Inference Providers

·

Metrics for top trending models

Kimi-K2.7-Code
---2.3625YesNo
Kimi-K2.7-Code
fireworks-ai
fastest
---0.82141YesNo
MiniMax-M3
---1.4331YesNo
MiniMax-M3
together
cheapest
$0.30$1.20524,2880.54117YesYes
MiniMax-M3
fireworks-ai
fastest
---0.52157YesNo
DeepSeek-V4-Pro
novita
cheapest
$1.60$3.381,048,5760.4850YesNo
DeepSeek-V4-Pro
$1.74$3.48512,0001.1150YesYes
DeepSeek-V4-Pro
fireworks-ai
fastest
--1,048,5760.9174YesNo
DeepSeek-V4-Pro
$1.74$3.4865,5360.5652YesYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.22143YesYes
gemma-4-31B-it
novita
fastest
$0.14$0.40262,1440.7150YesNo
gemma-4-31B-it
-------
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.5130YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
together
cheapest
$0.60$3.60512,2880.33119YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
fireworks-ai
fastest
---0.51157YesNo
DeepSeek-V4-Flash
novita
cheapest
$0.14$0.281,048,5760.9479YesNo
DeepSeek-V4-Flash
fireworks-ai
fastest
---0.54129YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5760.4530YesYes
Qwen3.6-27B
---0.2860YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.3344YesYes
Kimi-K2.6
together
fastest
$1.20$4.50262,1440.35131YesYes
Kimi-K2.6
--262,1440.3898YesNo
Kimi-K2.6
$0.75$3.50262,1440.7772YesNo
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.6189NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
nscale
fastest
$0.06$0.06131,0720.63149NoNo
Llama-3.1-8B-Instruct
---0.40148YesYes
gemma-4-26B-A4B-it
novita
fastest
$0.13$0.40262,1440.5445YesYes
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.5123YesYes
gpt-oss-120b
$0.15$0.75131,0720.32430YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.39103YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.21904YesNo
gpt-oss-120b
$0.22$0.59131,0721.32430YesYes
gpt-oss-120b
$0.10$0.40131,0720.48114YesYes
gpt-oss-120b
$0.15$0.60131,0720.26116YesYes
gpt-oss-120b
$0.15$0.60131,0720.40197YesNo
gpt-oss-120b
---0.37139YesYes
gpt-oss-120b
$0.09$0.47131,0720.21119YesYes
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.2966YesYes
Qwen3.5-9B
ovhcloud
cheapest
$0.12$0.18262,1440.4640YesYes
GLM-5.1
together
fastest
$1.40$4.40202,7520.5073YesYes
GLM-5.1
--202,7522.2347YesNo
GLM-5.1
---3.7530YesNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7520.8038YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8001.4039YesNo
MiniMax-M2.7
$0.30$1.20196,6080.3754YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.77172YesNo
Qwen3-Coder-Next
$0.20$1.50262,1441.16119YesNo
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.16736YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0721.30193NoYes
gpt-oss-20b
$0.05$0.20131,0720.54171YesYes
gpt-oss-20b
$0.05$0.20131,0720.25109NoNo
gpt-oss-20b
$0.05$0.20131,0720.50141YesNo
gpt-oss-20b
$0.05$0.18131,0720.3377YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.23120YesYes
Meta-Llama-3-8B-Instruct
-------
Meta-Llama-3-8B-Instruct
$0.14$0.148,1921.01117NoYes
DeepSeek-R1
$0.70$2.5064,0001.7523YesYes
DeepSeek-R1
-------
DeepSeek-R1
-------
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.34135YesYes
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.3512YesYes
Qwen3-VL-8B-Instruct
$0.08$0.50131,0720.5965YesYes
Qwen3-8B
$0.07$0.1840,9601.16125YesNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.32292YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4846YesNo
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.5332NoNo
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.4061NoNo
Llama-3.3-70B-Instruct
$1.04$1.04131,0720.70104YesYes
Llama-3.3-70B-Instruct
---0.4685YesNo
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.2936YesYes
Kimi-K2.5
novita
cheapest
$0.60$3.00262,1441.0935YesYes
Kimi-K2.5
fireworks-ai
fastest
--262,1440.3272YesNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.5349NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.33128YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.46154NoYes
Qwen3.5-35B-A3B
$0.25$2.00262,1440.87101YesNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8001.4650YesNo
GLM-4.7
cerebras
fastest
---0.29426YesNo
GLM-4.7
---2.2121YesNo
DeepSeek-OCR
$0.03$0.038,1921.31112NoNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.50161YesYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.46137YesYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1441.2548YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.54189YesYes
Qwen3.5-397B-A17B
---0.4490YesYes
Qwen3.5-397B-A17B
$0.71$4.25262,1440.37125YesYes
Qwen3.5-397B-A17B
$0.49$3.60262,1440.4925YesNo
GLM-4.7-Flash
novita
cheapest fastest
$0.07$0.40200,0002.0961NoNo
GLM-4.7-Flash
---3.3749NoNo
Qwen3-14B
$0.07$0.2040,9600.5495YesNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.6830NoYes
DeepSeek-V3.2
$0.27$0.40163,8401.1833YesYes
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1440.7488YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.4636YesYes
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0720.7961YesNo
GLM-4.5-Air
zai-org
fastest
---1.8569YesNo
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0721.4092YesNo
gpt-oss-safeguard-20b
--131,0720.41712YesNo
Llama-3.1-70B-Instruct
---0.3983YesYes
