Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.74$3.481,048,5761.3532YesNo
DeepSeek-V4-Pro
$2.10$4.40512,0001.3818YesYes
DeepSeek-V4-Pro
fireworks-ai
fastest
--1,048,5760.6444NoYes
Kimi-K2.6
novita
cheapest
$0.95$4.00262,1441.8118YesNo
Kimi-K2.6
$1.20$4.50262,1442.0118YesYes
Kimi-K2.6
fireworks-ai
fastest
--262,1440.5627YesNo
gemma-4-31B-it
novita
cheapest fastest
$0.14$0.40262,1440.7418NoYes
gemma-4-31B-it
$0.20$0.50262,1440.3814YesYes
GLM-5.1
together
cheapest
$1.40$4.40202,7521.7122YesYes
GLM-5.1
--202,7520.9427YesNo
GLM-5.1
zai-org
fastest
---3.8033YesNo
gemma-4-26B-A4B-it
$0.13$0.40262,1440.9243YesYes
MiniMax-M2.7
novita
cheapest fastest
$0.30$1.20204,8000.9043YesNo
MiniMax-M2.7
$0.30$1.20196,6080.4436YesYes
MiniMax-M2.7
--196,6080.9617YesNo
Qwen3.5-9B
$0.10$0.15262,1440.3479YesYes
gpt-oss-120b
$0.15$0.75131,0720.29423YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.4951YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.151,172YesNo
gpt-oss-120b
$0.22$0.59131,0720.46605YesYes
gpt-oss-120b
$0.10$0.40131,0720.90114YesYes
gpt-oss-120b
$0.15$0.60131,0720.2974YesYes
gpt-oss-120b
$0.15$0.60131,0720.3467YesNo
gpt-oss-120b
---0.32149YesYes
gpt-oss-120b
$0.09$0.47131,0720.3071YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.24122YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.4752NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.241,068NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.7560NoYes
Llama-3.1-8B-Instruct
---0.28144YesYes
DeepSeek-R1
$0.70$2.5064,0001.3617YesYes
DeepSeek-R1
-------
DeepSeek-R1
hyperbolic
cheapest fastest
$2.00$2.00163,8400.9398NoNo
DeepSeek-R1
$3.00$7.00163,8400.5963NoYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.50597YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.75114NoYes
gpt-oss-20b
$0.05$0.20131,0720.88154YesYes
gpt-oss-20b
$0.05$0.20131,0720.35108YesYes
gpt-oss-20b
$0.05$0.20131,0722.6691YesNo
gpt-oss-20b
$0.05$0.18131,0720.30103YesNo
Qwen3-Coder-Next
$0.20$1.50262,1441.01124YesNo
Kimi-K2.5
$0.60$3.00262,1441.4639YesYes
Kimi-K2.5
together
cheapest
$0.50$2.80262,1440.5133YesYes
Kimi-K2.5
fireworks-ai
fastest
--262,1440.2865YesNo
Qwen3.5-27B
$0.30$2.40262,1441.0158YesNo
Qwen3-Coder-30B-A3B-Instruct
---0.5239YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest fastest
$0.07$0.26262,1440.3854YesYes
Qwen3.5-35B-A3B
$0.25$2.00262,1440.79101YesNo
DeepSeek-V3.2
novita
cheapest
$0.27$0.40163,8401.2229YesYes
DeepSeek-V3.2
fireworks-ai
fastest
--163,8403.1448YesNo
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.4684NoYes
Llama-3.3-70B-Instruct
$0.59$0.79131,0720.23272YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4244YesNo
Llama-3.3-70B-Instruct
sambanova
fastest
$0.60$1.20131,0720.59286YesYes
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.33103YesYes
Llama-3.3-70B-Instruct
$0.90$0.90131,0720.39102NoNo
Llama-3.3-70B-Instruct
---0.3575YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.4636YesYes
Qwen3-8B
nscale
cheapest
$0.07$0.1840,9600.8558YesNo
Qwen3-8B
fireworks-ai
fastest
--40,9600.22139YesNo
Llama-3.2-1B-Instruct
--131,0000.47197NoNo
Arch-Router-1.5B
---0.1277NoYes
MiMo-V2-Flash
$0.10$0.30262,1441.6886YesNo
GLM-5
novita
cheapest
$1.00$3.20202,8001.7836NoNo
GLM-5
$1.00$3.20202,7520.6249YesYes
GLM-5
fireworks-ai
fastest
--202,7521.3364YesNo
GLM-5
---3.7537NoNo
Qwen3.5-122B-A10B
$0.40$3.20262,1440.6988YesNo
Apertus-8B-Instruct-2509
