Inference Providers

·

Metrics for top trending models

DeepSeek-V4-Pro
novita
cheapest
$1.64$3.381,048,5760.9239YesNo
DeepSeek-V4-Pro
$2.10$4.40512,0000.4741YesYes
DeepSeek-V4-Pro
fireworks-ai
fastest
--1,048,5761.4454YesNo
DeepSeek-V4-Pro
$1.74$3.4865,5362.3420YesYes
DeepSeek-V4-Flash
novita
cheapest fastest
$0.14$0.281,048,5760.91100YesNo
DeepSeek-V4-Flash
---0.6259YesNo
DeepSeek-V4-Flash
$0.14$0.281,048,5760.7014YesYes
Qwen3.6-35B-A3B
$0.15$0.95262,1440.37140YesYes
gemma-4-31B-it
novita
fastest
$0.14$0.40262,1441.3339NoYes
gemma-4-31B-it
$0.39$0.97262,1441.0410YesYes
gemma-4-31B-it
deepinfra
cheapest
$0.13$0.38262,1440.4538YesYes
Kimi-K2.6
novita
cheapest
$0.80$3.40262,1441.7647YesNo
Kimi-K2.6
together
fastest
$1.20$4.50262,1440.3648YesYes
Kimi-K2.6
--262,1441.0634YesNo
Kimi-K2.6
$0.75$3.50262,1440.7514YesNo
GLM-5.1
$1.40$4.40202,7520.5756YesYes
GLM-5.1
--202,7521.1755YesNo
GLM-5.1
---3.5034YesNo
GLM-5.1
deepinfra
cheapest fastest
$1.05$3.50202,7520.6566YesYes
gemma-4-26B-A4B-it
novita
fastest
$0.13$0.40262,1441.8146NoNo
gemma-4-26B-A4B-it
deepinfra
cheapest
$0.07$0.34262,1440.4534YesYes
Llama-3.1-8B-Instruct
novita
cheapest
$0.02$0.0516,3840.4353NoNo
Llama-3.1-8B-Instruct
cerebras
fastest
$0.10$0.10-0.171,369NoNo
Llama-3.1-8B-Instruct
$0.10$0.2016,3840.49675NoYes
Llama-3.1-8B-Instruct
$0.06$0.06131,0720.8159NoYes
Llama-3.1-8B-Instruct
---0.28127YesYes
Qwen3.5-9B
together
cheapest fastest
$0.10$0.15262,1440.2565YesYes
Qwen3.5-9B
$0.12$0.18262,1440.2941YesYes
gpt-oss-20b
groq
fastest
$0.10$0.50131,0720.14856YesNo
gpt-oss-20b
novita
cheapest
$0.04$0.15131,0720.4687NoYes
gpt-oss-20b
$0.05$0.20131,0720.97157YesYes
gpt-oss-20b
$0.05$0.20131,0720.29104YesNo
gpt-oss-20b
$0.05$0.20131,0720.9854YesNo
gpt-oss-20b
$0.05$0.18131,0720.3282YesYes
gpt-oss-120b
$0.15$0.75131,0720.18441YesNo
gpt-oss-120b
novita
cheapest
$0.05$0.25131,0720.50250YesYes
gpt-oss-120b
cerebras
fastest
$0.25$0.69-0.20966YesNo
gpt-oss-120b
$0.22$0.59131,0720.69552YesYes
gpt-oss-120b
$0.10$0.40131,0720.92117YesYes
gpt-oss-120b
$0.15$0.60131,0720.26144YesYes
gpt-oss-120b
$0.15$0.60131,0720.37177YesNo
gpt-oss-120b
---0.38162YesYes
gpt-oss-120b
$0.09$0.47131,0720.2295YesYes
Qwen2.5-7B-Instruct
$0.30$0.3032,7680.3486YesNo
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
---0.34107YesNo
Qwen3-Coder-30B-A3B-Instruct
ovhcloud
cheapest
$0.07$0.26262,1440.3923YesYes
MiniMax-M2.7
novita
cheapest
$0.30$1.20204,8000.8633YesNo
MiniMax-M2.7
$0.30$1.20196,6080.3222YesYes
MiniMax-M2.7
fireworks-ai
fastest
--196,6081.36137YesNo
Llama-3.2-1B-Instruct
--131,0000.52193NoNo
Meta-Llama-3-8B-Instruct
$0.04$0.048,1920.5086NoYes
Qwen3-Coder-Next
