Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.60$3.381,048,5760.5533YesNo
DeepSeek-V4-Pro
$2.10$4.40512,0000.6733YesYes
DeepSeek-V4-Pro
fireworks-ai
fastest
--1,048,5761.0361YesNo
DeepSeek-V4-Pro
$1.74$3.4865,5360.6450YesYes
DeepSeek-V4-Flash
novita
cheapest fastest
$0.14$0.281,048,5760.9492YesNo
DeepSeek-V4-Flash
---0.6177YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5760.6818YesYes
NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
$0.60$3.60512,2880.31129YesNo
Qwen3.6-27B
---3.0632YesYes
gemma-4-31B-it
$0.14$0.40262,1440.8512YesYes
gemma-4-31B-it
$0.39$0.97262,1440.4127YesYes
gemma-4-31B-it
deepinfra
cheapest fastest
$0.13$0.38262,1441.2743YesYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.26152YesYes
gemma-4-26B-A4B-it
$0.13$0.40262,1440.8042YesNo
gemma-4-26B-A4B-it
deepinfra
cheapest fastest
$0.07$0.34262,1440.3346YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.5416YesNo
Kimi-K2.6
$1.20$4.50262,1440.4233YesYes
Kimi-K2.6
fireworks-ai
fastest
--262,1441.9674YesNo
Kimi-K2.6
$0.75$3.50262,1441.5715YesNo
Llama-3.1-8B-Instruct
novita
cheapest fastest
$0.02$0.0516,3840.70174NoNo
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
-------
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.61149NoYes
Llama-3.1-8B-Instruct
---0.38149YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8001.0152YesNo
MiniMax-M2.7
$0.30$1.20196,6080.3625YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6080.42179YesNo
Qwen3.5-9B
together
fastest
$0.17$0.25262,1440.2384YesYes
Qwen3.5-9B
ovhcloud
cheapest
$0.12$0.18262,1440.5541YesYes
GLM-5.1
together
fastest
$1.40$4.40202,7521.0675YesYes
GLM-5.1
--202,7521.1740YesNo
GLM-5.1
---3.2035YesNo
GLM-5.1
deepinfra
cheapest
$1.05$3.50202,7521.1412YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.25681YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.52118NoYes
gpt-oss-20b
$0.05$0.20131,0720.57160YesYes
gpt-oss-20b
$0.05$0.20131,0720.28109NoNo
gpt-oss-20b
$0.05$0.20131,0720.5873YesNo
gpt-oss-20b
$0.05$0.18131,0720.3262YesYes
gpt-oss-120b
$0.15$0.75131,0720.25418YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.4060YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.231,048YesNo
gpt-oss-120b
$0.22$0.59131,0721.32430YesYes
gpt-oss-120b
$0.10$0.40131,0720.65107YesYes
gpt-oss-120b
$0.15$0.60131,0720.35103YesYes
gpt-oss-120b
$0.15$0.60131,0720.27165YesNo
gpt-oss-120b
---0.41140YesYes
gpt-oss-120b
$0.09$0.47131,0720.38111YesYes
Qwen3-Coder-Next
$0.20$1.50262,1441.05119YesNo
DeepSeek-R1
$0.70$2.5064,0001.4925YesYes
DeepSeek-R1
-------
DeepSeek-R1
-------
Qwen3-VL-8B-Instruct
$0.08$0.50131,0720.7372YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.24111YesNo
Qwen3-8B
$0.07$0.1840,9600.67121YesNo
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0721.1247NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.3476YesNo
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.3561YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.3959YesYes
Meta-Llama-3-8B-Instruct
-------
Meta-Llama-3-8B-Instruct
$0.14$0.148,1921.20110NoYes
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.21285YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.4525YesNo
Llama-3.3-70B-Instruct
-------
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.6737NoNo
Llama-3.3-70B-Instruct
$0.40$0.40131,0721.2884NoNo
Llama-3.3-70B-Instruct
$1.04$1.04131,0720.40105YesYes
Llama-3.3-70B-Instruct
---0.4781YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.4435YesYes
Qwen3.5-122B-A10B
novita
fastest
$0.40$3.20262,1440.7093YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest
$0.29$2.40262,1440.2982YesYes
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.57108YesYes
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.82143NoYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.74329YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.4945NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.6173YesYes
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1440.9996YesNo
Qwen3.5-397B-A17B
together
fastest
$0.60$3.60262,1440.47154YesYes
Qwen3.5-397B-A17B
---1.0544YesYes
Qwen3.5-397B-A17B
$0.71$4.25262,1440.38122YesNo
Qwen3.5-397B-A17B
$0.49$3.60262,1440.3341YesYes
GLM-4.7-Flash
$0.07$0.40200,0000.7258NoNo
GLM-4.7-Flash
-------
DeepSeek-OCR
$0.03$0.038,1921.27171NoNo
Kimi-K2.5
novita
cheapest
$0.60$3.00262,1440.8835YesYes
Kimi-K2.5
fireworks-ai
fastest
--262,1440.2850YesNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.5926YesNo
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.60310NoNo
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8000.9487YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.6099YesNo
DeepSeek-V3-0324
$0.27$1.12163,8400.9436YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
GLM-4.5-Air
novita
cheapest fastest
$0.13$0.85131,0720.8459YesNo
GLM-4.5-Air
---2.4257YesNo
Qwen3-Coder-480B-A35B-Instruct
$0.38$1.55262,1441.2257YesYes
Qwen3-Coder-480B-A35B-Instruct
-------
Qwen3.5-35B-A3B
$0.25$2.00262,1440.80111YesNo
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8001.6043YesNo
GLM-4.6