$0.10$0.20-1.2673NoYes
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.8427NoYes
Qwen3.5-397B-A17B
-------
Qwen3.5-397B-A17B
together
cheapest fastest
$0.60$3.60262,1440.6163YesYes
Qwen3.5-397B-A17B
---0.5025YesYes
Qwen3-VL-8B-Instruct
$0.08$0.50131,0720.6343YesYes
Qwen3-VL-8B-Instruct
-------
Qwen3-VL-30B-A3B-Instruct
novita
cheapest
$0.20$0.70131,0720.62109YesYes
Qwen3-VL-30B-A3B-Instruct
fireworks-ai
fastest
--262,1440.26141YesNo
DeepSeek-OCR
$0.03$0.038,1920.55199NoNo
gpt-oss-safeguard-20b
--131,0720.38726YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.2325YesYes
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.53296YesNo
Qwen3-32B
$0.10$0.4540,9600.7448NoNo
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.7926YesYes
Qwen3-32B
$0.09$0.2532,7680.3737YesYes
GLM-5.1-FP8
fireworks-ai
fastest
--202,7521.5432YesNo
GLM-5.1-FP8
---3.6632YesNo
Qwen3-30B-A3B
$0.09$0.4540,9600.7169YesNo
DeepSeek-V3.1
novita
cheapest
$0.27$1.00131,0721.5524YesYes
DeepSeek-V3.1
together
fastest
$0.60$1.70131,0720.4453YesYes
DeepSeek-V3.1
--163,8400.3736NoNo
DeepSeek-V3
novita
fastest
$0.40$1.3064,0001.1435YesNo
DeepSeek-V3
together
cheapest
$1.25$1.25131,0720.3431YesYes
Kimi-K2-Instruct
$0.57$2.30131,0720.9329YesNo
DeepSeek-V3-0324
novita
cheapest
$0.27$1.12163,8400.8835YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
hyperbolic
fastest
$1.25$1.25163,8400.7659NoNo
DeepSeek-V3-0324
$1.25$1.25131,0720.6041YesYes
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.30$1.30262,1441.0954YesYes
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
fastest
$2.00$2.00262,1440.4776NoNo
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.2270YesYes
QwQ-32B
$0.18$0.20131,0720.8229NoYes
c4ai-command-r7b-12-2024
---0.2186YesNo
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.85141NoNo
gemma-3-27b-it
---0.4433YesYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.7872YesNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.7013NoNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8000.7539YesNo
GLM-4.7
cerebras
fastest
---0.20457YesNo
GLM-4.7
--202,7520.8489YesNo
GLM-4.7
---2.6841YesNo
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8000.8953YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.4387YesNo
Hermes-2-Pro-Llama-3-8B
$0.14$0.148,1920.45110NoNo
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.7857NoNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0721.3033YesNo
GLM-4.6V-Flash
zai-org
fastest
---1.7976NoNo
GLM-4.6
novita
cheapest
$0.55$2.20204,8000.7630YesNo
GLM-4.6
zai-org
fastest
---3.2533YesNo
GLM-4.6V
---2.9736YesNo
DeepSeek-R1-0528
novita
cheapest
$0.70$2.50163,8401.6218YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
$3.00$3.00163,8400.7357NoNo
DeepSeek-R1-0528
together
fastest
$3.00$7.00163,8400.5069NoYes
DeepSeek-R1-Distill-Llama-70B
novita
cheapest
$0.80$0.808,1920.5234NoNo
DeepSeek-R1-Distill-Llama-70B
-------
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3771YesYes
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.8025YesNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.8096YesNo
Qwen2.5-Coder-32B-Instruct
-------
Qwen2.5-Coder-32B-Instruct
---0.3374YesNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.1244NoNo
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.14177YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.9424YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1442.6624YesYes