$0.20$1.50262,1441.16123YesNo
Kimi-K2.5
novita
cheapest
$0.60$3.00262,1441.0838YesYes
Kimi-K2.5
-------
Kimi-K2.5
fireworks-ai
fastest
--262,1440.9199YesNo
Qwen3.5-35B-A3B
$0.25$2.00262,1440.8295YesNo
Llama-3.3-70B-Instruct
groq
fastest
$0.59$0.79131,0720.19290YesNo
Llama-3.3-70B-Instruct
novita
cheapest
$0.14$0.40131,0720.5442YesNo
Llama-3.3-70B-Instruct
$0.60$1.20131,0720.39289YesYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.9417NoYes
Llama-3.3-70B-Instruct
$0.40$0.40131,0720.8271NoNo
Llama-3.3-70B-Instruct
$0.88$0.88131,0720.39113YesYes
Llama-3.3-70B-Instruct
---0.3876YesYes
Llama-3.3-70B-Instruct
$0.74$0.74131,0720.3136YesYes
Step-3.5-Flash
$0.10$0.30262,1440.2845YesNo
Qwen3-4B-Instruct-2507
$0.01$0.03262,1440.7986YesNo
GLM-4.7-Flash
novita
cheapest fastest
$0.07$0.40200,0000.8661YesNo
GLM-4.7-Flash
---2.8156YesNo
DeepSeek-OCR
$0.03$0.038,1921.19128NoNo
Qwen3-8B
$0.07$0.1840,9601.0357YesNo
Qwen3.5-397B-A17B
novita
cheapest
$0.60$3.60262,1440.9689YesNo
Qwen3.5-397B-A17B
$0.60$3.60262,1440.5388YesYes
Qwen3.5-397B-A17B
scaleway
fastest
---0.41111YesYes
Qwen3.5-397B-A17B
$0.71$4.25262,1440.27106YesYes
Qwen3.5-397B-A17B
$0.49$3.60262,1440.3824YesYes
Qwen3.5-27B
$0.30$2.40262,1440.6047YesNo
Qwen3-VL-8B-Instruct
$0.08$0.50131,0720.6741YesYes
Qwen3-VL-8B-Instruct
-------
Ling-2.6-1T
$0.30$2.50262,1441.1781YesNo
QwQ-32B
$0.18$0.20131,0720.9329YesYes
DeepSeek-R1
$0.70$2.5064,0001.7721YesYes
DeepSeek-R1
-------
DeepSeek-R1
-------
DeepSeek-R1
-------
gpt-oss-safeguard-20b
--131,0720.59693YesNo
MiniMax-M2.5
novita
cheapest
$0.30$1.20204,8000.8671YesNo
MiniMax-M2.5
fireworks-ai
fastest
---0.51140YesNo
Qwen3-4B-Thinking-2507
$0.01$0.03262,1440.9293YesNo
gemma-3-27b-it
---0.5548YesYes
Llama-4-Scout-17B-16E-Instruct
groq
fastest
$0.11$0.34131,0720.76325YesNo
Llama-4-Scout-17B-16E-Instruct
$0.18$0.59131,0720.4553NoNo
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
$0.09$0.29890,0000.7533YesYes
DeepSeek-V3
$0.40$1.3064,0001.1033YesNo
DeepSeek-V3
-------
L3-8B-Stheno-v3.2
$0.05$0.058,1920.6195NoNo
GLM-5
novita
cheapest
$1.00$3.20202,8001.1933YesNo
GLM-5
together
fastest
$1.00$3.20202,7520.7097YesYes
GLM-5
---3.6335NoNo
Qwen3-30B-A3B
$0.09$0.4540,9600.7146YesNo
Qwen3.5-122B-A10B
$0.40$3.20262,1440.7186YesNo
Qwen3.5-122B-A10B
deepinfra
cheapest fastest
$0.29$2.40262,1440.3396YesYes
tiny-aya-earth
---0.23122NoNo
DeepSeek-R1-Distill-Qwen-14B
$0.20$0.20131,0720.8833NoYes
Apertus-8B-Instruct-2509
$0.10$0.20-0.69116NoYes
EuroLLM-22B-Instruct-2512
$0.10$0.20-2.313NoNo
GLM-5.1-FP8
fireworks-ai
fastest
--202,7520.8747YesNo
GLM-5.1-FP8
---3.3734YesNo
GLM-4.7
novita
cheapest
$0.60$2.20204,8001.4259YesNo