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1441.1053YesYes
Qwen3-Coder-480B-A35B-Instruct
-------
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.47336NoNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.1414NoNo
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.15415YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3769NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.5773YesYes
QwQ-32B
$0.18$0.20131,0720.5249YesYes
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.7240NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.5437NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3682YesYes
GLM-5.1-FP8
fireworks-ai
fastest
--202,7520.9964YesNo
GLM-5.1-FP8
---3.8431YesNo
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8001.3170YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.7096YesNo
MiniMax-M2.1
$0.30$1.20204,8001.1275YesNo
tiny-aya-global
---0.38121NoNo
tiny-aya-fire
---0.34132NoNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.5025NoYes
Kimi-K2-Instruct
$0.57$2.30131,0721.4325YesNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.8145YesYes
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.1443YesNo
DeepSeek-R1-0528
$0.70$2.50163,8402.0624YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0720.6496YesYes
DeepSeek-V3-0324
$0.27$1.12163,8401.1633YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
Apertus-8B-Instruct-2509
$0.10$0.20-0.78119NoYes
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.6418YesNo
GLM-5
novita
cheapest
$1.00$3.20202,8002.4438YesNo
GLM-5
together
fastest
$1.00$3.20202,7520.6595YesYes
GLM-5
---3.7835NoNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6989NoNo
MiniMax-M2
$0.30$1.20204,8001.0662YesNo
gemma-3n-E4B-it
$0.06$0.1232,7680.2639NoYes
DeepSeek-V3
$0.40$1.3064,0001.1936YesNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.3247YesYes
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.6214YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.1842YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
---0.3997YesYes
Kimi-K2-Thinking
$0.60$2.50262,1441.0259NoNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0720.7783YesNo
GLM-4.6V-Flash
zai-org
fastest
---1.4884YesNo
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.6191NoYes
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.63172NoYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.47147NoYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.59167NoNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.6241NoYes
rnj-1-instruct
$0.15$0.1532,7680.17114YesYes
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5360.8817YesNo
GLM-4.5V
---3.0517NoNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.7054YesNo
GLM-4.5
---2.2954YesNo
GLM-4.7-FP8
---1.63102YesNo
Step-3.5-Flash
$0.10$0.30262,1440.2244YesNo
c4ai-command-a-03-2025
---0.2163YesNo
c4ai-command-r-08-2024
---0.3757NoNo
Qwen3.5-27B
$0.30$2.40262,1440.8157YesNo
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.3161NoNo
cogito-671b-v2.1
$1.25$1.25163,8400.2760NoNo
cogito-671b-v2.1
-------
GLM-4.6V-FP8
---1.8769YesNo
aya-expanse-32b
---0.3439NoNo
GLM-4.6V
---1.7975YesNo
aya-vision-32b
---0.3036NoNo
Gemma-4-31B-it-pearl
$0.28$0.86262,1441.0614YesNo
c4ai-command-r7b-12-2024
---0.2781YesNo
tiny-aya-earth
---0.31131NoNo
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8001.8658YesNo
GLM-4.6
---3.7520YesNo
GLM-4.5V-FP8
---3.8413NoNo
tiny-aya-water
---0.35130NoNo
command-a-translate-08-2025
---0.3968YesNo
GLM-4.6-FP8
---3.4615YesNo
command-a-reasoning-08-2025
---0.2983YesNo
command-a-vision-07-2025
---0.1547NoNo
c4ai-command-r7b-arabic-02-2025
---0.27101YesNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.9652YesNo
GLM-4-32B-0414
$0.55$1.6632,0001.1636NoNo
Qwen3-235B-A22B
$0.20$0.8040,9600.4112NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0000.7316YesYes
DeepSeek-Prover-V2-671B
$0.70$2.50160,0001.0511NoNo
MiniMax-M1-80k
$0.55$2.201,000,0001.2059YesNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.3041NoNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.31252YesNo
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.5743YesYes
Qwen3-32B
$0.09$0.2532,7680.2641YesYes
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.5653NoYes
DeepSeek-V3.1
$0.27$1.00131,0722.3434YesYes
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.5021YesNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.92165YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.7526YesYes
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.0326YesYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Arch-Router-1.5B
---0.1080NoYes
gemma-3-27b-it
---0.4848YesYes
Ling-2.6-1T
$0.30$2.50262,1441.3883YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.71110NoNo
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.1766YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.3248YesYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.0250NoYes
Apertus-70B-Instruct-2509
$0.82$2.92-0.6258NoYes
WizardLM-2-8x22B
$0.62$0.6265,5350.8829NoNo
Qwen3-VL-30B-A3B-Thinking
$0.20$1.00131,0721.0878YesNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.3682NoNo
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.4059NoYes