Qwen3-235B-A22B-Instruct-2507
---0.9053YesYes
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5360.9145YesNo
GLM-4.5V
---2.6539YesNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.1811NoNo
gemma-3n-E4B-it
$0.06$0.1232,7680.3214NoYes
Qwen3-Coder-Next-FP8
$0.50$1.20262,1440.61136YesYes
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0721.03394YesYes
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.5424YesYes
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.0445YesNo
Kimi-K2-Thinking
$0.60$2.50262,1441.2230YesNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0001.106NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.5838NoNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7681.0871NoYes
Qwen3-14B
$0.07$0.2040,9600.7552YesYes
Llama-4-Scout-17B-16E-Instruct
groq
cheapest fastest
$0.11$0.34131,0720.47349YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.3923NoNo
Llama-4-Scout-17B-16E-Instruct
-------
tiny-aya-fire
---0.19123NoNo
c4ai-command-a-03-2025
---1.3546YesNo
L3-70B-Euryale-v2.1
$1.48$1.488,1920.5335NoNo
Qwen3-VL-30B-A3B-Thinking
novita
cheapest
$0.20$1.00131,0720.81120YesNo
Qwen3-VL-30B-A3B-Thinking
fireworks-ai
fastest
--262,1440.31130YesNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.7071NoNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.4824NoYes
rnj-1-instruct
$0.15$0.1532,7680.22118YesYes
tiny-aya-earth
---1.18106NoNo
tiny-aya-global
---0.17122NoNo
tiny-aya-water
---1.52103NoNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.6252NoNo
GLM-4.5
---2.2247YesNo
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0720.7870YesNo
GLM-4.5-Air
zai-org
fastest
---2.0472YesNo
command-a-translate-08-2025
---0.3867YesNo
command-a-reasoning-08-2025
---0.3582YesNo
GLM-4.6-FP8
---3.5725YesNo
GLM-4.5V-FP8
---2.5734YesNo
command-a-vision-07-2025
---0.3346NoNo
c4ai-command-r7b-arabic-02-2025
---0.17104YesNo
GLM-4.6V-FP8
---2.7939YesNo
aya-vision-32b
---0.5436NoNo
GLM-4.7-FP8
---1.8672YesNo
aya-expanse-32b
---0.1841NoNo
c4ai-command-r-08-2024
---0.2733NoNo
Qwen3-235B-A22B
$0.20$0.8040,9600.676NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.0221YesYes
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.4527NoYes
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.8725NoYes
Apertus-70B-Instruct-2509
$0.82$2.92-1.1658NoYes
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.6047NoYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.5045YesYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.3865YesYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
MiniMax-M2.1
$0.30$1.20204,8001.3852YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.7423NoNo
MiniMax-M2
$0.30$1.20204,8002.2653YesNo
cogito-671b-v2.1
$1.25$1.25163,8400.8416NoNo
cogito-671b-v2.1
-------
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.6145YesYes
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.9397YesNo
Llama-3.1-70B-Instruct
---0.3676YesYes
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.8244YesNo
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.1042NoNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.5820NoYes
MiniMax-M1-80k
$0.55$2.201,000,0001.0950YesNo
GLM-4-32B-0414
$0.55$1.6632,0001.0935NoNo
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.2568YesYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.4223NoYes
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.3914NoNo