GLM-4.7
cerebras
fastest
---0.16495YesNo
GLM-4.7
---2.2121YesNo
Qwen2.5-VL-72B-Instruct
$1.01$1.0132,7680.3827NoYes
Qwen3-Next-80B-A3B-Instruct
$0.15$1.50131,0721.0780YesNo
Qwen2.5-72B-Instruct
$0.38$0.4032,0000.5429YesNo
Qwen3-VL-235B-A22B-Instruct
$0.30$1.50131,0720.6831YesYes
Qwen3-VL-235B-A22B-Thinking
$0.98$3.95131,0720.8448YesNo
DeepSeek-V3-0324
$0.27$1.12163,8400.8633YesNo
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
DeepSeek-V3-0324
-------
Apertus-70B-Instruct-2509
$0.82$2.92-0.5955NoYes
Qwen3-32B
groq
fastest
$0.29$0.59131,0720.31260YesNo
Qwen3-32B
$0.10$0.4540,9600.31102NoNo
Qwen3-32B
nscale
cheapest
$0.08$0.2540,9601.0125YesYes
Qwen3-32B
$0.09$0.2532,7680.3539YesYes
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
$0.38$1.55262,1441.1058YesYes
Qwen3-Coder-480B-A35B-Instruct
$2.00$2.00262,1440.6076NoNo
Qwen3-Coder-480B-A35B-Instruct
together
fastest
$2.00$2.00262,1440.2092YesYes
Kimi-K2-Instruct
$0.57$2.30131,0721.3526YesNo
WizardLM-2-8x22B
$0.62$0.6265,5350.6415NoNo
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
$0.09$0.58131,0721.0845YesYes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
$0.60$1.20-0.21584YesNo
Qwen3-235B-A22B-Instruct-2507
$0.20$0.6032,7681.0924YesYes
Qwen3-235B-A22B-Instruct-2507
$0.20$0.60262,1440.2241YesYes
Qwen3-235B-A22B-Instruct-2507
---0.8543YesYes
gemma-3n-E4B-it
$0.06$0.1232,7680.2148NoYes
tiny-aya-fire
---0.27120NoNo
tiny-aya-global
---0.35119NoNo
tiny-aya-water
---0.84113NoNo
Llama-Guard-4-12B
$0.20$0.201,048,5760.1911NoNo
GLM-4.5-Air
novita
cheapest
$0.13$0.85131,0720.8755NoNo
GLM-4.5-Air
zai-org
fastest
---1.9166YesNo
GLM-4.6V-Flash
novita
cheapest
$0.30$0.90131,0720.8643YesNo
GLM-4.6V-Flash
zai-org
fastest
---1.4685YesNo
GLM-4.7-FP8
---1.63102YesNo
c4ai-command-a-03-2025
---0.3530YesNo
MiniMax-M2.1
$0.30$1.20204,8001.1866YesNo
MiMo-V2-Flash
$0.10$0.30262,1441.1890YesNo
AutoGLM-Phone-9B-Multilingual
$0.04$0.1465,5360.7045NoNo
Kimi-K2-Instruct-0905
$0.60$2.50262,1441.3811YesNo
MiniMax-M2
$0.30$1.20204,8001.7361YesNo
Mixtral-8x22B-Instruct-v0.1
$1.20$1.2065,5361.1325NoYes
DeepSeek-R1-Distill-Qwen-7B
$0.15$0.15131,0720.9365NoNo
Kimi-K2-Thinking
$0.60$2.50262,1441.1627YesNo
Qwen3-Next-80B-A3B-Thinking
$0.15$1.50131,0720.87106YesNo
Qwen3-VL-30B-A3B-Instruct
$0.20$0.70131,0720.87111YesYes
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
$0.06$0.20131,0720.8227NoYes
Qwen2.5-Coder-32B-Instruct
scaleway
fastest
---0.3891YesNo
DeepSeek-R1-Distill-Qwen-32B
$0.30$0.30131,0720.9825NoYes
DeepSeek-V3.2
$0.27$0.40163,8401.4434YesYes
Qwen3-VL-30B-A3B-Thinking
$0.20$1.00131,0721.11117YesNo
DeepSeek-V3.1-Terminus