---3.7520YesNo
GLM-4.6V-Flash
novita
cheapest fastest
$0.30$0.90131,0720.7881YesNo
GLM-4.6V-Flash
---1.9252YesNo
DeepSeek-V3.2
$0.27$0.40163,8401.3937YesYes
Qwen3-14B
$0.07$0.2040,9600.5695YesYes
Step-3.5-Flash
$0.10$0.30262,1440.4435YesNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7680.51149NoYes
gpt-oss-safeguard-20b
--131,0720.24749YesNo
GLM-5
novita
cheapest
$1.00$3.20202,8001.7741YesNo
GLM-5
together
fastest
$1.00$3.20202,7520.6760YesYes
GLM-5
---3.4639YesNo
c4ai-command-a-03-2025
---0.2861YesNo
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.59146NoNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.5718NoYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.7837NoYes
gemma-3-27b-it
---0.5648YesNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.1413NoNo
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.8243YesYes
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0721.2575YesYes
tiny-aya-global
---0.35121NoNo
Qwen3.5-27B
$0.30$2.40262,1440.9050YesNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1441.08121YesYes
Apertus-8B-Instruct-2509
$0.10$0.20-1.15111NoNo
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Gemma-4-31B-it-pearl
$0.28$0.86262,1440.7024YesNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.2250YesYes
Qwen3-235B-A22B-Instruct-2507
-------
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7680.6516YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.2330YesYes
Qwen3-235B-A22B-Instruct-2507
scaleway
fastest
---0.3490YesYes
GLM-5.1-FP8
fireworks-ai
fastest
--202,7521.2744YesNo
GLM-5.1-FP8
---3.7030YesNo
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.26244YesNo
Qwen3-32B
-------
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9600.6648YesYes
Qwen3-32B
$0.09$0.2532,7680.3042YesYes
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2457NoNo
c4ai-command-r7b-12-2024
---0.2582YesNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.4893NoNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.9133YesNo
c4ai-command-r-08-2024
---0.5059YesNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.4625YesNo
tiny-aya-earth
---0.25122NoNo
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0720.8078YesNo
tiny-aya-water
---0.23121NoNo
L3-8B-Stheno-v3.2
$0.05$0.058,1920.7085NoNo
DeepSeek-V3
$0.40$1.3064,0001.2234YesNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.5333NoYes
QwQ-32B
$0.18$0.20131,0720.7049YesNo
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.4245NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0720.6138NoYes
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.3673YesYes
aya-vision-32b
---0.2335NoNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8001.5045YesNo
GLM-4.7
cerebras
fastest
---0.18350YesNo
GLM-4.7
---2.2121YesNo
GLM-4.7-FP8
---1.63102NoNo
cogito-671b-v2.1
$1.25$1.25163,8400.2753NoNo
cogito-671b-v2.1
-------
rnj-1-instruct
$0.15$0.1532,7680.24118YesYes
gemma-3n-E4B-it
$0.06$0.1232,7680.3047NoYes
Arch-Router-1.5B
---0.1079NoYes
GLM-4.6V-FP8
---2.0780YesNo
GLM-4.6V
---2.3072YesNo
GLM-4.5V-FP8
---3.5734YesNo
GLM-4.6-FP8
---3.4615YesNo
tiny-aya-fire
---0.23122NoNo
aya-expanse-32b
---0.2442NoNo
GLM-4.5V
novita
cheapest fastest
$0.60$1.8065,5360.9048YesNo
GLM-4.5V
---2.6630YesNo
command-a-translate-08-2025
---0.4667YesNo
command-a-reasoning-08-2025
---0.3153YesNo
c4ai-command-r7b-arabic-02-2025
---0.2887YesNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.6857YesNo
GLM-4.5
---2.6051YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.6989NoNo
Apertus-70B-Instruct-2509
$0.82$2.92-0.6461NoYes
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0721.0480YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.6029YesYes
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0721.2045YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.3432YesYes
Qwen3-VL-30B-A3B-Thinking
$0.20$1.00131,0721.07117YesNo
MiniMax-M2
$0.30$1.20204,8000.9773YesNo
Kimi-K2-Thinking
$0.60$2.50262,1440.9856NoNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.4951NoYes
MiniMax-M2.1
$0.30$1.20204,8001.2172YesNo
Ling-2.6-1T
$0.30$2.50262,1440.9490YesNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5360.5239NoYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.46151NoNo
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.5793NoYes
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.6850NoYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.2143NoNo
WizardLM-2-8x22B
$0.62$0.6265,5350.9111NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.3375NoNo
Llama-3.1-70B-Instruct
---0.4285YesYes
Qwen3-235B-A22B
$0.20$0.8040,9601.553NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0000.7416YesYes
GLM-4-32B-0414
$0.55$1.6632,0000.7040NoNo
DeepSeek-R1-0528
$0.70$2.50163,8401.7325YesNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
MiniMax-M1-80k
$0.55$2.201,000,0001.2754YesNo
Kimi-K2-Instruct
$0.57$2.30131,0722.4124YesNo
DeepSeek-V3.1
$0.27$1.00131,0721.6829YesYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.1366YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.3648YesYes