command-a-translate-08-2025
---0.5170YesNo
aya-expanse-32b
---0.2043NoNo
c4ai-command-r7b-12-2024
---1.0681YesNo
c4ai-command-a-03-2025
---0.1567YesNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.51161YesYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.59183NoYes
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.6897NoNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-2.0050NoYes
Apertus-70B-Instruct-2509
$0.82$2.92-0.6960NoYes
gpt-oss-safeguard-20b
--131,0720.23771YesNo
Gemma-4-31B-it-pearl
$0.28$0.86262,1440.5221YesNo
Step-3.5-Flash
$0.10$0.30262,1440.2552YesNo
tiny-aya-fire
---1.85108NoNo
tiny-aya-earth
---0.23133NoNo
Qwen3-VL-30B-A3B-Thinking
$0.20$1.00131,0721.20117YesNo
GLM-4.5
novita
cheapest
$0.60$2.20131,0721.1450YesNo
GLM-4.5
zai-org
fastest
---2.1855YesNo
tiny-aya-water
---1.21117NoNo
command-a-reasoning-08-2025
---0.3382YesNo
GLM-4.6-FP8
---3.4615YesNo
GLM-4.5V-FP8
---2.9019YesNo
GLM-4.6V
---1.7968YesNo
c4ai-command-r7b-arabic-02-2025
---0.2085YesNo
GLM-4.6V-FP8
---1.9669YesNo
aya-vision-32b
---0.2742NoNo
GLM-4.7-FP8
---1.63102YesNo
c4ai-command-r-08-2024
---0.2058YesNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.5655NoYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.7890YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.5930YesYes
DeepSeek-V3.1
$0.27$1.00131,0721.6331YesYes
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.9339YesYes
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.6757YesNo
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.0740YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.2629YesYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.5345NoNo
MiniMax-M1-80k
$0.55$2.201,000,0001.5861YesNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.6728NoNo
GLM-4-32B-0414
$0.55$1.6632,0000.8341NoNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.6459NoYes
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.9187YesNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.4082NoNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.4622NoYes
WizardLM-2-8x22B
$0.62$0.6265,5350.8616NoNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.1766YesYes
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2866NoNo
cogito-671b-v2.1
$1.25$1.25163,8400.2868NoNo
cogito-671b-v2.1
-------
rnj-1-instruct
$0.15$0.1532,7680.17120YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.3542YesYes
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0720.58107YesYes