$0.27$1.00131,0721.5624YesYes
GLM-4.6
novita
cheapest fastest
$0.55$2.20204,8001.6060YesNo
GLM-4.6
---3.7520YesNo
DeepSeek-V3.2-Exp
$0.27$0.41163,8401.1027YesYes
rnj-1-instruct
$0.15$0.1532,7680.21122YesYes
cogito-671b-v2.1
$1.25$1.25163,8400.2858NoNo
cogito-671b-v2.1
-------
cogito-671b-v2.1-FP8
$1.25$1.25163,8400.2357NoNo
Qwen2.5-Coder-7B-Instruct
$0.01$0.03131,0720.8460NoYes
Qwen3-Coder-480B-A35B-Instruct-FP8
$2.00$2.00262,1440.1784YesYes
command-a-translate-08-2025
---0.3370YesNo
command-a-reasoning-08-2025
---0.4179YesNo
command-a-vision-07-2025
---0.1947NoNo
c4ai-command-r7b-arabic-02-2025
---0.2672YesNo
aya-vision-32b
---0.2537NoNo
Gemma-4-31B-it-pearl
$0.28$0.8632,0000.3931YesNo
aya-expanse-32b
---0.1841NoNo
GLM-4.5
novita
cheapest fastest
$0.60$2.20131,0720.8856YesNo
GLM-4.5
---2.3645YesNo
GLM-4.5V
novita
cheapest
$0.60$1.8065,5360.9223NoNo
GLM-4.5V
zai-org
fastest
---3.1131NoNo
GLM-4.6-FP8
---3.4615NoNo
GLM-4.5V-FP8
---2.8918YesNo
GLM-4.6V
---2.8134YesNo
GLM-4.6V-FP8
---3.9245YesNo
c4ai-command-r-08-2024
---0.1758YesNo
c4ai-command-r7b-12-2024
---0.2192YesNo
DeepSeek-Prover-V2-671B
$0.70$2.50160,0000.5515NoNo
GLM-4-32B-0414
$0.55$1.6632,0000.8348NoNo
Qwen3-235B-A22B
$0.20$0.8040,9600.4220NoNo
Qwen3-235B-A22B
nscale
cheapest fastest
$0.20$0.6032,0001.2423YesYes
DictaLM-3.0-24B-Thinking
$0.20$0.40-1.0865YesYes
Qwen-SEA-LION-v4-32B-IT
$0.25$0.50-1.2248YesYes
Olmo-3-7B-Instruct
$0.10$0.20---YesNo
Gemma-SEA-LION-v4-27B-IT
$0.20$0.40-1.4451NoYes
Llama-4-Maverick-17B-128E-Instruct-FP8
$0.27$0.851,048,5760.5814NoYes
DeepSeek-R1-0528
$0.70$2.50163,8401.8524NoNo
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
DeepSeek-R1-0528
-------
MiniMax-M1-80k
$0.55$2.201,000,0001.2561YesNo
ERNIE-4.5-300B-A47B-Base-PT
$0.28$1.10123,0001.8621NoYes
ERNIE-4.5-VL-424B-A47B-Base-PT
$0.42$1.25123,0001.1043NoNo
Qwen3-14B
$0.07$0.2040,9600.9450YesNo
Qwen3-235B-A22B-Thinking-2507
$0.30$3.00131,0720.8143YesNo
DeepSeek-R1-Distill-Llama-70B
$0.80$0.808,1920.3643NoNo
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
$0.75$0.75131,0721.1417NoNo
DeepSeek-R1-Distill-Llama-70B
scaleway
fastest
---0.4384YesYes
Arch-Router-1.5B
---0.1080NoYes
DeepSeek-V3.1
$0.27$1.00131,0721.4927YesYes
DeepSeek-V3.1
-------
Llama-3.1-70B-Instruct
---0.4885YesNo
Qwen2.5-Coder-3B-Instruct
$0.01$0.0332,7681.0078NoYes
DeepSeek-R1-Distill-Llama-8B
$0.05$0.05131,0720.8057NoYes
DeepSeek-R1-Distill-Qwen-1.5B
$0.10$0.10131,0720.78141NoNo
Meta-Llama-3-70B-Instruct
$0.51$0.748,1920.4522NoYes
L3-70B-Euryale-v2.1
$1.48$1.488,1920.6037NoNo
L3-8B-Lunaris-v1
$0.05$0.058,1920.6137NoNo
Llama-4-Maverick-17B-128E-Instruct
$0.63$1.80131,0721.20364YesYes